Generalizing to Unseen Domains: A Survey on Domain Generalization

Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interest...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on knowledge and data engineering Ročník 35; číslo 8; s. 8052 - 8072
Hlavní autoři: Wang, Jindong, Lan, Cuiling, Liu, Chang, Ouyang, Yidong, Qin, Tao, Lu, Wang, Chen, Yiqiang, Zeng, Wenjun, Yu, Philip S.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.08.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1041-4347, 1558-2191
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future.
AbstractList Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future.
Author Zeng, Wenjun
Lu, Wang
Wang, Jindong
Ouyang, Yidong
Yu, Philip S.
Qin, Tao
Chen, Yiqiang
Lan, Cuiling
Liu, Chang
Author_xml – sequence: 1
  givenname: Jindong
  orcidid: 0000-0002-4833-0880
  surname: Wang
  fullname: Wang, Jindong
  email: jindong.wang@microsoft.com
  organization: Microsoft Research Asia, Beijing, China
– sequence: 2
  givenname: Cuiling
  orcidid: 0000-0001-9145-9957
  surname: Lan
  fullname: Lan, Cuiling
  email: culan@microsoft.com
  organization: Microsoft Research Asia, Beijing, China
– sequence: 3
  givenname: Chang
  surname: Liu
  fullname: Liu, Chang
  email: changliu@microsoft.com
  organization: Microsoft Research Asia, Beijing, China
– sequence: 4
  givenname: Yidong
  surname: Ouyang
  fullname: Ouyang, Yidong
  email: yidongouyang@link.cuhk.edu.cn
  organization: School of Data Science, Chinese University of Hong Kong, Shenzhen, China
– sequence: 5
  givenname: Tao
  orcidid: 0000-0002-9095-0776
  surname: Qin
  fullname: Qin, Tao
  email: taoqin@microsoft.com
  organization: Microsoft Research Asia, Beijing, China
– sequence: 6
  givenname: Wang
  orcidid: 0000-0003-4035-0737
  surname: Lu
  fullname: Lu, Wang
  email: luwang@ict.ac.cn
  organization: Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
– sequence: 7
  givenname: Yiqiang
  orcidid: 0000-0002-8407-0780
  surname: Chen
  fullname: Chen, Yiqiang
  email: yqchen@ict.ac.cn
  organization: Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
– sequence: 8
  givenname: Wenjun
  orcidid: 0000-0003-2531-3137
  surname: Zeng
  fullname: Zeng, Wenjun
  email: wezeng@microsoft.com
  organization: Microsoft Research Asia, Beijing, China
– sequence: 9
  givenname: Philip S.
  orcidid: 0000-0002-3491-5968
  surname: Yu
  fullname: Yu, Philip S.
  email: psyu@uic.edu
  organization: University of Illinois at Chicago, Chicago, IL, USA
BookMark eNp9kMFOAjEQhhuDiYg-gPGyiefFmXa723ojoGgk8SCcN-1u15RAi-1iok_vIsjBg6eZTP5vJvOdk57zzhByhTBEBHk7f57cDylQOmRYCKTihPSRc5FSlNjresgwzVhWnJHzGJcAILpYn4ymxpmgVvbLurek9cnCRWNcMvFrZV28S0bJ6zZ8mM_E_w6TI6Ja690FOW3UKprLQx2QxcP9fPyYzl6mT-PRLK0Yl22aa-QSNas543WuoWoazDlIYxQaUEprlFDTRsucGUHrRuRFTSudKV3VGiQbkJv93k3w71sT23Lpt8F1J0sqWMaAC5Z3KdynquBjDKYpN8GuVfgsEcqdqXJnqtyZKg-mOqb4w1S2_fmtDcqu_iWv96Q1xhwvyUJQDsC-Ad9md9Y
CODEN ITKEEH
CitedBy_id crossref_primary_10_1088_1361_6501_adeaca
crossref_primary_10_1016_j_engappai_2023_106248
crossref_primary_10_1016_j_knosys_2024_111506
crossref_primary_10_1016_j_measurement_2024_115674
crossref_primary_10_1088_1361_6560_ad341a
crossref_primary_10_1007_s13042_024_02219_y
crossref_primary_10_1109_TIM_2025_3569001
crossref_primary_10_1016_j_patcog_2024_110656
crossref_primary_10_1093_bib_bbaf294
crossref_primary_10_1145_3659943
crossref_primary_10_1109_TIM_2023_3267520
crossref_primary_10_1109_TCAD_2024_3447208
crossref_primary_10_1109_TKDE_2023_3271851
crossref_primary_10_1007_s11227_024_06622_8
crossref_primary_10_1016_j_neunet_2024_106099
crossref_primary_10_1109_TGRS_2024_3413542
crossref_primary_10_1109_TIE_2023_3250768
crossref_primary_10_1109_MC_2024_3449435
crossref_primary_10_1109_JBHI_2023_3337072
crossref_primary_10_1007_s13748_025_00402_y
crossref_primary_10_1109_TIP_2024_3437212
crossref_primary_10_1016_j_neunet_2023_12_017
crossref_primary_10_1109_ACCESS_2023_3276775
crossref_primary_10_1007_s11760_022_02394_x
crossref_primary_10_1109_TKDE_2024_3374373
crossref_primary_10_1007_s10626_025_00421_w
crossref_primary_10_1109_JPROC_2023_3309299
crossref_primary_10_1145_3625238
crossref_primary_10_1016_j_actaastro_2023_08_001
crossref_primary_10_1109_TSG_2024_3452490
crossref_primary_10_1016_j_neunet_2023_12_014
crossref_primary_10_1109_TIM_2022_3217870
crossref_primary_10_1007_s10462_024_10745_y
crossref_primary_10_1016_j_chaos_2024_114811
crossref_primary_10_1145_3649900
crossref_primary_10_1109_TIV_2024_3364714
crossref_primary_10_1088_2632_2153_ad5a60
crossref_primary_10_1016_j_asoc_2025_113495
crossref_primary_10_1109_TGRS_2024_3506749
crossref_primary_10_3389_fnins_2024_1293962
crossref_primary_10_1145_3729483
crossref_primary_10_1016_j_media_2024_103282
crossref_primary_10_1088_1361_6501_acc04a
crossref_primary_10_1016_j_knosys_2025_113316
crossref_primary_10_1109_TAFFC_2024_3462603
crossref_primary_10_1007_s11263_024_02106_7
crossref_primary_10_1016_j_ress_2023_109188
crossref_primary_10_1109_JSTARS_2025_3582949
crossref_primary_10_1016_j_knosys_2023_111331
crossref_primary_10_1109_TIM_2025_3545703
crossref_primary_10_1109_JIOT_2025_3558163
crossref_primary_10_1109_TCE_2025_3529613
crossref_primary_10_1016_j_ress_2023_109516
crossref_primary_10_1109_ACCESS_2024_3425602
crossref_primary_10_1016_j_knosys_2025_113422
crossref_primary_10_1007_s10586_024_04933_2
crossref_primary_10_1109_JIOT_2024_3387538
crossref_primary_10_1029_2024JH000550
crossref_primary_10_1109_TIP_2025_3592549
crossref_primary_10_1038_s41524_024_01316_4
crossref_primary_10_1016_j_media_2023_103014
crossref_primary_10_1016_j_compmedimag_2025_102549
crossref_primary_10_1109_TMC_2023_3301501
crossref_primary_10_1093_plphys_kiaf132
crossref_primary_10_1016_j_jvcir_2025_104396
crossref_primary_10_1109_TIM_2025_3542885
crossref_primary_10_1109_ACCESS_2025_3559135
crossref_primary_10_1016_j_patcog_2023_110213
crossref_primary_10_1109_TFUZZ_2024_3423024
crossref_primary_10_1016_j_engappai_2023_106201
crossref_primary_10_1016_j_knosys_2024_112877
crossref_primary_10_1109_TITS_2024_3522308
crossref_primary_10_1109_TBME_2024_3432934
crossref_primary_10_1109_TIM_2025_3548070
crossref_primary_10_1109_TSM_2022_3222475
crossref_primary_10_1109_ACCESS_2024_3510889
crossref_primary_10_1109_TIFS_2024_3356234
crossref_primary_10_1109_TKDE_2024_3397683
crossref_primary_10_1016_j_neucom_2024_127530
crossref_primary_10_1109_TIM_2024_3497058
crossref_primary_10_1109_ACCESS_2023_3268704
crossref_primary_10_1016_j_knosys_2024_112765
crossref_primary_10_1109_TII_2023_3337364
crossref_primary_10_1016_j_bspc_2025_107971
