VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis

Real‐world machine learning models require rigorous evaluation before deployment, especially in safety‐critical domains like autonomous driving and surveillance. The evaluation of machine learning models often focuses on data slices, which are subsets of the data that share a set of characteristics....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer graphics forum Ročník 44; číslo 3
Hlavní autoři: Yan, Xinyuan, Xuan, Xiwei, Ono, Jorge Piazentin, Guo, Jiajing, Mohanty, Vikram, Kumar, Shekar Arvind, Gou, Liang, Wang, Bei, Ren, Liu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Blackwell Publishing Ltd 01.06.2025
Témata:
ISSN:0167-7055, 1467-8659
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Real‐world machine learning models require rigorous evaluation before deployment, especially in safety‐critical domains like autonomous driving and surveillance. The evaluation of machine learning models often focuses on data slices, which are subsets of the data that share a set of characteristics. Data slice finding automatically identifies conditions or data subgroups where models underperform, aiding developers in mitigating performance issues. Despite its popularity and effectiveness, data slicing for vision model validation faces several challenges. First, data slicing often needs additional image metadata or visual concepts, and falls short in certain computer vision tasks, such as object detection. Second, understanding data slices is a labor‐intensive and mentally demanding process that heavily relies on the expert's domain knowledge. Third, data slicing lacks a human‐in‐the‐loop solution that allows experts to form hypothesis and test them interactively. To overcome these limitations and better support the machine learning operations lifecycle, we introduce VISLIX, a novel visual analytics framework that employs state‐of‐the‐art foundation models to help domain experts analyze slices in computer vision models. Our approach does not require image metadata or visual concepts, automatically generates natural language insights, and allows users to test data slice hypothesis interactively. We evaluate VISLIX with an expert study and three use cases, that demonstrate the effectiveness of our tool in providing comprehensive insights for validating object detection models.
AbstractList Real‐world machine learning models require rigorous evaluation before deployment, especially in safety‐critical domains like autonomous driving and surveillance. The evaluation of machine learning models often focuses on data slices, which are subsets of the data that share a set of characteristics. Data slice finding automatically identifies conditions or data subgroups where models underperform, aiding developers in mitigating performance issues. Despite its popularity and effectiveness, data slicing for vision model validation faces several challenges. First, data slicing often needs additional image metadata or visual concepts, and falls short in certain computer vision tasks, such as object detection. Second, understanding data slices is a labor‐intensive and mentally demanding process that heavily relies on the expert's domain knowledge. Third, data slicing lacks a human‐in‐the‐loop solution that allows experts to form hypothesis and test them interactively. To overcome these limitations and better support the machine learning operations lifecycle, we introduce VISLIX, a novel visual analytics framework that employs state‐of‐the‐art foundation models to help domain experts analyze slices in computer vision models. Our approach does not require image metadata or visual concepts, automatically generates natural language insights, and allows users to test data slice hypothesis interactively. We evaluate VISLIX with an expert study and three use cases, that demonstrate the effectiveness of our tool in providing comprehensive insights for validating object detection models.
Author Ono, Jorge Piazentin
Wang, Bei
Yan, Xinyuan
Xuan, Xiwei
Guo, Jiajing
Kumar, Shekar Arvind
Mohanty, Vikram
Gou, Liang
Ren, Liu
Author_xml – sequence: 1
  givenname: Xinyuan
  orcidid: 0000-0003-3396-1310
  surname: Yan
  fullname: Yan, Xinyuan
  organization: Scientific Computing and Imaging Institute, University of Utah
– sequence: 2
  givenname: Xiwei
  orcidid: 0000-0002-0828-8761
  surname: Xuan
  fullname: Xuan, Xiwei
  organization: University of California
– sequence: 3
  givenname: Jorge Piazentin
  orcidid: 0000-0002-2424-0186
  surname: Ono
  fullname: Ono, Jorge Piazentin
  organization: Bosch Research North America and Bosch Center for Artificial Intelligence (BCAI)
– sequence: 4
  givenname: Jiajing
  orcidid: 0000-0003-0511-136X
  surname: Guo
  fullname: Guo, Jiajing
  organization: Bosch Research North America and Bosch Center for Artificial Intelligence (BCAI)
– sequence: 5
  givenname: Vikram
  orcidid: 0000-0001-6296-3134
  surname: Mohanty
  fullname: Mohanty, Vikram
  organization: Bosch Research North America and Bosch Center for Artificial Intelligence (BCAI)
– sequence: 6
  givenname: Shekar Arvind
  orcidid: 0000-0002-5853-5310
  surname: Kumar
  fullname: Kumar, Shekar Arvind
  organization: Robert Bosch GmbH
– sequence: 7
  givenname: Liang
  orcidid: 0009-0006-9138-3351
  surname: Gou
  fullname: Gou, Liang
  organization: Splunk Technology
– sequence: 8
  givenname: Bei
  orcidid: 0000-0002-9240-0700
  surname: Wang
  fullname: Wang, Bei
  organization: Scientific Computing and Imaging Institute, University of Utah
– sequence: 9
  givenname: Liu
  orcidid: 0009-0002-1813-8844
  surname: Ren
  fullname: Ren, Liu
  organization: Bosch Research North America and Bosch Center for Artificial Intelligence (BCAI)
BookMark eNp1kEFPwjAYhhuDiYAe_AdNPHkYtN3abt4ICi7BeECRW1O2FotjxXZI9u-tzqvf5fsOz_vmyzMAvdrWCoBrjEY4zLjY6hFHmNAz0McJ41HKaNYDfYTDzRGlF2Dg_Q4hlHBG--BtlS8X-foOTmq4nuRw5uRenaz7gNo6uJKVKWVj6i1cGW9sDZ9sqSoPT6Z5h8vKFAreG1_YL-VaKOsy1Miq9cZfgnMtK6-u_vYQvM4eXqaP0eJ5nk8ni6ggNKMR2WSas41GLE03XHFMSZbSkqWcSsQ1SkqEEaGa8zLThEjCeKy4ziRmKuOSxENw0_UenP08Kt-InT268IQXMYlJEsJJEqjbjiqc9d4pLQ7O7KVrBUbix5sI3sSvt8COO_ZkKtX-D4rpfNYlvgHKV23g
Cites_doi 10.1109/JPROC.2023.3238524
10.1109/ICCV.2015.135
10.1109/CVPR42600.2020.01164
10.1145/3531146.3533240
10.1145/3640543.3645163
10.32614/CRAN.package.uwot
10.1007/s11263-019-01247-4
10.1109/TMM.2016.2642789
10.1109/ICDE.2019.00139
10.1145/3035918.3035928
10.1145/3479569
10.3390/app13084956
10.1109/TVCG.2020.3030350
10.1145/3544548.3581373
10.1109/ICCV.2015.169
10.1145/335191.335372
10.1145/3544548.3581268
10.18653/v1/2020.findings-emnlp.253
10.1145/3448016.3457323
10.1145/3448016.3457284
10.1007/978-3-642-37456-2_14
10.1109/ICPR48806.2021.9413131
10.1016/0377-0427(87)90125-7
10.1038/s41586-019-1138-y
10.1109/TVCG.2025.3546644
10.1609/hcomp.v11i1.27548
10.18653/v1/2021.findings-acl.336
10.1145/3544548.3581555
10.1109/CVPR52733.2024.02484
10.1016/j.isprsjprs.2022.12.021
10.18653/v1/2022.findings-naacl.31
ContentType Journal Article
Copyright 2025 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
2025 The Eurographics Association and John Wiley & Sons Ltd.
Copyright_xml – notice: 2025 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
– notice: 2025 The Eurographics Association and John Wiley & Sons Ltd.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1111/cgf.70125
DatabaseName CrossRef
Computer and Information Systems 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
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage n/a
ExternalDocumentID 10_1111_cgf_70125
CGF70125
Genre article
GrantInformation_xml – fundername: NSF
  funderid: IIS‐2205418; DMS‐2134223
– fundername: Utah Board of Higher Education's Deep Technology Initiative
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEUYR
AEYWJ
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHEFC
AHQJS
AIDQK
AIDYY
AITYG
AIURR
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAYXX
AIQQE
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2595-2b9f76bf0688b7e7152985d6875a07f04d01025f77d9f22a2673e7f9a16e97a23
IEDL.DBID DRFUL
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001493947300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Sat Aug 23 12:59:47 EDT 2025
Sat Nov 29 07:41:02 EST 2025
Wed Jul 23 09:40:20 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2595-2b9f76bf0688b7e7152985d6875a07f04d01025f77d9f22a2673e7f9a16e97a23
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-0511-136X
0009-0006-9138-3351
0000-0002-2424-0186
0000-0003-3396-1310
0009-0002-1813-8844
0000-0002-0828-8761
0000-0002-9240-0700
0000-0002-5853-5310
0000-0001-6296-3134
PQID 3232402544
PQPubID 30877
PageCount 12
ParticipantIDs proquest_journals_3232402544
crossref_primary_10_1111_cgf_70125
wiley_primary_10_1111_cgf_70125_CGF70125
PublicationCentury 2000
PublicationDate June 2025
2025-06-00
20250601
PublicationDateYYYYMMDD 2025-06-01
PublicationDate_xml – month: 06
  year: 2025
  text: June 2025
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2025
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2021; 5
2000; 29
2023; 13
2023; 11
2016; 19
2024; 30
2020; 128
2023; 1
2019; 568
2020; 33
2025
2024
2024; 36
2021; 1
2022; 29
1987; 20
2023
2022
2023; 196
2021
2020
2021; 139
2023; 111
2019
2020; 27
2018
2017
2015
1994; 1215
2013
2018; 31
e_1_2_10_23_2
e_1_2_10_44_2
e_1_2_10_21_2
e_1_2_10_42_2
e_1_2_10_40_2
Radford A. (e_1_2_10_46_2) 2021
e_1_2_10_18_2
e_1_2_10_39_2
e_1_2_10_53_2
e_1_2_10_16_2
e_1_2_10_37_2
Pastor E. (e_1_2_10_43_2) 2023
e_1_2_10_55_2
e_1_2_10_6_2
e_1_2_10_14_2
e_1_2_10_35_2
e_1_2_10_11_2
e_1_2_10_34_2
e_1_2_10_58_2
Chen C. (e_1_2_10_12_2) 2024; 30
Bordes F. (e_1_2_10_8_2) 2024; 36
e_1_2_10_30_2
e_1_2_10_51_2
Agrawal R. (e_1_2_10_4_2) 1994; 1215
Zhang X. (e_1_2_10_61_2) 2022; 29
e_1_2_10_63_2
e_1_2_10_27_2
e_1_2_10_48_2
e_1_2_10_22_2
e_1_2_10_45_2
e_1_2_10_20_2
e_1_2_10_41_2
Li C. (e_1_2_10_36_2) 2024; 36
Krishnakumar A. (e_1_2_10_29_2) 2021; 1
e_1_2_10_19_2
e_1_2_10_3_2
e_1_2_10_17_2
e_1_2_10_5_2
e_1_2_10_15_2
e_1_2_10_38_2
e_1_2_10_54_2
e_1_2_10_7_2
e_1_2_10_13_2
e_1_2_10_9_2
e_1_2_10_57_2
e_1_2_10_33_2
e_1_2_10_59_2
e_1_2_10_10_2
e_1_2_10_31_2
Liu H. (e_1_2_10_32_2) 2024; 36
Sohoni N. (e_1_2_10_50_2) 2020; 33
Touvron H. (e_1_2_10_52_2) 2023; 1
Idrissi B. Y. (e_1_2_10_25_2) 2022
Xuan X. (e_1_2_10_56_2) 2024
e_1_2_10_60_2
Adebayo J. (e_1_2_10_2_2) 2018; 31
e_1_2_10_28_2
e_1_2_10_62_2
e_1_2_10_26_2
e_1_2_10_49_2
e_1_2_10_24_2
e_1_2_10_47_2
References_xml – volume: 1215
  start-page: 487
  year: 1994
  end-page: 499
  article-title: Fast algorithms for mining association rules
  publication-title: Proceedings of 20th International Conference on Very Large Data Bases (VLDB)
– start-page: 4003
  year: 2023
  end-page: 4014
– start-page: 160
  year: 2013
  end-page: 172
  article-title: Density-based clustering based on hierarchical density estimates
– start-page: 2290
  year: 2021
  end-page: 2299
– volume: 31
  year: 2018
  article-title: Sanity checks for saliency maps
  publication-title: Advances in neural information processing systems
– start-page: 1550
  year: 2019
  end-page: 1553
  article-title: Slice Finder: Automated data slicing for model validation
– volume: 568
  start-page: 477
  issue: 7753
  year: 2019
  end-page: 486
  article-title: Machine behaviour
  publication-title: Nature
– volume: 13
  start-page: 4956
  issue: 8
  year: 2023
  article-title: An analysis of artificial intelligence techniques in surveillance video anomaly detection: A comprehensive survey
  publication-title: Applied Sciences
– year: 2023
  article-title: A hierarchical approach to anomalous subgroup discovery
– start-page: 274
  year: 2024
  end-page: 287
– start-page: 3840
  year: 2021
  end-page: 3852
– volume: 29
  start-page: 1
  issue: 2
  year: 2000
  end-page: 12
  article-title: Mining frequent patterns without candidate generation
  publication-title: ACM sigmod record
– start-page: 1
  year: 2023
  end-page: 14
– year: 2018
– start-page: 4090
  year: 2023
  end-page: 4099
– volume: 128
  start-page: 261
  year: 2020
  end-page: 318
  article-title: Deep learning for generic object detection: A survey
  publication-title: International journal of computer vision
– volume: 33
  start-page: 19339
  year: 2020
  end-page: 19352
  article-title: No subclass left behind: Fine-grained robustness in coarse-grained classification problems
  publication-title: Advances in Neural Information Processing Systems
– start-page: 4126
  year: 2017
  end-page: 4134
– start-page: 1
  year: 2023
  end-page: 20
– start-page: 1440
  year: 2015
  end-page: 1448
– volume: 36
  year: 2024
  article-title: LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day
  publication-title: Advances in Neural Information Processing Systems
– volume: 27
  start-page: 261
  issue: 2
  year: 2020
  end-page: 271
  article-title: VATLD: A visual analytics system to assess, understand and improve traffic light detection
  publication-title: IEEE transactions on visualization and computer graphics
– year: 2025
– year: 2022
– volume: 30
  start-page: 76
  issue: 1
  year: 2024
  end-page: 86
  article-title: A unified interactive model evaluation for classification, object detection, and instance segmentation in computer vision
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 36
  year: 2024
  article-title: Visual instruction tuning
  publication-title: Advances in neural information processing systems
– volume: 139
  start-page: 8748
  year: 2021
  end-page: 8763
  article-title: Learning transferable visual models from natural language supervision
– year: 2019
– start-page: 541
  year: 2017
  end-page: 556
– start-page: 2810
  year: 2020
  end-page: 2829
– start-page: 215
  year: 2024
  end-page: 231
  article-title: SLIM: Spuriousness mitigation with minimal human annotations
– start-page: 1400
  year: 2021
  end-page: 1412
– volume: 1
  year: 2021
  article-title: UDIS: Unsupervised discovery of bias in deep visual recognition models
  publication-title: British Machine Vision Conference (BMVC)
– volume: 19
  start-page: 944
  issue: 5
  year: 2016
  end-page: 954
  article-title: Attentive contexts for object detection
  publication-title: IEEE Transactions on Multimedia
– start-page: 19730
  year: 2023
  end-page: 19742
– start-page: 11621
  year: 2020
  end-page: 11631
– volume: 111
  start-page: 257
  issue: 3
  year: 2023
  end-page: 276
  article-title: Object detection in 20 years: A survey
  publication-title: Proceedings of the IEEE
– start-page: 8371
  year: 2024
  end-page: 8376
– start-page: 1962
  year: 2022
  end-page: 1981
– volume: 196
  start-page: 146
  year: 2023
  end-page: 177
  article-title: Perception and sensing for autonomous vehicles under adverse weather conditions: A survey
  publication-title: ISPRS Journal of Photogrammetry and Remote Sensing
– start-page: 5145
  year: 2021
  end-page: 5152
  article-title: N2D:(not too) deep clustering via clustering the local manifold of an autoencoded embedding
– volume: 1
  year: 2023
  article-title: Llama 2: Open foundation and fine-tuned chat models
  publication-title: arXiv preprint arXiv:2307.09288
– start-page: 21475
  year: 2022
  end-page: 21483
– start-page: 1
  year: 2023
  end-page: 16
– start-page: 26296
  year: 2024
  end-page: 26306
– year: 2023
– volume: 5
  start-page: 1
  issue: CSCW2
  year: 2021
  end-page: 22
  article-title: Discovering and validating AI errors with crowdsourced failure reports
  publication-title: Proceedings of the ACM on Human-Computer Interaction
– start-page: 1134
  year: 2015
  end-page: 1142
– start-page: 336
  year: 2022
  end-page: 351
  article-title: Simple data balancing achieves competitive worst-group-accuracy
– start-page: 410
  year: 2022
  end-page: 424
  article-title: Few-shot self-rationalization with natural language prompts
– volume: 29
  start-page: 842
  issue: 1
  year: 2022
  end-page: 852
  article-title: SliceTeller: A data slice-driven approach for machine learning model validation
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 20
  start-page: 53
  year: 1987
  end-page: 65
  article-title: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
  publication-title: Journal of computational and applied mathematics
– volume: 36
  year: 2024
  article-title: PUG: Photorealistic and semantically controllable synthetic data for representation learning
  publication-title: Advances in Neural Information Processing Systems
– volume: 11
  start-page: 65
  year: 2023
  end-page: 76
  article-title: Where does my model underperform? a human evaluation of slice discovery algorithms
  publication-title: Proceedings of the AAAI Conference on Human Computation and Crowdsourcing
– ident: e_1_2_10_20_2
– ident: e_1_2_10_34_2
– ident: e_1_2_10_59_2
  doi: 10.1109/JPROC.2023.3238524
– ident: e_1_2_10_26_2
– ident: e_1_2_10_18_2
– volume: 30
  start-page: 76
  issue: 1
  year: 2024
  ident: e_1_2_10_12_2
  article-title: A unified interactive model evaluation for classification, object detection, and instance segmentation in computer vision
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– ident: e_1_2_10_22_2
  doi: 10.1109/ICCV.2015.135
– ident: e_1_2_10_9_2
  doi: 10.1109/CVPR42600.2020.01164
– ident: e_1_2_10_16_2
  doi: 10.1145/3531146.3533240
– ident: e_1_2_10_17_2
– ident: e_1_2_10_42_2
– volume: 1
  year: 2023
  ident: e_1_2_10_52_2
  article-title: Llama 2: Open foundation and fine-tuned chat models
  publication-title: arXiv preprint arXiv:2307.09288
– ident: e_1_2_10_62_2
  doi: 10.1145/3640543.3645163
– volume-title: 39th IEEE International Conference on Data Engineering, ICDE 2023, Anaheim, California, USA, April 3–7, 2023
  year: 2023
  ident: e_1_2_10_43_2
– ident: e_1_2_10_39_2
  doi: 10.32614/CRAN.package.uwot
– ident: e_1_2_10_41_2
– ident: e_1_2_10_33_2
  doi: 10.1007/s11263-019-01247-4
– ident: e_1_2_10_55_2
– ident: e_1_2_10_58_2
– ident: e_1_2_10_35_2
  doi: 10.1109/TMM.2016.2642789
– ident: e_1_2_10_13_2
  doi: 10.1109/ICDE.2019.00139
– ident: e_1_2_10_63_2
– volume: 36
  year: 2024
  ident: e_1_2_10_8_2
  article-title: PUG: Photorealistic and semantically controllable synthetic data for representation learning
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_10_28_2
– volume: 1215
  start-page: 487
  year: 1994
  ident: e_1_2_10_4_2
  article-title: Fast algorithms for mining association rules
  publication-title: Proceedings of 20th International Conference on Very Large Data Bases (VLDB)
– ident: e_1_2_10_5_2
  doi: 10.1145/3035918.3035928
– ident: e_1_2_10_10_2
  doi: 10.1145/3479569
– ident: e_1_2_10_51_2
  doi: 10.3390/app13084956
– volume: 33
  start-page: 19339
  year: 2020
  ident: e_1_2_10_50_2
  article-title: No subclass left behind: Fine-grained robustness in coarse-grained classification problems
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_10_23_2
  doi: 10.1109/TVCG.2020.3030350
– ident: e_1_2_10_54_2
– ident: e_1_2_10_6_2
– ident: e_1_2_10_15_2
– ident: e_1_2_10_31_2
– ident: e_1_2_10_3_2
  doi: 10.1145/3544548.3581373
– ident: e_1_2_10_21_2
  doi: 10.1109/ICCV.2015.169
– ident: e_1_2_10_24_2
  doi: 10.1145/335191.335372
– volume: 29
  start-page: 842
  issue: 1
  year: 2022
  ident: e_1_2_10_61_2
  article-title: SliceTeller: A data slice-driven approach for machine learning model validation
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– volume: 31
  year: 2018
  ident: e_1_2_10_2_2
  article-title: Sanity checks for saliency maps
  publication-title: Advances in neural information processing systems
– ident: e_1_2_10_11_2
  doi: 10.1145/3544548.3581268
– ident: e_1_2_10_38_2
  doi: 10.18653/v1/2020.findings-emnlp.253
– ident: e_1_2_10_53_2
– ident: e_1_2_10_49_2
  doi: 10.1145/3448016.3457323
– ident: e_1_2_10_44_2
  doi: 10.1145/3448016.3457284
– start-page: 215
  volume-title: European Conference on Computer Vision
  year: 2024
  ident: e_1_2_10_56_2
– start-page: 336
  volume-title: Conference on Causal Learning and Reasoning
  year: 2022
  ident: e_1_2_10_25_2
– ident: e_1_2_10_14_2
  doi: 10.1007/978-3-642-37456-2_14
– ident: e_1_2_10_40_2
  doi: 10.1109/ICPR48806.2021.9413131
– ident: e_1_2_10_48_2
  doi: 10.1016/0377-0427(87)90125-7
– ident: e_1_2_10_45_2
  doi: 10.1038/s41586-019-1138-y
– ident: e_1_2_10_57_2
  doi: 10.1109/TVCG.2025.3546644
– volume: 36
  year: 2024
  ident: e_1_2_10_36_2
  article-title: LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_10_19_2
– volume: 1
  year: 2021
  ident: e_1_2_10_29_2
  article-title: UDIS: Unsupervised discovery of bias in deep visual recognition models
  publication-title: British Machine Vision Conference (BMVC)
– ident: e_1_2_10_27_2
  doi: 10.1609/hcomp.v11i1.27548
– volume: 36
  year: 2024
  ident: e_1_2_10_32_2
  article-title: Visual instruction tuning
  publication-title: Advances in neural information processing systems
– ident: e_1_2_10_47_2
  doi: 10.18653/v1/2021.findings-acl.336
– ident: e_1_2_10_7_2
  doi: 10.1145/3544548.3581555
– ident: e_1_2_10_30_2
  doi: 10.1109/CVPR52733.2024.02484
– ident: e_1_2_10_60_2
  doi: 10.1016/j.isprsjprs.2022.12.021
– ident: e_1_2_10_37_2
  doi: 10.18653/v1/2022.findings-naacl.31
– start-page: 8748
  volume-title: Proceedings of the 38th International Conference on Machine Learning
  year: 2021
  ident: e_1_2_10_46_2
SSID ssj0004765
Score 2.4369004
Snippet Real‐world machine learning models require rigorous evaluation before deployment, especially in safety‐critical domains like autonomous driving and...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Index Database
Publisher
SubjectTerms CCS Concepts
Computer vision
Computer vision tasks
Computing methodologies → Model verification and validation
Effectiveness
Human‐centered computing → Visual analytics
Hypotheses
Interactive systems and tools
Machine learning
Metadata
Object recognition
Subgroups
Title VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.70125
https://www.proquest.com/docview/3232402544
Volume 44
WOSCitedRecordID wos001493947300001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1q60EPfovVKot48BKJu8luo6dSjRZKEWtrbmE32S2FEqWpgv_e3W3S1oMgeMshCWEyb-bNsPMG4EKJ1NMYIo4kgjraKbgjUlfDXZMBrjMMw9KzyyZYr9eMouCpArflLMxcH2LRcDPIsPHaAJyLfAXkyUhdMR1e_TWoYe23fhVqd8_hoLsci2TUL6W9jWhMISxkDvIsHv6ZjpYcc5Wp2lQTbv_rI3dgq2CYqDV3iV2oyGwPNld0B_fhddjpdzvRDWplKGp1UFie0EKawqKhpuZm6CEboaGdPEdmYdokR6Zni_oTHVrQ3ThPzOHPL8SzFJXKJgcwCO9f2o9OsWHBSXTZ4ztYBIpRoczmGcEk08k8aPop1UUMd5lyvdRIzvmKsTRQGHNMGZFMBfyayoBxTA6hmr1l8giQryijhv1pwugxIjhN3YQIiTkXTY-IOpyXho7f50IacVmAaCvF1kp1aJS_IC6wlMfEkD4rpVaHS2vs318Qtx9Ce3H891tPYAObpb62tdKA6mz6IU9hPfmcjfPpWeFU32vry7c
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1qK6gHv8Vq1UU8eInEfOw24qW0xgZjEVtrb2E32S2FEqWpgv_e3W3S1oMgeMshCWEyb-bNsPMG4EKwxJEYsg1uM2xIp6AGS0wJd0kGqMwwxOKOXjZBOp36YOA9leC2mIWZ6UPMG24KGTpeK4CrhvQSyuOhuCIyvrorUHGkG0n_rrSe_ZdwMRdJsFtoeyvVmFxZSJ3kmT_8Mx8tSOYyVdW5xt_631duw2bOMVFj5hQ7UOLpLmwsKQ_uwWs_6IbB4AY1UjRoBMgvzmghSWJRX5JzNfaQDlFfz54jtTJtnCHVtUXdsQwuqDXKYnX88wvRNEGFtsk-vPh3vWbbyHcsGLEsfFzDYp4gmAm1e4YRTmQ69-pugmUZQ00iTCdRonOuICTxhGVRCxObE-HRa8w9Qi37AMrpW8oPAbkCE6z4n6SMDrEZxYkZ24xblLK6Y7MqnBeWjt5nUhpRUYJIK0XaSlWoFf8gytGURbaifVpMrQqX2tq_vyBq3vv64ujvt57BWrv3GEZh0Hk4hnVLrfjVjZYalKeTD34Cq_HndJRNTnMP-wa0ZM-n
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1qK6IHv8Vq1UU8eInEfOw24qW0RoOlFGtrbmE32S2FEktTBf-9u9ukrQdB8JZDEsJk3sybYecNwJVgiSMxZBvcZtiQTkENlpgS7pIMUJlhiMUdvWyCdDr1MPS6JbgvZmHm-hCLhptCho7XCuB8kogVlMdDcUNkfHXXoOKoJTJlqLRe_H57ORdJsFtoeyvVmFxZSJ3kWTz8Mx8tSeYqVdW5xt_531fuwnbOMVFj7hR7UOLpPmytKA8ewNsg6LWD8A41UhQ2AuQXZ7SQJLFoIMm5GntIh2igZ8-RWpk2zpDq2qLeWAYX1BplsTr--YVomqBC2-QQ-v7Da_PJyHcsGLEsfFzDYp4gmAm1e4YRTmQ69-pugmUZQ00iTCdRonOuICTxhGVRCxObE-HRW8w9Qi37CMrpe8qPAbkCE6z4n6SMDrEZxYkZ24xblLK6Y7MqXBaWjiZzKY2oKEGklSJtpSrUin8Q5WjKIlvRPi2mVoVrbe3fXxA1H319cfL3Wy9go9vyo3bQeT6FTUtt-NV9lhqUZ9MPfgbr8edslE3Pcwf7BoTYzyI
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=VISLIX+%3A+An+XAI+Framework+for+Validating+Vision+Models+with+Slice+Discovery+and+Analysis&rft.jtitle=Computer+graphics+forum&rft.au=Yan%2C+Xinyuan&rft.au=Xuan%2C+Xiwei&rft.au=Ono%2C+Jorge+Piazentin&rft.au=Guo%2C+Jiajing&rft.date=2025-06-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=44&rft.issue=3&rft_id=info:doi/10.1111%2Fcgf.70125&rft.externalDBID=n%2Fa&rft.externalDocID=10_1111_cgf_70125
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon