Deep Learning for Classification of Hyperspectral Data: A Comparative Review
In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. T...
Gespeichert in:
| Veröffentlicht in: | IEEE geoscience and remote sensing magazine Jg. 7; H. 2; S. 159 - 173 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
01.06.2019
|
| Schlagworte: | |
| ISSN: | 2473-2397, 2168-6831 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. This article presents the state of the art of previous machine-learning approaches, reviews the various deeplearning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties that arise in the implementation of deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided, and a software toolbox is publicly released to allow experimenting with these methods (https://github.com/nshaud/DeepHyperX). This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deeplearning techniques to their own data set. |
|---|---|
| AbstractList | In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. This article presents the state of the art of previous machine-learning approaches, reviews the various deeplearning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties that arise in the implementation of deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided, and a software toolbox is publicly released to allow experimenting with these methods (https://github.com/nshaud/DeepHyperX). This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deeplearning techniques to their own data set. In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the rule, but has intrinsic specificities which make application of deep learning less straightforward than with other optical data. This article presents a state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties which arise to implement deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided and a software toolbox is publicly released to allow experimenting with these methods. 1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset. |
| Author | Le Saux, Bertrand Audebert, Nicolas Lefevre, Sebastien |
| Author_xml | – sequence: 1 givenname: Nicolas orcidid: 0000-0001-6486-3102 surname: Audebert fullname: Audebert, Nicolas email: nicolas.audebert@onera.fr organization: Information Processing and Systems, University Paris Saclay, Palaiseau, France – sequence: 2 givenname: Bertrand orcidid: 0000-0001-7162-6746 surname: Le Saux fullname: Le Saux, Bertrand email: bertrand.le_saux@onera.fr organization: Information Processing and Systems, University Paris Saclay, Palaiseau, France – sequence: 3 givenname: Sebastien orcidid: 0000-0002-2384-8202 surname: Lefevre fullname: Lefevre, Sebastien email: sebastien.lefevre@irisa.fr organization: Research in Computer Science and Random Systems, Universite de Bretagne Sud, France |
| BackLink | https://hal.science/hal-02104998$$DView record in HAL |
| BookMark | eNp9kD1PwzAQhi1UJErpD0AsXhlSfHY-bLaqhRYpCKnAbDnOBYzSJHKiov57EloYGLjlTqf3vY_nnIyqukJCLoHNAJi6eVxtnmecgZpxBTyKxQkZc4hlEEsBo74OExFwoZIzMm3bD9aHjECBHJN0idjQFI2vXPVGi9rTRWna1hXOms7VFa0Lut436NsGbedNSZemM7d0Thf1tjG-F-2QbnDn8POCnBambHF6zBPyen_3slgH6dPqYTFPA8sl64JYoQgFqFjY3OaR4aExChRmOYvzMANbmCiRKstEf7dFbjECkeRZjCZDi1ZMyPVh7rspdePd1vi9ro3T63mqhx7jwEKl5A56bXLQWl-3rcdCW9d9f9Y_40oNTA8M9cBQDwz1kWHvhD_On1X_ea4OHoeIv3qZCMnCSHwBikV-2g |
| CODEN | IGRSCZ |
| CitedBy_id | crossref_primary_10_3390_rs14030608 crossref_primary_10_1371_journal_pone_0328888 crossref_primary_10_1039_D3EW00541K crossref_primary_10_1364_AO_498021 crossref_primary_10_3390_rs16010182 crossref_primary_10_3390_rs15020451 crossref_primary_10_1109_TGRS_2020_3017709 crossref_primary_10_1016_j_jag_2024_104213 crossref_primary_10_1016_j_jrmge_2025_03_018 crossref_primary_10_3390_app10228189 crossref_primary_10_1109_JSTARS_2023_3349175 crossref_primary_10_1016_j_compeleceng_2022_108381 crossref_primary_10_1002_adfm_202423331 crossref_primary_10_1016_j_engappai_2023_106017 crossref_primary_10_1109_MGRS_2022_3161377 crossref_primary_10_1109_TGRS_2022_3217892 crossref_primary_10_1109_TGRS_2022_3185612 crossref_primary_10_1109_JSTARS_2023_3283342 crossref_primary_10_1109_TGRS_2021_3132683 crossref_primary_10_1109_TIP_2023_3287738 crossref_primary_10_1088_1742_6596_1950_1_012087 crossref_primary_10_3390_rs14174288 crossref_primary_10_1007_s11600_024_01473_6 crossref_primary_10_1080_01431161_2023_2171742 crossref_primary_10_3390_rs12182956 crossref_primary_10_1007_s12145_023_01031_6 crossref_primary_10_32604_cmc_2023_033054 crossref_primary_10_1109_LGRS_2021_3119867 crossref_primary_10_1109_MGRS_2020_3043504 crossref_primary_10_1016_j_neucom_2025_130722 crossref_primary_10_1016_j_jfranklin_2025_107532 crossref_primary_10_1109_TGRS_2022_3169018 crossref_primary_10_3390_rs15194796 crossref_primary_10_1109_TCSVT_2025_3526960 crossref_primary_10_1016_j_dsp_2024_104740 crossref_primary_10_1109_TGRS_2020_3005623 crossref_primary_10_1109_TGRS_2023_3336771 crossref_primary_10_1016_j_jfranklin_2024_107464 crossref_primary_10_1016_j_gsf_2023_101562 crossref_primary_10_1016_j_isprsjprs_2019_09_006 crossref_primary_10_1080_07038992_2020_1760714 crossref_primary_10_1109_ACCESS_2024_3455369 crossref_primary_10_1007_s11042_022_12452_8 crossref_primary_10_1016_j_engappai_2023_106234 crossref_primary_10_1016_j_aca_2022_339668 crossref_primary_10_3390_rs14205199 crossref_primary_10_3390_rs13173547 crossref_primary_10_1109_TGRS_2023_3257865 crossref_primary_10_3390_rs15225331 crossref_primary_10_1002_cpe_6945 crossref_primary_10_1109_ACCESS_2020_2997327 crossref_primary_10_1109_TIP_2022_3192712 crossref_primary_10_1007_s11042_023_17546_5 crossref_primary_10_54392_irjmt2365 crossref_primary_10_3390_s20185322 crossref_primary_10_1007_s11042_023_16241_9 crossref_primary_10_1080_22797254_2022_2153747 crossref_primary_10_3390_rs12142335 crossref_primary_10_3390_rs15235483 crossref_primary_10_1109_TIP_2022_3177322 crossref_primary_10_1016_j_jfranklin_2024_107285 crossref_primary_10_1109_TNNLS_2021_3112268 crossref_primary_10_1109_JSTARS_2023_3342983 crossref_primary_10_1109_JSTARS_2022_3212983 crossref_primary_10_3390_electronics13132540 crossref_primary_10_1109_TGRS_2022_3232705 crossref_primary_10_1109_TMM_2023_3290426 crossref_primary_10_1016_j_jag_2024_104308 crossref_primary_10_1109_TCSVT_2022_3215513 crossref_primary_10_1109_JSTARS_2022_3144312 crossref_primary_10_1007_s11760_021_02029_7 crossref_primary_10_1080_01431161_2022_2048319 crossref_primary_10_3390_rs13234921 crossref_primary_10_1109_TGRS_2024_3476116 crossref_primary_10_1080_01431161_2024_2384098 crossref_primary_10_1109_TGRS_2020_2994057 crossref_primary_10_3389_fpls_2021_736334 crossref_primary_10_3390_rs13183637 crossref_primary_10_3390_rs15153900 crossref_primary_10_1016_j_cosrev_2023_100584 crossref_primary_10_1109_ACCESS_2024_3376258 crossref_primary_10_1109_LGRS_2023_3277841 crossref_primary_10_1109_JSTARS_2025_3565894 crossref_primary_10_1088_1742_6596_2562_1_012026 crossref_primary_10_1109_TGRS_2024_3511618 crossref_primary_10_1016_j_displa_2022_102278 crossref_primary_10_1109_JSTARS_2022_3144339 crossref_primary_10_1016_j_jag_2021_102603 crossref_primary_10_1109_ACCESS_2024_3359036 crossref_primary_10_1016_j_isprsjprs_2024_05_003 crossref_primary_10_1109_TGRS_2022_3220748 crossref_primary_10_1016_j_compmedimag_2024_102339 crossref_primary_10_34133_plantphenomics_0197 crossref_primary_10_3390_rs14092265 crossref_primary_10_1109_TGRS_2025_3559137 crossref_primary_10_1109_JSTARS_2020_3019300 crossref_primary_10_1109_LGRS_2022_3181627 crossref_primary_10_1002_srin_202100826 crossref_primary_10_1109_TGRS_2020_3048002 crossref_primary_10_1109_TGRS_2020_3048128 crossref_primary_10_1109_TGRS_2024_3385501 crossref_primary_10_1109_TGRS_2023_3235819 crossref_primary_10_1109_TGRS_2024_3505292 crossref_primary_10_3390_rs17162800 crossref_primary_10_1109_MGRS_2022_3169947 crossref_primary_10_1109_ACCESS_2024_3469228 crossref_primary_10_1109_TGRS_2023_3297216 crossref_primary_10_1109_ACCESS_2024_3420089 crossref_primary_10_1080_07038992_2024_2333424 crossref_primary_10_1109_TGRS_2025_3571606 crossref_primary_10_3390_rs15112720 crossref_primary_10_1007_s12393_022_09327_x crossref_primary_10_1109_TGRS_2022_3167569 crossref_primary_10_1109_TGRS_2020_3035642 crossref_primary_10_3390_rs14205251 crossref_primary_10_1109_TGRS_2025_3599172 crossref_primary_10_3389_fpls_2020_611622 crossref_primary_10_1109_JSTARS_2023_3337112 crossref_primary_10_3390_rs16214050 crossref_primary_10_2340_actadv_v102_2045 crossref_primary_10_3390_rs14030681 crossref_primary_10_1109_TGRS_2022_3181501 crossref_primary_10_3390_app14167361 crossref_primary_10_3390_rs12081294 crossref_primary_10_1016_j_asr_2024_05_064 crossref_primary_10_3390_rs13030498 crossref_primary_10_3390_su142013485 crossref_primary_10_1109_TIM_2023_3279922 crossref_primary_10_1016_j_jfca_2025_108041 crossref_primary_10_1109_MGRS_2022_3145854 crossref_primary_10_3390_s20185262 crossref_primary_10_3390_rs14194982 crossref_primary_10_1109_JSTARS_2025_3581451 crossref_primary_10_1109_TIP_2022_3176537 crossref_primary_10_3390_rs13214342 crossref_primary_10_1109_TGRS_2020_3043267 crossref_primary_10_3788_COL202523_051103 crossref_primary_10_1007_s10489_024_06139_w crossref_primary_10_1109_TGRS_2024_3463745 crossref_primary_10_1109_TGRS_2023_3346714 crossref_primary_10_1109_TGRS_2021_3110601 crossref_primary_10_1364_AO_432704 crossref_primary_10_3390_s25082346 crossref_primary_10_1109_TGRS_2023_3240481 crossref_primary_10_1088_1674_1056_ac8cd7 crossref_primary_10_1109_JSTARS_2021_3135548 crossref_primary_10_1007_s11042_022_13721_2 crossref_primary_10_1109_TGRS_2020_3047682 crossref_primary_10_1002_agj2_21648 crossref_primary_10_1109_JSTARS_2021_3065987 crossref_primary_10_1016_j_compag_2021_106226 crossref_primary_10_1109_TSP_2023_3304789 crossref_primary_10_1109_JSTARS_2022_3232995 crossref_primary_10_3390_rs16163097 crossref_primary_10_1109_LGRS_2024_3393290 crossref_primary_10_1109_JSTARS_2020_2992310 crossref_primary_10_1109_TNNLS_2023_3264587 crossref_primary_10_1109_TGRS_2025_3566070 crossref_primary_10_1007_s00521_025_11315_1 crossref_primary_10_3390_rs16132336 crossref_primary_10_1109_JSTARS_2025_3595648 crossref_primary_10_3390_rs15112879 crossref_primary_10_1016_j_knosys_2025_114372 crossref_primary_10_1109_TGRS_2022_3207933 crossref_primary_10_1109_JSTARS_2024_3424954 crossref_primary_10_1007_s10103_022_03665_2 crossref_primary_10_1016_j_asoc_2025_113055 crossref_primary_10_1016_j_jag_2021_102456 crossref_primary_10_1109_JSTARS_2024_3429492 crossref_primary_10_1109_TGRS_2022_3177478 crossref_primary_10_1109_TGRS_2021_3067096 crossref_primary_10_1109_TGRS_2022_3199467 crossref_primary_10_1109_ACCESS_2023_3339565 crossref_primary_10_1038_s41467_022_27980_y crossref_primary_10_1007_s12524_024_02083_x crossref_primary_10_3390_rs14112653 crossref_primary_10_3390_app14062327 crossref_primary_10_3390_rs15225385 crossref_primary_10_1016_j_rsase_2022_100823 crossref_primary_10_1016_j_inffus_2025_103257 crossref_primary_10_1016_j_infrared_2022_104470 crossref_primary_10_1371_journal_pone_0304202 crossref_primary_10_1109_JSTARS_2025_3571226 crossref_primary_10_1109_JSTARS_2025_3529985 crossref_primary_10_3390_s20226666 crossref_primary_10_1109_TGRS_2023_3242978 crossref_primary_10_3390_land10080867 crossref_primary_10_1109_TGRS_2024_3443953 crossref_primary_10_1080_22797254_2021_2023910 crossref_primary_10_1109_LGRS_2025_3587604 crossref_primary_10_1109_TGRS_2020_3022029 crossref_primary_10_1109_TGRS_2024_3350700 crossref_primary_10_1109_TGRS_2020_2975295 crossref_primary_10_1038_s41598_025_87030_7 crossref_primary_10_3390_rs16224270 crossref_primary_10_1109_TGRS_2022_3203476 crossref_primary_10_1080_01431161_2022_2098078 crossref_primary_10_1109_JSTARS_2025_3596770 crossref_primary_10_1016_j_infrared_2023_104666 crossref_primary_10_1080_01431161_2022_2093621 crossref_primary_10_1080_01431161_2021_1881184 crossref_primary_10_1109_JSTARS_2021_3053567 crossref_primary_10_1109_TGRS_2023_3294227 crossref_primary_10_1080_01431161_2023_2297178 crossref_primary_10_1109_JSTARS_2024_3522318 crossref_primary_10_1016_j_rsase_2024_101390 crossref_primary_10_1109_JSTARS_2021_3078631 crossref_primary_10_3390_rs15245656 crossref_primary_10_3390_rs14184523 crossref_primary_10_1016_j_rse_2021_112652 crossref_primary_10_1016_j_jfca_2024_106404 crossref_primary_10_1109_TGRS_2025_3567632 crossref_primary_10_3390_rs15153795 crossref_primary_10_3390_rs15153793 crossref_primary_10_1016_j_infsof_2023_107281 crossref_primary_10_1109_LGRS_2022_3185407 crossref_primary_10_1109_TCYB_2021_3064571 crossref_primary_10_3390_app14177438 crossref_primary_10_1109_JSTARS_2022_3216590 crossref_primary_10_1016_j_neucom_2025_131016 crossref_primary_10_1109_TGRS_2022_3164341 crossref_primary_10_1109_TGRS_2024_3374081 crossref_primary_10_1109_TGRS_2024_3404929 crossref_primary_10_1109_TGRS_2024_3433025 crossref_primary_10_1016_j_dsp_2021_103016 crossref_primary_10_1145_3543848 crossref_primary_10_1109_TGRS_2022_3232498 crossref_primary_10_1016_j_jhydrol_2019_124482 crossref_primary_10_1016_j_tifs_2021_04_042 crossref_primary_10_1109_JSTARS_2021_3121556 crossref_primary_10_1080_01431161_2023_2232552 crossref_primary_10_1016_j_isprsjprs_2024_09_020 crossref_primary_10_3390_rs16091615 crossref_primary_10_1080_07038992_2023_2248270 crossref_primary_10_1109_JSTARS_2024_3440254 crossref_primary_10_1109_TNNLS_2024_3511575 crossref_primary_10_1080_01431161_2021_1949069 crossref_primary_10_3390_rs15082014 crossref_primary_10_1109_TGRS_2023_3282247 crossref_primary_10_1016_j_neucom_2019_11_092 crossref_primary_10_3390_app13148451 crossref_primary_10_1186_s43074_022_00065_1 crossref_primary_10_3390_rs15174328 crossref_primary_10_3390_rs17081373 crossref_primary_10_1038_s41598_024_69732_6 crossref_primary_10_1109_TGRS_2023_3271424 crossref_primary_10_1109_TGRS_2023_3330568 crossref_primary_10_1109_TNNLS_2022_3158280 crossref_primary_10_1038_s41598_024_58125_4 crossref_primary_10_1016_j_isprsjprs_2021_04_020 crossref_primary_10_1016_j_isprsjprs_2020_10_015 crossref_primary_10_1109_JSTARS_2022_3162423 crossref_primary_10_1016_j_jag_2024_104092 crossref_primary_10_3390_rs16183531 crossref_primary_10_1109_TGRS_2020_3042274 crossref_primary_10_3390_rs13214405 crossref_primary_10_3390_drones7040240 crossref_primary_10_3390_rs12233879 crossref_primary_10_1016_j_eswa_2023_122172 crossref_primary_10_3390_rs13071253 crossref_primary_10_1109_TIM_2023_3271713 crossref_primary_10_1007_s11042_022_12494_y crossref_primary_10_1109_LGRS_2022_3185449 crossref_primary_10_1109_MGRS_2021_3051859 crossref_primary_10_1109_TGRS_2024_3474736 crossref_primary_10_1109_TGRS_2024_3386256 crossref_primary_10_1109_TGRS_2023_3345923 crossref_primary_10_1364_AO_523199 crossref_primary_10_1109_JSTARS_2025_3586779 crossref_primary_10_1080_2150704X_2024_2379513 crossref_primary_10_3390_rs13071248 crossref_primary_10_1016_j_rse_2021_112322 crossref_primary_10_1117_1_JRS_18_016509 crossref_primary_10_3389_ffgc_2023_1179910 crossref_primary_10_1109_ACCESS_2025_3542038 crossref_primary_10_1109_JSTARS_2024_3438123 crossref_primary_10_1109_TGRS_2022_3140353 crossref_primary_10_1109_TGRS_2023_3281490 crossref_primary_10_1016_j_isprsjprs_2021_04_001 crossref_primary_10_1080_01431161_2024_2307943 crossref_primary_10_1109_TGRS_2023_3346923 crossref_primary_10_1109_TGRS_2021_3073924 crossref_primary_10_1007_s40998_025_00871_w crossref_primary_10_1016_j_neucom_2024_128885 crossref_primary_10_1109_ACCESS_2025_3543122 crossref_primary_10_1155_2021_9923491 crossref_primary_10_1109_JSTARS_2020_2984568 crossref_primary_10_3390_rs15184391 crossref_primary_10_1016_j_gsf_2021_101203 crossref_primary_10_3390_rs17121964 crossref_primary_10_1109_TGRS_2023_3349076 crossref_primary_10_1007_s10994_025_06829_7 crossref_primary_10_3390_rs14102355 crossref_primary_10_3390_rs12223839 crossref_primary_10_3390_s25144322 crossref_primary_10_3390_rs12223836 crossref_primary_10_1109_TIP_2021_3055613 crossref_primary_10_3390_s24103153 crossref_primary_10_3390_rs14091968 crossref_primary_10_1109_TGRS_2022_3153673 crossref_primary_10_3390_rs17173015 crossref_primary_10_1109_TGRS_2025_3586287 crossref_primary_10_1109_LGRS_2022_3225151 crossref_primary_10_1080_01431161_2022_2055986 crossref_primary_10_1016_j_asr_2025_04_081 crossref_primary_10_1109_MGRS_2023_3269979 crossref_primary_10_1007_s11432_020_3084_1 crossref_primary_10_1016_j_jag_2023_103482 crossref_primary_10_1109_TGRS_2025_3541879 crossref_primary_10_1016_j_gsf_2022_101425 crossref_primary_10_1109_TGRS_2024_3439094 crossref_primary_10_1007_s00500_021_06105_5 crossref_primary_10_1007_s11042_024_19773_w crossref_primary_10_1109_JSTARS_2022_3221098 crossref_primary_10_1016_j_ecolind_2024_111608 crossref_primary_10_1109_TGRS_2022_3174305 crossref_primary_10_1109_JSTARS_2023_3345411 crossref_primary_10_1109_TGRS_2022_3177935 crossref_primary_10_1109_TGRS_2025_3603650 crossref_primary_10_3390_agronomy11030575 crossref_primary_10_1109_JSTARS_2022_3216624 crossref_primary_10_3390_geosciences12060248 crossref_primary_10_1109_JSTARS_2021_3066378 crossref_primary_10_1016_j_jag_2022_103095 crossref_primary_10_1109_TGRS_2020_3014286 crossref_primary_10_1109_TNNLS_2024_3457781 crossref_primary_10_1109_JSEN_2025_3572485 crossref_primary_10_1109_JSTARS_2023_3283862 crossref_primary_10_1016_j_bspc_2024_106982 crossref_primary_10_1007_s11760_025_04359_2 crossref_primary_10_1109_TGRS_2020_3008844 crossref_primary_10_3390_rs16112029 crossref_primary_10_3390_aerospace11110933 crossref_primary_10_3103_S8756699021020102 crossref_primary_10_1080_22797254_2023_2262738 crossref_primary_10_1109_TGRS_2020_3018879 crossref_primary_10_14358_PERS_22_00111R2 crossref_primary_10_3390_rs13224704 crossref_primary_10_1109_JSTARS_2021_3132856 crossref_primary_10_3390_land14010172 crossref_primary_10_3390_app14125061 crossref_primary_10_1109_MGRS_2024_3382510 crossref_primary_10_3390_app13127143 crossref_primary_10_1016_j_aca_2021_339308 crossref_primary_10_1016_j_rse_2024_114291 crossref_primary_10_3390_rs13163232 crossref_primary_10_1109_MGRS_2024_3509139 crossref_primary_10_3390_rs13234875 crossref_primary_10_1109_TGRS_2020_2964777 crossref_primary_10_1109_TGRS_2024_3436821 crossref_primary_10_3390_rs14071542 crossref_primary_10_3390_rs15071758 crossref_primary_10_1109_TGRS_2019_2961141 crossref_primary_10_3390_s23125366 crossref_primary_10_1109_ACCESS_2023_3297630 crossref_primary_10_1016_j_jfca_2025_107857 crossref_primary_10_1109_JSTARS_2025_3604753 crossref_primary_10_1111_jmi_13372 crossref_primary_10_1007_s11042_025_20825_y crossref_primary_10_1007_s10333_025_01024_9 crossref_primary_10_1109_TGRS_2025_3572128 crossref_primary_10_3390_rs13071306 crossref_primary_10_1109_LGRS_2023_3321343 crossref_primary_10_1016_j_jag_2023_103326 crossref_primary_10_3390_rs16010140 crossref_primary_10_3390_rs13020198 crossref_primary_10_1109_LGRS_2022_3200145 crossref_primary_10_1007_s10489_021_02805_5 crossref_primary_10_3390_app10248833 crossref_primary_10_1109_TGRS_2022_3230378 crossref_primary_10_1109_LGRS_2021_3103180 crossref_primary_10_1016_j_knosys_2025_113973 crossref_primary_10_1016_j_neucom_2023_01_054 crossref_primary_10_1109_TGRS_2024_3403648 crossref_primary_10_5194_gi_11_195_2022 crossref_primary_10_3390_diagnostics11101810 crossref_primary_10_3390_rs16244695 crossref_primary_10_3390_rs12213501 crossref_primary_10_1109_JSTARS_2023_3342461 crossref_primary_10_1002_eap_2300 crossref_primary_10_1109_JSTARS_2022_3151149 crossref_primary_10_3390_rs12183053 crossref_primary_10_1109_TGRS_2025_3603835 crossref_primary_10_1016_j_icarus_2021_114849 crossref_primary_10_1080_01431161_2024_2431174 crossref_primary_10_1109_TGRS_2025_3576670 crossref_primary_10_1109_TGRS_2023_3265388 crossref_primary_10_1016_j_compag_2024_109726 crossref_primary_10_3390_s24227131 crossref_primary_10_1016_j_eswa_2024_123155 crossref_primary_10_3390_agriculture12111838 crossref_primary_10_3390_rs14153751 crossref_primary_10_3390_electronics14010102 crossref_primary_10_3390_sym12020277 crossref_primary_10_1016_j_jag_2022_103022 crossref_primary_10_3390_rs15153721 crossref_primary_10_1109_TGRS_2025_3542422 crossref_primary_10_3390_jimaging6120132 crossref_primary_10_1109_TNNLS_2024_3445136 crossref_primary_10_1080_01431161_2020_1857877 crossref_primary_10_1016_j_jag_2024_103754 crossref_primary_10_1109_LGRS_2024_3418856 crossref_primary_10_1016_j_jag_2024_103876 crossref_primary_10_3390_rs15010261 crossref_primary_10_1016_j_future_2023_05_003 crossref_primary_10_3390_rs15184439 crossref_primary_10_1109_JSTARS_2025_3566214 crossref_primary_10_3390_rs15184560 crossref_primary_10_1109_TGRS_2022_3223508 crossref_primary_10_1016_j_jenvman_2024_123410 crossref_primary_10_1109_LGRS_2022_3192912 crossref_primary_10_1109_JSTARS_2023_3328389 crossref_primary_10_1109_LGRS_2023_3341497 crossref_primary_10_3390_rs16020288 |
| Cites_doi | 10.1109/ICICS.2013.6782778 10.1016/S0168-1699(03)00020-6 10.1109/LGRS.2006.878240 10.1109/TGRS.2017.2748160 10.1080/2150704X.2015.1047045 10.1109/TIP.2017.2725580 10.1109/TGRS.2015.2478379 10.1080/2150704X.2015.1062157 10.1109/TGRS.2009.2016214 10.1109/TGRS.2018.2818945 10.1145/2733373.2806306 10.1007/BF00121320 10.1016/j.isprsjprs.2015.01.006 10.1109/TGRS.2016.2642479 10.3390/rs9101042 10.1109/TGRS.2016.2616585 10.1109/LGRS.2015.2482520 10.1109/TGRS.2002.802494 10.1155/2015/258619 10.1109/MGRS.2017.2762307 10.1109/TIP.2017.2772836 10.1080/2150704X.2017.1331053 10.1109/CVPR.2015.7298594 10.1109/TGRS.2004.831865 10.1109/TGRS.2016.2584107 10.1109/IGARSS.2015.7326945 10.3390/rs9030298 10.3390/rs9010067 10.1109/TGRS.2014.2350771 10.5194/isprsarchives-XL-3-W3-459-2015 10.1080/01431161.2010.512425 10.1109/MGRS.2017.2762087 10.1109/TGRS.2016.2636241 10.1109/TGRS.2018.2833808 10.1109/MGRS.2018.2798161 10.1109/IGARSS.2018.8518321 10.1109/ICCV.2015.123 10.1109/JPROC.2012.2197589 10.1109/TGRS.2018.2805286 10.1007/s00500-016-2246-3 10.1145/2660859.2660946 10.1109/LGRS.2018.2817361 10.1109/MGRS.2013.2244672 10.1016/j.patcog.2010.01.016 10.1117/12.2245011 10.1109/ICIP.2017.8297014 10.1109/TGRS.2004.842481 10.1109/TGRS.2016.2543748 10.1109/JSTARS.2014.2304304 10.1109/JSTARS.2016.2517204 10.1109/LGRS.2005.846011 10.1109/CVPR.2016.90 10.1109/ICALIP.2018.8455251 10.1109/LGRS.2005.857031 10.1109/LGRS.2004.837009 10.5194/isprsannals-III-3-473-2016 10.1155/2016/3632943 10.1016/j.rse.2007.12.015 10.1162/neco.1989.1.4.541 10.3390/rs9030196 10.1007/978-3-319-54181-5_12 10.1109/TGRS.2009.2037898 10.1109/IGARSS.2016.7729675 10.1109/JSTARS.2014.2329330 10.1016/j.patcog.2011.03.035 10.1109/WHISPERS.2015.8075378 10.1109/JSTARS.2015.2388577 10.1080/01431169408954055 10.1109/TGRS.2015.2513424 10.1109/ICIP.2014.7026039 |
| ContentType | Journal Article |
| Copyright | Distributed under a Creative Commons Attribution 4.0 International License |
| Copyright_xml | – notice: Distributed under a Creative Commons Attribution 4.0 International License |
| DBID | 97E RIA RIE AAYXX CITATION 1XC VOOES |
| DOI | 10.1109/MGRS.2019.2912563 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Geology Computer Science |
| EISSN | 2168-6831 |
| EndPage | 173 |
| ExternalDocumentID | oai:HAL:hal-02104998v1 10_1109_MGRS_2019_2912563 8738045 |
| Genre | orig-research |
| GroupedDBID | 0R~ 4.4 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD HZ~ IFIPE IPLJI JAVBF M43 O9- OCL RIA RIE AAYXX CITATION 1XC VOOES |
| ID | FETCH-LOGICAL-c280t-69e3431963cdcd5a24aa919ebd06d4b1cfa5789bb3473ce2ce5137db6eabecec3 |
| IEDL.DBID | RIE |
| ISSN | 2473-2397 |
| IngestDate | Sat Nov 29 15:07:35 EST 2025 Tue Nov 18 22:33:07 EST 2025 Sat Nov 29 05:56:56 EST 2025 Wed Aug 27 05:51:22 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| 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 Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c280t-69e3431963cdcd5a24aa919ebd06d4b1cfa5789bb3473ce2ce5137db6eabecec3 |
| ORCID | 0000-0002-2384-8202 0000-0001-6486-3102 0000-0001-7162-6746 |
| OpenAccessLink | https://hal.science/hal-02104998 |
| PageCount | 15 |
| ParticipantIDs | hal_primary_oai_HAL_hal_02104998v1 ieee_primary_8738045 crossref_primary_10_1109_MGRS_2019_2912563 crossref_citationtrail_10_1109_MGRS_2019_2912563 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-06-01 |
| PublicationDateYYYYMMDD | 2019-06-01 |
| PublicationDate_xml | – month: 06 year: 2019 text: 2019-06-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | IEEE geoscience and remote sensing magazine |
| PublicationTitleAbbrev | GRSM |
| PublicationYear | 2019 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref57 ref13 rodarmel (ref20) 2002; 62 ref56 ref59 ref15 ref58 ref14 ref53 ref52 ref55 ref11 ioffe (ref76) 0 ref54 ref19 ref51 ref50 ref46 ref45 kingma (ref73) 2015 ref48 ref47 ref42 ref41 ref44 ref43 tao (ref61) 2015; 12 ref49 parra (ref18) 0 gualtieri (ref24) 0; 3584 ref8 ref7 ref9 ref4 ref6 ref5 ref82 nair (ref78) 0 ref81 ref40 ozkan (ref39) 2017 ref80 ref79 ref35 ref34 ref37 ref36 ref31 ref74 ref30 ref77 ref33 ref32 ref2 ref1 ref38 ref71 ref70 ref72 ref68 ref67 ref23 ref26 ref69 ref25 ref64 ref63 du (ref16) 0 ref66 ref22 ref65 ref21 marmanis (ref3) 2016; 3 ref28 ref27 ref29 (ref12) 2018 ref60 ref62 srivastava (ref75) 2014; 15 yuhas (ref17) 1992 chavez (ref10) 1996; 62 |
| References_xml | – ident: ref57 doi: 10.1109/ICICS.2013.6782778 – ident: ref40 doi: 10.1016/S0168-1699(03)00020-6 – ident: ref15 doi: 10.1109/LGRS.2006.878240 – ident: ref65 doi: 10.1109/TGRS.2017.2748160 – ident: ref52 doi: 10.1080/2150704X.2015.1047045 – ident: ref49 doi: 10.1109/TIP.2017.2725580 – ident: ref54 doi: 10.1109/TGRS.2015.2478379 – ident: ref53 doi: 10.1080/2150704X.2015.1062157 – ident: ref34 doi: 10.1109/TGRS.2009.2016214 – ident: ref63 doi: 10.1109/TGRS.2018.2818945 – year: 2015 ident: ref73 publication-title: Adam A method for stochastic optimization – ident: ref50 doi: 10.1145/2733373.2806306 – ident: ref8 doi: 10.1007/BF00121320 – ident: ref37 doi: 10.1016/j.isprsjprs.2015.01.006 – ident: ref21 doi: 10.1109/TGRS.2016.2642479 – ident: ref80 doi: 10.3390/rs9101042 – ident: ref2 doi: 10.1109/TGRS.2016.2616585 – volume: 12 start-page: 2438 year: 2015 ident: ref61 article-title: Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification publication-title: IEEE Geosci Remote Sens Lett doi: 10.1109/LGRS.2015.2482520 – ident: ref31 doi: 10.1109/TGRS.2002.802494 – ident: ref42 doi: 10.1155/2015/258619 – start-page: 942 year: 0 ident: ref18 article-title: Unmixing hyperspectral data publication-title: Proc 12th Int Conf Neural Information Processing Systems – ident: ref6 doi: 10.1109/MGRS.2017.2762307 – start-page: 374 year: 0 ident: ref16 article-title: Band selection and its impact on target detection and classification in hyperspectral image analysis publication-title: Proc IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data – ident: ref44 doi: 10.1109/TIP.2017.2772836 – ident: ref70 doi: 10.1080/2150704X.2017.1331053 – year: 2017 ident: ref39 publication-title: Endnet Sparse autoencoder network for endmember extraction and hyperspectral unmixing – ident: ref67 doi: 10.1109/CVPR.2015.7298594 – ident: ref23 doi: 10.1109/TGRS.2004.831865 – ident: ref71 doi: 10.1109/TGRS.2016.2584107 – ident: ref48 doi: 10.1109/IGARSS.2015.7326945 – ident: ref45 doi: 10.3390/rs9030298 – ident: ref68 doi: 10.3390/rs9010067 – ident: ref5 doi: 10.1109/TGRS.2014.2350771 – year: 2018 ident: ref12 publication-title: 2018 IEEE GRSS Data Fusion Contest – ident: ref19 doi: 10.5194/isprsarchives-XL-3-W3-459-2015 – ident: ref30 doi: 10.1080/01431161.2010.512425 – ident: ref7 doi: 10.1109/MGRS.2017.2762087 – ident: ref43 doi: 10.1109/TGRS.2016.2636241 – ident: ref77 doi: 10.1109/TGRS.2018.2833808 – ident: ref13 doi: 10.1109/MGRS.2018.2798161 – ident: ref81 doi: 10.1109/IGARSS.2018.8518321 – ident: ref74 doi: 10.1109/ICCV.2015.123 – start-page: 807 year: 0 ident: ref78 article-title: Rectified linear units improve restricted Boltzmann machines publication-title: Proc 27th Int Conf Mach Learn (ICML-10) – ident: ref28 doi: 10.1109/JPROC.2