crossref_primary_10_1016_j_media_2023_102904
crossref_primary_10_1109_TKDE_2024_3425268
crossref_primary_10_1109_TPAMI_2025_3581552
crossref_primary_10_1007_s11220_023_00428_3
crossref_primary_10_1088_1361_6501_ad66ff
crossref_primary_10_1109_JBHI_2025_3552072
crossref_primary_10_1109_RBME_2023_3296938
crossref_primary_10_1016_j_measurement_2025_118879
crossref_primary_10_1109_TIM_2024_3417540
crossref_primary_10_1016_j_compeleceng_2024_109548
crossref_primary_10_1016_j_patcog_2025_111416
crossref_primary_10_3389_fpsyg_2023_980523
crossref_primary_10_1109_JSTARS_2023_3335891
crossref_primary_10_1109_JBHI_2024_3454097
crossref_primary_10_1109_TCSVT_2023_3335147
crossref_primary_10_1049_itr2_12372
crossref_primary_10_1145_3645101
crossref_primary_10_1007_s10489_024_05266_8
crossref_primary_10_3847_1538_4357_adec78
crossref_primary_10_1109_TCSVT_2022_3232717
crossref_primary_10_1109_TKDE_2023_3301036
crossref_primary_10_1109_TPAMI_2024_3457751
crossref_primary_10_1016_j_engappai_2025_111129
crossref_primary_10_1109_JBHI_2024_3431230
crossref_primary_10_1038_s41598_025_86529_3
crossref_primary_10_1371_journal_pone_0329799
crossref_primary_10_1016_j_patcog_2024_111244
crossref_primary_10_1109_JSEN_2024_3516093
crossref_primary_10_1016_j_aei_2024_103077
crossref_primary_10_1109_TGRS_2024_3394435
crossref_primary_10_1109_TIM_2024_3507042
crossref_primary_10_1016_j_isatra_2025_05_008
crossref_primary_10_1088_1361_6501_adf2c6
crossref_primary_10_1109_TITS_2023_3276946
crossref_primary_10_1109_ACCESS_2025_3597980
crossref_primary_10_3847_1538_4357_ad73d4
crossref_primary_10_1016_j_neucom_2024_127317
crossref_primary_10_1088_1361_6501_add040
crossref_primary_10_1109_TGRS_2024_3495765
crossref_primary_10_1016_j_ymssp_2023_110228
crossref_primary_10_1109_TETCI_2023_3306253
crossref_primary_10_1007_s11263_024_02181_w
crossref_primary_10_23919_JSEE_2025_000053
crossref_primary_10_14778_3725688_3725699
crossref_primary_10_1109_JBHI_2024_3423708
crossref_primary_10_1016_j_ins_2024_120825
crossref_primary_10_1515_jmbm_2025_0074
crossref_primary_10_1109_JIOT_2024_3486068
crossref_primary_10_3390_s23020984
crossref_primary_10_1016_j_aei_2024_103063
crossref_primary_10_1109_ACCESS_2023_3298369
crossref_primary_10_1109_JSEN_2025_3543928
crossref_primary_10_1109_JSTARS_2024_3434448
crossref_primary_10_1109_TMM_2024_3521671
crossref_primary_10_1029_2023MS003658
crossref_primary_10_1007_s10845_024_02458_4
crossref_primary_10_1016_j_neunet_2024_106561
crossref_primary_10_1109_TIM_2023_3291776
crossref_primary_10_1109_TKDE_2024_3460806
crossref_primary_10_1016_j_eswa_2025_127521
crossref_primary_10_1109_TMI_2024_3461312
crossref_primary_10_1016_j_cviu_2024_103979
crossref_primary_10_1109_JSEN_2025_3542385
crossref_primary_10_1109_TKDE_2024_3392980
crossref_primary_10_1109_TIP_2024_3404241
crossref_primary_10_1109_JPROC_2025_3596173
crossref_primary_10_1007_s11263_025_02518_z
crossref_primary_10_1109_TITS_2023_3348815
crossref_primary_10_1109_LSP_2025_3601998
crossref_primary_10_1016_j_eswa_2024_126286
crossref_primary_10_1007_s10462_024_10922_z
crossref_primary_10_1109_TII_2024_3454772
crossref_primary_10_1016_j_future_2025_107814
crossref_primary_10_1016_j_inffus_2023_102221
crossref_primary_10_1016_j_jbi_2025_104802
crossref_primary_10_1016_j_ress_2023_109380
crossref_primary_10_1109_TMC_2025_3573457
crossref_primary_10_1109_TCE_2023_3278283
crossref_primary_10_1109_ACCESS_2025_3601406
crossref_primary_10_1186_s41747_022_00295_9
crossref_primary_10_7232_JKIIE_2024_50_2_075
crossref_primary_10_1109_TGRS_2025_3599172
crossref_primary_10_1016_j_isprsjprs_2025_01_027
crossref_primary_10_1109_JBHI_2023_3346057
crossref_primary_10_1109_TIFS_2025_3543040
crossref_primary_10_1109_TMM_2024_3399468
crossref_primary_10_1109_ACCESS_2024_3454082
crossref_primary_10_1016_j_ces_2025_122426
crossref_primary_10_1145_3708497
crossref_primary_10_1109_TII_2022_3210555
crossref_primary_10_1109_TPAMI_2024_3418862
crossref_primary_10_1016_j_ijheatmasstransfer_2025_127474
crossref_primary_10_1109_ACCESS_2025_3548321
crossref_primary_10_1016_j_soildyn_2023_108420
crossref_primary_10_1109_ACCESS_2023_3324545
crossref_primary_10_1016_j_ress_2024_110534
crossref_primary_10_1145_3665894
crossref_primary_10_1038_s42003_024_07171_9
crossref_primary_10_1016_j_media_2024_103211
crossref_primary_10_1109_TIFS_2024_3393237
crossref_primary_10_1016_j_compbiomed_2024_109256
crossref_primary_10_1109_TKDE_2025_3581706
crossref_primary_10_1109_TIP_2025_3581012
crossref_primary_10_1109_TCSVT_2024_3522936
crossref_primary_10_1109_JBHI_2024_3372999
crossref_primary_10_1109_TGRS_2023_3344670
crossref_primary_10_1109_TRO_2025_3543302
crossref_primary_10_1162_tacl_a_00755
crossref_primary_10_1121_10_0036456
crossref_primary_10_1109_TMI_2024_3371987
crossref_primary_10_1109_TBIOM_2024_3470232
crossref_primary_10_1007_s10489_024_06224_0
crossref_primary_10_1109_TGRS_2024_3443915
crossref_primary_10_1109_TII_2024_3495781
crossref_primary_10_1121_10_0025687
crossref_primary_10_1016_j_neucom_2023_126527
crossref_primary_10_1109_TMC_2024_3376697
crossref_primary_10_1109_JSEN_2024_3443532
crossref_primary_10_1016_j_apenergy_2022_120143
crossref_primary_10_1007_s10499_025_02022_8
crossref_primary_10_1109_JSTARS_2025_3542617
crossref_primary_10_1162_tacl_a_00621
crossref_primary_10_1109_TNSRE_2023_3305202
crossref_primary_10_5194_hess_28_479_2024
crossref_primary_10_1109_TIE_2023_3243293
crossref_primary_10_3390_electronics12051255
crossref_primary_10_1109_TNSRE_2023_3293334
crossref_primary_10_1109_TPAMI_2024_3416302
crossref_primary_10_1088_1741_2552_acb7a0
crossref_primary_10_1364_OE_557580
crossref_primary_10_1016_j_patcog_2024_110360
crossref_primary_10_1109_TIM_2024_3368493
crossref_primary_10_1109_ACCESS_2025_3537981
crossref_primary_10_1016_j_knosys_2024_112915
crossref_primary_10_1109_TMM_2024_3521719
crossref_primary_10_1109_TBIOM_2025_3540919
crossref_primary_10_1103_PhysRevE_111_014303
crossref_primary_10_1109_TPAMI_2024_3355212
crossref_primary_10_1109_TGRS_2024_3401231
crossref_primary_10_1109_TPAMI_2025_3581941
crossref_primary_10_1109_TKDE_2023_3271771
crossref_primary_10_1360_SSPMA_2024_0474
crossref_primary_10_1007_s42979_024_03553_2
crossref_primary_10_1016_j_imavis_2024_105359
crossref_primary_10_1109_TRO_2025_3550771
crossref_primary_10_1109_TGRS_2024_3518502
crossref_primary_10_1088_1741_2552_ad430d
crossref_primary_10_1109_TII_2024_3463705
crossref_primary_10_1109_TMC_2022_3230665
crossref_primary_10_1109_TIM_2025_3600723
crossref_primary_10_1109_TETCI_2025_3535659
crossref_primary_10_1007_s10845_024_02357_8
crossref_primary_10_1109_TIP_2024_3451933
crossref_primary_10_1109_JPROC_2024_3507831
crossref_primary_10_1109_TII_2024_3369240
crossref_primary_10_1109_TNSRE_2024_3521229
crossref_primary_10_1109_TR_2024_3441592
crossref_primary_10_3390_machines12110762
crossref_primary_10_1016_j_neucom_2024_127822
crossref_primary_10_1109_TITS_2024_3419003
crossref_primary_10_1109_TGRS_2023_3322787
crossref_primary_10_1109_TIM_2025_3541814
crossref_primary_10_1109_TPAMI_2024_3450282
crossref_primary_10_1002_lom3_10659
crossref_primary_10_1109_JIOT_2023_3263240
crossref_primary_10_3389_frobt_2025_1548143
crossref_primary_10_1109_TIM_2024_3453330
crossref_primary_10_1109_TCI_2025_3539448
crossref_primary_10_1109_TKDE_2024_3486204
crossref_primary_10_3389_fpls_2024_1485903
crossref_primary_10_1109_TII_2023_3342885
crossref_primary_10_1109_TASLP_2024_3410877
crossref_primary_10_1016_j_yacr_2023_05_001
crossref_primary_10_1007_s11063_025_11747_9
crossref_primary_10_1109_MCOM_001_2400578
crossref_primary_10_5194_hess_28_2505_2024
crossref_primary_10_1109_TASE_2024_3362322
crossref_primary_10_1016_j_measurement_2025_118690
crossref_primary_10_1109_TIM_2024_3413128
crossref_primary_10_1016_j_eswa_2025_126710
crossref_primary_10_1109_TETCI_2024_3406422
crossref_primary_10_1109_TIFS_2025_3550071
crossref_primary_10_1007_s00521_024_10353_5
crossref_primary_10_1109_TMC_2025_3572220
crossref_primary_10_1109_TIM_2024_3415788
crossref_primary_10_1007_s00371_024_03327_0
crossref_primary_10_1186_s43170_024_00273_8
crossref_primary_10_1016_j_patcog_2023_110029
crossref_primary_10_1109_TMM_2024_3407696
crossref_primary_10_1109_JSTSP_2024_3507371
crossref_primary_10_1109_TIM_2023_3312470
crossref_primary_10_1109_TII_2023_3342896
crossref_primary_10_1109_TGRS_2023_3317301
crossref_primary_10_1016_j_knosys_2024_112358
crossref_primary_10_1109_JBHI_2024_3454158
crossref_primary_10_1109_TSC_2025_3576692
crossref_primary_10_1007_s11071_023_08657_7
crossref_primary_10_1145_3641289
Cites_doi 10.1609/aaai.v32i1.11596
10.1109/CVPR46437.2021.00107
10.1007/978-3-642-15561-1_16
10.1007/978-3-030-03341-5_3
10.1109/TPAMI.2013.50
10.1145/3240508.3240512
10.18653/v1/2021.naacl-main.33
10.1109/CVPR46437.2021.01273
10.1109/CVPR.2019.00258
10.1109/TPAMI.2020.2992393
10.1007/978-3-319-19258-1_28
10.1609/aaai.v35i13.17416
10.1007/978-3-642-33718-5_12
10.1109/ICCV.2015.293
10.1038/npre.2008.2298.1
10.1007/978-3-030-58592-1_28
10.1109/JPROC.2020.3004555
10.1109/CVPR.2016.352
10.1145/3022671.2984041
10.1109/ICCV.2019.00219
10.1145/3474085.3475271
10.1109/ICCVW.2019.00403
10.1023/A:1007379606734
10.1109/BCI51272.2021.9385322
10.1007/978-3-030-58536-5_8
10.1109/ICIP40778.2020.9191364
10.1109/TIP.2021.3112012
10.1109/TIM.2020.2992829
10.1109/CVPR.2016.350
10.1109/ICCV.2019.00153
10.1109/ICIP42928.2021.9506516
10.1109/IROS.2017.8202133
10.18653/v1/2020.coling-main.574
10.1016/j.bbmt.2007.02.002
10.1109/CVPR.2019.00081
10.1109/ICCV.2017.609
10.1016/j.neucom.2021.09.046
10.1109/CVPR42600.2020.00321
10.1109/ICCV48922.2021.00135
10.1609/aaai.v34i07.6846
10.1109/CVPR.2017.572
10.1109/TIP.2017.2758199
10.1109/ICDM51629.2021.00203
10.1145/3394171.3413815
10.1109/CVPR.2019.01026
10.1109/ICCV.2017.167
10.1109/ICCV48922.2021.00087
10.1109/ICRA.2018.8460528
10.1109/CVPR.2016.17
10.1109/WACV.2019.00210
10.1007/978-3-030-01225-0_29
10.1023/A:1019956318069
10.3115/1610075.1610094
10.1109/CVPR46437.2021.00950
10.1109/CVPRW.2018.00122
10.1109/CVPR46437.2021.01415
10.1109/ICCV48922.2021.00948
10.1109/CVPR46437.2021.01504
10.1007/978-3-030-92273-3_7
10.34133/2020/3521852
10.1360/N112018-00312
10.1016/j.neucom.2020.05.014
10.1109/CVPRW53098.2021.00361
10.1007/BF00994018
10.1109/ICCV.2013.208
10.1109/CVPR.2018.00646
10.1609/aaai.v34i07.7003
10.1109/CVPR.2018.00566
10.1109/CVPR46437.2021.00533
10.1109/TPAMI.2016.2599532
10.1109/TPAMI.2022.3157441
10.1007/978-3-030-66415-2_39
10.1109/CVPR46437.2021.00621
10.1109/CVPR42600.2020.00851
10.1145/3298981
10.1109/ICCV.2015.477
10.1109/TMI.2018.2867350
10.1007/978-3-030-01267-0_38
10.1109/TKDE.2009.191
10.1109/ICASSP43922.2022.9747363
10.1007/978-3-030-87234-2_10
10.1109/TMM.2021.3104379
10.1609/aaai.v32i1.11682
10.1109/CVPR46437.2021.00858
10.1109/CVPR42600.2020.01257
10.1145/3293318
10.1109/ICCV.2019.00149
10.1016/j.compbiomed.2020.103757
10.1109/MIS.2020.2988604
10.1007/978-3-030-58539-6_45
10.1038/s42256-020-0186-1
10.1109/WACV.2019.00067
10.1109/LRA.2018.2809700
10.1109/TPAMI.2017.2704624
10.7551/mitpress/7503.003.0022
10.1109/ICCV.2017.591
10.1109/IJCNN48605.2020.9206635
10.1145/3474085.3475311
10.1016/j.patcog.2020.107383
10.1109/CVPR.2019.00233
10.1145/3360309
10.1109/CVPR46437.2021.00682
10.1007/978-3-030-58607-2_12
10.1109/CVPR46437.2021.00672
10.1007/978-3-030-01270-0_28
10.1109/ICASSP40776.2020.9053273
10.1109/ICCV48922.2021.00876
10.1109/CVPR46437.2021.00811
10.1109/CVPRW.2018.00143
10.1109/ICCV48922.2021.00642
10.1162/neco.1994.6.5.851
10.1109/CVPR46437.2021.01411
10.1186/s40537-016-0043-6
10.1109/WACV51458.2022.00024
10.18653/v1/D19-1018
10.1145/3308560.3317593
10.1007/978-3-030-58517-4_33
10.1109/CVPR46437.2021.00820
10.1145/3459637.3482315
10.1609/aaai.v29i1.9542
10.1016/j.neucom.2018.05.083
10.1038/s41467-020-16185-w
10.1109/ICASSP39728.2021.9413872
10.1609/aaai.v30i1.10306
10.1186/s40537-019-0197-0
10.1007/978-3-319-49409-8_35
10.1109/CVPR.2017.437
10.1109/CVPR46437.2021.01141
10.1109/TNN.2010.2091281
10.1109/WACV.2018.00219
10.1007/978-3-030-58542-6_5
10.1109/TIM.2020.3016068
10.1007/s10994-021-06080-w
10.1109/ICIP.2018.8451318
10.1007/978-3-319-10578-9_41
10.1109/ICCV48922.2021.00883
10.1007/s10994-009-5152-4
10.1109/CVPR46437.2021.00029
10.1109/MSP.2014.2347059
10.1109/ICRA.2019.8794443
10.1016/j.patcog.2019.107124
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TKDE.2022.3178128
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1558-2191
EndPage 8072
ExternalDocumentID 10_1109_TKDE_2022_3178128
9782500
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: III-1763325; III-1909323; III-2106758; SaTC-1930941
  funderid: 10.13039/501100008982
– fundername: NSFC
  grantid: 61972383
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
1OL
5VS
9M8
AAYXX
ABFSI
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
E.L
H~9
ICLAB
IFJZH
RNI
RZB
TAF
VH1
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c359t-6b1591b3d535d6b0cff16509eea1e0aabb190d2fb963e82df867d2cb4abcdb093
IEDL.DBID RIE
ISICitedReferencesCount 695
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001033571000032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1041-4347
IngestDate Sun Nov 30 04:11:20 EST 2025
Sat Nov 29 02:36:05 EST 2025
Tue Nov 18 22:11:51 EST 2025
Wed Aug 27 02:25:53 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c359t-6b1591b3d535d6b0cff16509eea1e0aabb190d2fb963e82df867d2cb4abcdb093
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-2531-3137
0000-0002-8407-0780
0000-0002-4833-0880
0000-0002-9095-0776
0000-0001-9145-9957
0000-0003-4035-0737
0000-0002-3491-5968
PQID 2834305836
PQPubID 85438
PageCount 21
ParticipantIDs ieee_primary_9782500
crossref_primary_10_1109_TKDE_2022_3178128
crossref_citationtrail_10_1109_TKDE_2022_3178128
proquest_journals_2834305836
PublicationCentury 2000
PublicationDate 2023-08-01
PublicationDateYYYYMMDD 2023-08-01
PublicationDate_xml – month: 08
  year: 2023
  text: 2023-08-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev TKDE
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ganin (ref92) 2016; 17
ref56
ref59
ref53
ref52
ref204
ref55
ref54
chen (ref89) 2020
ref210
truong (ref42) 2019
d’innocente (ref137) 2018
liu (ref132) 2021
shi (ref151) 2022
ref46
gulrajani (ref87) 2021
baevski (ref264) 2020
ref219
ref48
ref215
ref44
triantafillou (ref121) 2021
ref43
ref213
ahuja (ref109) 2021
dumoulin (ref195) 2017
santoro (ref209) 2016
ref8
ref7
ref9
ref100
shankar (ref37) 2018
ref101
ref40
ref35
cha (ref165) 2021
ref34
adila (ref168) 2021
hu (ref66) 2019
deshmukh (ref118) 2018
ref31
ref30
ref33
ref32
ref39
ji (ref23) 2019; 49
peng (ref125) 2019
guo (ref108) 2021
jia (ref186) 2019
zhang (ref218) 2021
lin (ref217) 2021
johansson (ref25) 2019
ref24
ref26
ref20
iwasawa (ref265) 2021
ref22
ref21
sagawa (ref155) 2020
kang (ref199) 2021
ref29
ouyang (ref135) 2021
ref200
albuquerque (ref102) 2019
gong (ref205) 2018
ref128
ref249
rahimian (ref211) 2019
ref129
ref97
zhao (ref95) 2020
heinze-deml (ref206) 2019; 1050
ref96
ref127
ref248
deshmukh (ref28) 2019
ref99
ref245
ganin (ref91) 2015
ref246
ye (ref167) 2021
bui (ref198) 2021
zhou (ref3) 2021
liu (ref41) 2018
wang (ref157) 2021
blanchard (ref60) 2017
ref93
krueger (ref106) 2021
ref134
ref252
ref94
ref253
ref250
ref130
hu (ref237) 2020
ref90
ref139
ref86
ref138
ref259
finn (ref207) 2017
ref88
ref136
ref257
cortes (ref180) 1995; 20
hospedales (ref15) 2022; 44
yang (ref5) 2021
goodfellow (ref172) 2014
peng (ref58) 2021
ref82
ref144
ref81
ref266
koh (ref156) 2021
ref84
ref142
ref140
ref141
dou (ref143) 2019
ref80
ref260
ref229
ref78
ref227
wang (ref47) 2021
ref75
ref225
ref74
ref226
lu (ref243) 2021
ref77
richter (ref247) 2016
ref103
nazari (ref36) 2020
truong (ref50) 2019
gretton (ref175) 2012; 13
wang (ref258) 2020
ref71
ref232
ref70
ref233
ref73
ref230
ref72
ref231
ref68
ref119
ref67
ref238
vanschoren (ref16) 2018
ref239
ref64
ref115
weiss (ref10) 2016; 3
ref63
ref116
ref113
ref114
ref235
shen (ref4) 2021
jin (ref83) 2020
zhang (ref203) 2013
zhang (ref173) 2018
kingma (ref171) 2013
ref122
ref123
ref244
ref62
ref241
somavarapu (ref57) 2020
ref61
ref242
ref240
choe (ref110) 2020
zhang (ref164) 2021
ref169
zhang (ref131) 2020
brown (ref263) 2020
yang (ref224) 2019; 13
erfani (ref65) 2016
tolstikhin (ref176) 2017
qi (ref79) 2021
zhou (ref170) 2021
ref177
ref178
ref174
tzeng (ref188) 2014
maniyar (ref85) 2020
ref179
sonar (ref197) 2021
rosenfeld (ref111) 2021
ref181
ulyanov (ref196) 2016
schölkopf (ref202) 2012
quiñonero-candela (ref1) 2009
ref189
ref184
ref185
li (ref19) 2019
ref183
ref148
ref149
ref146
ref147
zhang (ref221) 2021
liu (ref154) 2021
garg (ref45) 2021
taylor (ref236) 2019
zhang (ref228) 2021
zhou (ref182) 2020
ref153
ilse (ref124) 2020
balaji (ref18) 2018
ref150
sharifi-noghabi (ref145) 2020
ref159
ref158
zhou (ref49) 2021
arjovsky (ref104) 2019
rame (ref152) 2021
ref166
devlin (ref262) 2019
segù (ref69) 2020
mahajan (ref76) 2021
zhang (ref222) 2022
ref163
parascandolo (ref256) 2021
ref160
ref161
ref13
ref12
ref14
wald (ref214) 2021
ref11
volpi (ref38) 2018
ref17
ahuja (ref105) 2021
snell (ref208) 2017
blanchard (ref6) 2021; 22
wang (ref255) 2022
mahajan (ref223) 2021
sagawa (ref212) 2020
robey (ref51) 2021
muandet (ref27) 2013
wang (ref254) 2022
hu (ref120) 2021
zhang (ref126) 2021
nam (ref187) 2018
ryu (ref162) 2019
ref2
ref191
ref192
duboudin (ref216) 2021
ref190
beery (ref234) 2020
zhu (ref261) 2021
ahuja (ref112) 2020
piratla (ref117) 2020
ref193
ref194
sohn (ref220) 2020
sicilia (ref98) 2021
brockman (ref251) 2016
sun (ref133) 2021
wang (ref201) 2021
mitrovic (ref107) 2021
References_xml – year: 2020
  ident: ref264
  article-title: wav2vec 2.0: A framework for self-supervised learning of speech representations
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref17
  doi: 10.1609/aaai.v32i1.11596
– ident: ref219
  doi: 10.1109/CVPR46437.2021.00107
– start-page: 666
  year: 2020
  ident: ref36
  article-title: Domain generalization using shape representation
  publication-title: Proc Eur Conf Comput Vis
– ident: ref229
  doi: 10.1007/978-3-642-15561-1_16
– start-page: 1255
  year: 2012
  ident: ref202
  article-title: On causal and anticausal learning
  publication-title: Proc Int Conf Mach Learn
– ident: ref140
  doi: 10.1007/978-3-030-03341-5_3
– ident: ref178
  doi: 10.1109/TPAMI.2013.50
– ident: ref189
  doi: 10.1145/3240508.3240512
– ident: ref147
  doi: 10.18653/v1/2021.naacl-main.33
– ident: ref266
  doi: 10.1109/CVPR46437.2021.01273
– year: 2013
  ident: ref171
  article-title: Auto-encoding variational Bayes
– ident: ref93
  doi: 10.1109/CVPR.2019.00258
– ident: ref213
  doi: 10.1109/TPAMI.2020.2992393
– start-page: 2563
  year: 2018
  ident: ref187
  article-title: Batch-instance normalization for adaptively style-invariant neural networks
  publication-title: Proc Int Conf Neural Inf Process
– start-page: 5102
  year: 2019
  ident: ref125
  article-title: Domain agnostic learning with disentangled representations
  publication-title: Proc Int Conf Mach Learn
– ident: ref61
  doi: 10.1007/978-3-319-19258-1_28
– start-page: 9898
  year: 2020
  ident: ref258
  article-title: Continuously indexed domain adaptation
  publication-title: Proc Int Conf Mach Learn
– ident: ref128
  doi: 10.1609/aaai.v35i13.17416
– ident: ref115
  doi: 10.1007/978-3-642-33718-5_12
– ident: ref67
  doi: 10.1109/ICCV.2015.293
– ident: ref252
  doi: 10.1038/npre.2008.2298.1
– ident: ref260
  doi: 10.1007/978-3-030-58592-1_28
– ident: ref11
  doi: 10.1109/JPROC.2020.3004555
– ident: ref248
  doi: 10.1109/CVPR.2016.352
– year: 2021
  ident: ref135
  article-title: Causality-inspired single-source domain generalization for medical image segmentation
– start-page: 1
  year: 2021
  ident: ref223
  article-title: The connection between out-of-distribution generalization and privacy of ML models
  publication-title: Proc Workshop Privacy Preserving Mach Learn NeurIPS
– start-page: 4077
  year: 2017
  ident: ref208
  article-title: Prototypical networks for few-shot learning
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref244
  doi: 10.1145/3022671.2984041
– year: 2021
  ident: ref152
  article-title: Fishr: Invariant gradient variances for out-of-distribution generalization
– ident: ref29
  doi: 10.1109/ICCV.2019.00219
– year: 2019
  ident: ref102
  article-title: Adversarial target-invariant representation learning for domain generalization
– ident: ref160
  doi: 10.1145/3474085.3475271
– ident: ref46
  doi: 10.1109/ICCVW.2019.00403
– ident: ref7
  doi: 10.1023/A:1007379606734
– start-page: 22405
  year: 2021
  ident: ref165
  article-title: SWAD: Domain generalization by seeking flat minima
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref86
  doi: 10.1109/BCI51272.2021.9385322
– year: 2021
  ident: ref5
  article-title: Generalized out-of-distribution detection: A survey
– ident: ref150
  doi: 10.1007/978-3-030-58536-5_8
– ident: ref75
  doi: 10.1109/ICIP40778.2020.9191364
– ident: ref8
  doi: 10.1109/TIP.2021.3112012
– ident: ref74
  doi: 10.1109/TIM.2020.2992829
– ident: ref246
  doi: 10.1109/CVPR.2016.350
– ident: ref146
  doi: 10.1109/ICCV.2019.00153
– start-page: 322
  year: 2020
  ident: ref124
  article-title: DIVA: Domain invariant variational autoencoders
  publication-title: Proc 3rd Conf Med Imag Deep Learn
– ident: ref149
  doi: 10.1109/ICIP42928.2021.9506516
– start-page: 6155
  year: 2021
  ident: ref132
  article-title: Learning causal semantic representation for out-of-distribution prediction
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref32
  doi: 10.1109/IROS.2017.8202133
– ident: ref21
  doi: 10.18653/v1/2020.coling-main.574
– ident: ref245
  doi: 10.1016/j.bbmt.2007.02.002
– start-page: 1
  year: 2021
  ident: ref49
  article-title: Domain generalization with mixstyle
  publication-title: Proc Int Conf Learn Representations
– start-page: 292
  year: 2019
  ident: ref66
  article-title: Domain generalization via multidomain discriminant analysis
  publication-title: Proc Conf Uncertainty of Artificial Intelligence
– start-page: 12356
  year: 2021
  ident: ref164
  article-title: Can subnetwork structure be the key to out-of-distribution generalization?
  publication-title: Proc Int Conf Mach Learn
– year: 2021
  ident: ref201
  article-title: Variational disentanglement for domain generalization
– ident: ref250
  doi: 10.1109/CVPR.2019.00081
– ident: ref68
  doi: 10.1109/ICCV.2017.609
– ident: ref144
  doi: 10.1016/j.neucom.2021.09.046
– start-page: 1
  year: 2021
  ident: ref261
  article-title: CrossMatch: Cross-classifier consistency regularization for open-set single domain generalization
  publication-title: Proc Int Conf Learn Representations
– start-page: 819
  year: 2013
  ident: ref203
  article-title: Domain adaptation under target and conditional shift
  publication-title: Proc Int Conf Mach Learn
– start-page: 16846
  year: 2021
  ident: ref133
  article-title: Recovering latent causal factor for generalization to distributional shifts
  publication-title: Proc Int Conf Neural Inf Process
– year: 2019
  ident: ref50
  article-title: Image alignment in unseen domains via domain deep generalization
– ident: ref70
  doi: 10.1109/CVPR42600.2020.00321
– start-page: 145
  year: 2020
  ident: ref112
  article-title: Invariant risk minimization games
  publication-title: Proc Int Conf Mach Learn
– start-page: 18408
  year: 2021
  ident: ref221
  article-title: FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref163
  doi: 10.1109/ICCV48922.2021.00135
– ident: ref97
  doi: 10.1609/aaai.v34i07.6846
– year: 2021
  ident: ref108
  article-title: Out-of-distribution prediction with invariant risk minimization: The limitation and an effective fix
– start-page: 3811
  year: 2021
  ident: ref228
  article-title: On the out-of-distribution generalization of probabilistic image modelling
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref231
  doi: 10.1109/CVPR.2017.572
– start-page: 10424
  year: 2021
  ident: ref121
  article-title: Learning a universal template for few-shot dataset generalization
  publication-title: Proc Int Conf Mach Learn
– ident: ref122
  doi: 10.1109/TIP.2017.2758199
– year: 2022
  ident: ref255
  article-title: Everything about transfer learning and domain adapation
– ident: ref184
  doi: 10.1109/ICDM51629.2021.00203
– year: 2021
  ident: ref3
  article-title: Domain generalization in vision: A survey
– ident: ref249
  doi: 10.1145/3394171.3413815
– ident: ref96
  doi: 10.1109/CVPR.2019.01026
– start-page: 2215
  year: 2021
  ident: ref214
  article-title: On calibration and out-of-domain generalization
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref177
  doi: 10.1109/ICCV.2017.167
– start-page: 7313
  year: 2021
  ident: ref76
  article-title: Domain generalization using causal matching
  publication-title: Proc Int Conf Mach Learn
– volume: 13
  start-page: 1
  year: 2019
  ident: ref224
  publication-title: Federated Learning
– start-page: 23519
  year: 2021
  ident: ref167
  article-title: Towards a theoretical framework of out-of-distribution generalization
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref59
  doi: 10.1109/ICCV48922.2021.00087
– ident: ref33
  doi: 10.1109/ICRA.2018.8460528
– year: 2020
  ident: ref110
  article-title: An empirical study of invariant risk minimization
– ident: ref62
  doi: 10.1109/CVPR.2016.17
– year: 2021
  ident: ref58
  article-title: Out-of-domain generalization from a single source: A uncertainty quantification approach
– ident: ref34
  doi: 10.1109/WACV.2019.00210
– start-page: 2672
  year: 2014
  ident: ref172
  article-title: Generative adversarial networks
  publication-title: Proc Int Conf Neural Inf Process
– start-page: 102
  year: 2016
  ident: ref247
  article-title: Playing for data: Ground truth from computer games
  publication-title: Proc Eur Conf Comput Vis
– start-page: 1
  year: 2020
  ident: ref237
  article-title: Open graph benchmark: Datasets for machine learning on graphs
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref185
  doi: 10.1007/978-3-030-01225-0_29
– year: 2021
  ident: ref98
  article-title: Domain adversarial neural networks for domain generalization: When it works and how to improve
– start-page: 21189
  year: 2021
  ident: ref198
  article-title: Exploiting domain-specific features to enhance domain generalization
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref14
  doi: 10.1023/A:1019956318069
– ident: ref253
  doi: 10.3115/1610075.1610094
– ident: ref54
  doi: 10.1109/CVPR46437.2021.00950
– start-page: 7728
  year: 2020
  ident: ref117
  article-title: Efficient domain generalization via common-specific low-rank decomposition
  publication-title: Proc Int Conf Mach Learn
– ident: ref174
  doi: 10.1109/CVPRW.2018.00122
– ident: ref55
  doi: 10.1109/CVPR46437.2021.01415
– ident: ref159
  doi: 10.1109/ICCV48922.2021.00948
– volume: 44
  start-page: 5149
  year: 2022
  ident: ref15
  article-title: Meta-learning in neural networks: A survey
  publication-title: IEEE Trans Pattern Anal Mach Intell
– start-page: 1
  year: 2021
  ident: ref170
  article-title: Semi-supervised domain generalization with stochastic stylematch
  publication-title: Proc Int Conf Neural Inf Process Syst Workshop
– year: 2021
  ident: ref4
  article-title: Towards out-of-distribution generalization: A survey
– ident: ref166
  doi: 10.1109/CVPR46437.2021.01504
– ident: ref101
  doi: 10.1007/978-3-030-92273-3_7
– ident: ref238
  doi: 10.34133/2020/3521852
– volume: 49
  start-page: 1299
  year: 2019
  ident: ref23
  article-title: A decadal survey of zero-shot image classification
  publication-title: Sci Sinica Inf
  doi: 10.1360/N112018-00312
– ident: ref90
  doi: 10.1016/j.neucom.2020.05.014
– year: 2021
  ident: ref120
  article-title: Domain and content adaptive convolution for domain generalization in medical image segmentation
– start-page: 1
  year: 2021
  ident: ref256
  article-title: Learning explanations that are hard to vary
  publication-title: Proc Int Conf Learn Representations
– ident: ref123
  doi: 10.1109/CVPRW53098.2021.00361
– volume: 20
  start-page: 273
  year: 1995
  ident: ref180
  article-title: Support-vector networks
  publication-title: Mach Learn
  doi: 10.1007/BF00994018
– start-page: 10
  year: 2013
  ident: ref27
  article-title: Domain generalization via invariant feature representation
  publication-title: Proc Int Conf Mach Learn
– ident: ref230
  doi: 10.1109/ICCV.2013.208
– ident: ref240
  doi: 10.1109/CVPR.2018.00646
– start-page: 1
  year: 2021
  ident: ref87
  article-title: In search of lost domain generalization
  publication-title: Proc Int Conf Learn Representations
– ident: ref39
  doi: 10.1609/aaai.v34i07.7003
– year: 2020
  ident: ref131
  article-title: A causal view on robustness of neural networks
  publication-title: Proc Int Conf Neural Inf Process
– year: 2020
  ident: ref145
  article-title: Domain generalization via semi-supervised meta learning
– ident: ref72
  doi: 10.1109/CVPR.2018.00566
– start-page: 2590
  year: 2018
  ident: ref41
  article-title: A unified feature disentangler for multi-domain image translation and manipulation
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref134
  doi: 10.1109/CVPR46437.2021.00533
– start-page: 1
  year: 2018
  ident: ref173
  article-title: mixup: Beyond empirical risk minimization
  publication-title: Proc Int Conf Learn Representations
– volume: 1050
  year: 2019
  ident: ref206
  article-title: Conditional variance penalties and domain shift robustness
  publication-title: Stat
– start-page: 20210
  year: 2021
  ident: ref51
  article-title: Model-based domain generalization
  publication-title: Proc Int Conf Neural Inf Process
– volume: 22
  year: 2021
  ident: ref6
  article-title: Domain generalization by marginal transfer learning
  publication-title: J Mach Learn Res
– ident: ref64
  doi: 10.1109/TPAMI.2016.2599532
– start-page: 51
  year: 2021
  ident: ref216
  article-title: Encouraging intra-class diversity through a reverse contrastive loss for better single-source domain generalization
  publication-title: Proc IEEE Int Conf Comput Vis Workshops
– ident: ref153
  doi: 10.1109/TPAMI.2022.3157441
– start-page: 5637
  year: 2021
  ident: ref156
  article-title: WILDS: A benchmark of in-the-wild distribution shifts
  publication-title: Proc Int Conf Mach Learn
– ident: ref259
  doi: 10.1007/978-3-030-66415-2_39
– start-page: 6781
  year: 2021
  ident: ref154
  article-title: Just train twice: Improving group robustness without training group information
  publication-title: Proc Int Conf Mach Learn
– volume: 13
  start-page: 723
  year: 2012
  ident: ref175
  article-title: A kernel two-sample test
  publication-title: J Mach Learn Res
– ident: ref210
  doi: 10.1109/CVPR46437.2021.00621
– ident: ref100
  doi: 10.1109/CVPR42600.2020.00851
– start-page: 1856
  year: 2022
  ident: ref222
  article-title: ReMoS: Reducing defect inheritance in transfer learning via relevant model slicing
  publication-title: Proc 4th Int Conf Software Engineering
– year: 2020
  ident: ref182
  article-title: Domain generalization with optimal transport and metric learning
– ident: ref225
  doi: 10.1145/3298981
– start-page: 1126
  year: 2017
  ident: ref207
  article-title: Model-agnostic meta-learning for fast adaptation of deep networks
  publication-title: Proc Int Conf Mach Learn
– start-page: 1
  year: 2021
  ident: ref111
  article-title: The risks of invariant risk minimization
  publication-title: Proc Int Conf Learn Representations
– ident: ref116
  doi: 10.1109/ICCV.2015.477
– start-page: 21
  year: 2021
  ident: ref197
  article-title: Invariant policy optimization: Towards stronger generalization in reinforcement learning
  publication-title: Proc 3rd Annu Conf Learn Dyn Control
– ident: ref235
  doi: 10.1109/TMI.2018.2867350
– ident: ref94
  doi: 10.1007/978-3-030-01267-0_38
– ident: ref9
  doi: 10.1109/TKDE.2009.191
– start-page: 1180
  year: 2015
  ident: ref91
  article-title: Unsupervised domain adaptation by backpropagation
  publication-title: Proc Int Conf Mach Learn
– ident: ref84
  doi: 10.1109/ICASSP43922.2022.9747363
– year: 2020
  ident: ref69
  article-title: Batch normalization embeddings for deep domain generalization
– ident: ref161
  doi: 10.1007/978-3-030-87234-2_10
– start-page: 1
  year: 2020
  ident: ref83
  article-title: Feature alignment and restoration for domain generalization and adaptation
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref71
  doi: 10.1109/TMM.2021.3104379
– year: 2016
  ident: ref196
  article-title: Instance normalization: The missing ingredient for fast stylization
– ident: ref63
  doi: 10.1609/aaai.v32i1.11682
– start-page: 8024
  year: 2021
  ident: ref126
  article-title: Towards principled disentanglement for domain generalization
  publication-title: Proc ICML Mach Learn Data Workshop
– start-page: 1
  year: 2020
  ident: ref89
  article-title: A study of domain generalization on ultrasound-based multi-class segmentation of arteries, veins, ligaments, and nerves using transfer learning
  publication-title: Proc Mach Learn Health NeurIPS
– ident: ref127
  doi: 10.1109/CVPR46437.2021.00858
– year: 2019
  ident: ref186
  article-title: Frustratingly easy person re-identification: Generalizing person re-ID in practice
  publication-title: Proc 30th Brit Mach Vis Conf
– ident: ref40
  doi: 10.1109/CVPR42600.2020.01257
– start-page: 527
  year: 2019
  ident: ref25
  article-title: Support and invertibility in domain-invariant representations
  publication-title: Proc 22nd Int Conf Artif Intell Statist
– start-page: 1
  year: 2021
  ident: ref109
  article-title: Empirical or invariant risk minimization? A sample complexity perspective
  publication-title: Proc Int Conf Learn Representations
– ident: ref22
  doi: 10.1145/3293318
– year: 2019
  ident: ref42
  article-title: Recognition in unseen domains: Domain generalization via universal non-volume preserving models
– year: 2019
  ident: ref104
  article-title: Invariant risk minimization
– ident: ref183
  doi: 10.1109/ICCV.2019.00149
– ident: ref88
  doi: 10.1016/j.compbiomed.2020.103757
– start-page: 1
  year: 2019
  ident: ref236
  article-title: RxRx1: An image set for cellular morphological variation across many experimental batches
  publication-title: Proc Int Conf Learn Representations
– year: 2020
  ident: ref95
  article-title: Domain generalization via entropy regularization
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref226
  doi: 10.1109/MIS.2020.2988604
– ident: ref119
  doi: 10.1007/978-3-030-58539-6_45
– ident: ref227
  doi: 10.1038/s42256-020-0186-1
– ident: ref56
  doi: 10.1109/WACV.2019.00067
– year: 2020
  ident: ref57
  article-title: Frustratingly simple domain generalization via image stylization
– year: 2020
  ident: ref220
  article-title: FixMatch: Simplifying semi-supervised learning with consistency and confidence
  publication-title: Proc 34th Int Conf Neural Inf Process Syst
– ident: ref141
  doi: 10.1109/LRA.2018.2809700
– start-page: 1
  year: 2022
  ident: ref151
  article-title: Gradient matching for domain generalization
  publication-title: Proc Int Conf Learn Representations
– ident: ref114
  doi: 10.1109/TPAMI.2017.2704624
– ident: ref179
  doi: 10.7551/mitpress/7503.003.0022
– ident: ref2
  doi: 10.1109/ICCV.2017.591
– ident: ref103
  doi: 10.1109/IJCNN48605.2020.9206635
– start-page: 1
  year: 2021
  ident: ref107
  article-title: Representation learning via invariant causal mechanisms
  publication-title: Proc Int Conf Learn Representations
– start-page: 2427
  year: 2021
  ident: ref265
  article-title: Test-time classifier adjustment module for model-agnostic domain generalization
  publication-title: Proc Int Conf Neural Inf Process
– start-page: 3574
  year: 2021
  ident: ref45
  article-title: Learn to expect the unexpected: Probably approximately correct domain generalization
  publication-title: Proc Int Conf Artif Intell Statist
– start-page: 4171
  year: 2019
  ident: ref262
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol
– start-page: 1842
  year: 2016
  ident: ref209
  article-title: Meta-learning with memory-augmented neural networks
  publication-title: Proc Int Conf Mach Learn
– year: 2019
  ident: ref211
  article-title: Distributionally robust optimization: A review
– start-page: 1
  year: 2020
  ident: ref212
  article-title: Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization
  publication-title: Proc Int Conf Learn Representations
– ident: ref44
  doi: 10.1109/CVPR46437.2021.00621
– year: 2022
  ident: ref254
  article-title: DeepDG: Deep domain generalization toolkit
– start-page: 1
  year: 2017
  ident: ref195
  article-title: A learned representation for artistic style
  publication-title: Proc Int Conf Learn Representations
– ident: ref200
  doi: 10.1145/3474085.3475311
– ident: ref136
  doi: 10.1016/j.patcog.2020.107383
– ident: ref158
  doi: 10.1109/CVPR.2019.00233
– year: 2021
  ident: ref218
  article-title: Federated learning with domain generalization
– start-page: 1
  year: 2021
  ident: ref243
  article-title: CodeXGLUE: A machine learning benchmark dataset for code understanding and generation
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref190
  doi: 10.1145/3360309
– ident: ref31
  doi: 10.1109/CVPR46437.2021.00682
– ident: ref20
  doi: 10.1007/978-3-030-58607-2_12
– start-page: 5815
  year: 2021
  ident: ref106
  article-title: Out-of-distribution generalization via risk extrapolation (REx)
  publication-title: Proc Int Conf Mach Learn
– ident: ref148
  doi: 10.1109/CVPR46437.2021.00672
– volume: 17
  start-page: 59:1
  year: 2016
  ident: ref92
  article-title: Domain-adversarial training of neural networks
  publication-title: J Mach Learn Res
– ident: ref232
  doi: 10.1007/978-3-030-01270-0_28
– start-page: 1
  year: 2019
  ident: ref162
  article-title: Generalized convolutional forest networks for domain generalization and visual recognition
  publication-title: Proc Int Conf Learn Representations
– ident: ref48
  doi: 10.1109/ICASSP40776.2020.9053273
– ident: ref53
  doi: 10.1109/ICCV48922.2021.00876
– year: 2021
  ident: ref79
  article-title: Unsupervised domain generalization for person re-identification: A domain-specific adaptive framework
– ident: ref81
  doi: 10.1109/CVPR46437.2021.00811
– ident: ref35
  doi: 10.1109/CVPRW.2018.00143
– ident: ref138
  doi: 10.1109/ICCV48922.2021.00642
– ident: ref26
  doi: 10.1162/neco.1994.6.5.851
– ident: ref142
  doi: 10.1109/CVPR46437.2021.01411
– start-page: 1455
  year: 2016
  ident: ref65
  article-title: Robust domain generalisation by enforcing distribution invariance
  publication-title: Proc 25th Int Joint Conf Artif Intell
– volume: 3
  start-page: 1
  year: 2016
  ident: ref10
  article-title: A survey of transfer learning
  publication-title: J Big Data
  doi: 10.1186/s40537-016-0043-6
– ident: ref82
  doi: 10.1109/WACV51458.2022.00024
– ident: ref242
  doi: 10.18653/v1/D19-1018
– start-page: 3438
  year: 2021
  ident: ref105
  article-title: Invariance principle meets information bottleneck for out-of-distribution generalization
  publication-title: Proc Int Conf Neural Inf Process
– year: 2018
  ident: ref16
  article-title: Meta-learning: A survey
– ident: ref239
  doi: 10.1145/3308560.3317593
– ident: ref43
  doi: 10.1007/978-3-030-58517-4_33
– ident: ref130
  doi: 10.1109/CVPR46437.2021.00820
– ident: ref233
  doi: 10.1109/ICCV.2019.00149
– ident: ref80
  doi: 10.1145/3459637.3482315
– start-page: 5334
  year: 2018
  ident: ref38
  article-title: Generalizing to unseen domains via adversarial data augmentation
  publication-title: Proc Int Conf Neural Inf Process
– ident: ref204
  doi: 10.1609/aaai.v29i1.9542
– ident: ref12
  doi: 10.1016/j.neucom.2018.05.083
– year: 2021
  ident: ref199
  article-title: Dynamically decoding source domain knowledge for unseen domain generalization
– year: 2019
  ident: ref28
  article-title: A generalization error bound for multi-class domain generalization
– start-page: 1
  year: 2021
  ident: ref157
  article-title: Class-conditioned domain generalization via wasserstein distributional robust optimization
  publication-title: Proc RobustML Workshop ICLR
– year: 2018
  ident: ref118
  article-title: Domain2Vec: Deep domain generalization
– ident: ref241
  doi: 10.1038/s41467-020-16185-w
– ident: ref78
  doi: 10.1109/ICASSP39728.2021.9413872
– ident: ref191
  doi: 10.1609/aaai.v30i1.10306
– start-page: 1
  year: 2020
  ident: ref85
  article-title: Zero shot domain generalization
  publication-title: Proc Brit Mach Vis Virtual Conf
– ident: ref169
  doi: 10.1186/s40537-019-0197-0
– start-page: 1
  year: 2021
  ident: ref168
  article-title: Understanding out-of-distribution: A perspective of data dynamics
  publication-title: Proc Int Conf Neural Inf Process Syst Workshop
– ident: ref192
  doi: 10.1007/978-3-319-49409-8_35
– ident: ref194
  doi: 10.1109/CVPR.2017.437
– year: 2014
  ident: ref188
  article-title: Deep domain confusion: Maximizing for domain invariance
– year: 2018
  ident: ref205
  article-title: Causal generative domain adaptation networks
– year: 2021
  ident: ref217
  article-title: Semi-supervised domain generalization in real world: New benchmark and strong baseline
– ident: ref129
  doi: 10.1109/CVPR46437.2021.01141
– start-page: 187
  year: 2018
  ident: ref137
  article-title: Domain generalization with domain-specific aggregation modules
  publication-title: Proc German Conf Pattern Recognit
– start-page: 6447
  year: 2019
  ident: ref143
  article-title: Domain generalization via model-agnostic learning of semantic features
  publication-title: Proc Int Conf Neural Inf Process
– year: 2009
  ident: ref1
  publication-title: Dataset Shift in Machine Learning
– year: 2020
  ident: ref234
  article-title: The iWildCam 2020 competition dataset
– start-page: 3915
  year: 2019
  ident: ref19
  article-title: Feature-critic networks for heterogeneous domain generalization
  publication-title: Proc Int Conf Mach Learn
– year: 2017
  ident: ref176
  article-title: Wasserstein auto-encoders
– ident: ref181
  doi: 10.1109/TNN.2010.2091281
– ident: ref193
  doi: 10.1109/WACV.2018.00219
– ident: ref77
  doi: 10.1007/978-3-030-58542-6_5
– ident: ref73
  doi: 10.1109/TIM.2020.3016068
– ident: ref257
  doi: 10.1007/s10994-021-06080-w
– year: 2020
  ident: ref263
  article-title: Language models are few-shot learners
  publication-title: Proc Int Conf Neural Inf Process
– year: 2021
  ident: ref47
  article-title: DomainMix: Learning generalizable person re-identification without human annotations
  publication-title: Proc Brit Mach Vis Conf
– ident: ref139
  doi: 10.1109/ICIP.2018.8451318
– start-page: 1
  year: 2018
  ident: ref37
  article-title: Generalizing across domains via cross-gradient training
  publication-title: Proc Int Conf Learn Representations
– ident: ref113
  doi: 10.1007/978-3-319-10578-9_41
– start-page: 1
  year: 2020
  ident: ref155
  article-title: Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization
  publication-title: Proc Int Conf Learn Representations
– start-page: 998
  year: 2018
  ident: ref18
  article-title: MetaReg: Towards domain generalization using meta-regularization
  publication-title: Proc Int Conf Neural Inf Process
– year: 2016
  ident: ref251
  article-title: OpenAI gym
– ident: ref215
  doi: 10.1109/ICCV48922.2021.00883
– ident: ref24
  doi: 10.1007/s10994-009-5152-4
– year: 2017
  ident: ref60
  article-title: Domain generalization by marginal transfer learning
– ident: ref52
  doi: 10.1109/CVPR46437.2021.00029
– ident: ref13
  doi: 10.1109/MSP.2014.2347059
– ident: ref30
  doi: 10.1109/ICRA.2019.8794443
– ident: ref99
  doi: 10.1016/j.patcog.2019.107124
SSID ssj0008781
Score 2.7568667
Snippet Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 8052
SubjectTerms Adaptation models
Algorithms
Computational modeling
Data models
domain adaptation
Domain generalization
Machine learning
Multitasking
out-of-distribution generalization
Predictive models
Task analysis
Training
transfer learning
Title Generalizing to Unseen Domains: A Survey on Domain Generalization
URI https://ieeexplore.ieee.org/document/9782500
https://www.proquest.com/docview/2834305836
Volume 35
WOSCitedRecordID wos001033571000032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-2191
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008781
  issn: 1041-4347
  databaseCode: RIE
  dateStart: 19890101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL3M4YM-ON0Up1Py4JNYTb9b34ZuCMoQ3GRvJWlSGGgr6zbQX-9NlpaBIvjWlgRCbj7O6U3OAbjwvFDaNHYsJkWGBIVSizFXWrHvC5F6ksY6Y_r6FI5G0XQaPzfgqr4LI6XUh8_ktXrUuXxRpEv1q0ypweKOjQR9KwyD9V2tetWNQm1IiuwCOZHrhSaDie24GT_eD5AJOg4SVCyljNc39iBtqvJjJdbby7D1v4btw56BkaS_jvsBNGTehlZl0UDMjG3D7obeYAf6RmR69oWvZFGQSV4ijyX3xTub5eUt6ZOX5XwlP0lRfSR1FR3CQ5gMB-O7B8t4KFip68cLK-CIV2zuCt_1RcBpmmW2Es2TktmSMsY5IgLhZBwnoowckUVBKJyUe4yngtPYPYJmXuTyGAgCv8DP3Ih5CnaFyIWU1g6zOSJOm0WsC7Tq1SQ1AuPK5-It0USDxokKRKICkZhAdOGyrvKxVtf4q3BH9Xxd0HR6F3pV6BIz_8oEQZPSMovc4OT3Wqewo4zj10f5etBczJfyDLbT1WJWzs_10PoGEODJvg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL0MFdQHp1NxOjUPPonV9Lv1bahjsjkEN9lbSZoUBtrKvkB_vTdZVgaK4FtbEgi5-TinNzkH4MLzQmnT2LGYFBkSFEotxlxpxb4vROpJGuuM6Ws37PWi4TB-rsBVeRdGSqkPn8lr9ahz-aJIZ-pXmVKDxR0bCfq673kOXdzWKtfdKNSWpMgvkBW5XmhymNiSm37n_gG5oOMgRcVSynp9ZRfStio_1mK9wbSq_2vaLuwYIEmai8jvQUXmNaguTRqImbM12F5RHNyHppGZHn3hK5kWZJBPkMmS--KdjfLJLWmSl9l4Lj9JsfxIyio6iAcwaD3079qWcVGwUtePp1bAEbHY3BW-64uA0zTLbCWbJyWzJWWMc8QEwsk4TkUZOSKLglA4KfcYTwWnsXsIa3mRyyMgCP0CP3Mj5ingFSIbUmo7zOaIOW0WsTrQZa8mqZEYV04Xb4mmGjROVCASFYjEBKIOl2WVj4W-xl-F91XPlwVNp9ehsQxdYmbgJEHYpNTMIjc4_r3WOWy2-0_dpPvY65zAlrKRXxzsa8DadDyTp7CRzqejyfhMD7Nvu3_NBQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Generalizing+to+Unseen+Domains%3A+A+Survey+on+Domain+Generalization&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Wang%2C+Jindong&rft.au=Lan%2C+Cuiling&rft.au=Liu%2C+Chang&rft.au=Ouyang%2C+Yidong&rft.date=2023-08-01&rft.issn=1041-4347&rft.eissn=1558-2191&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTKDE.2022.3178128&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TKDE_2022_3178128
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon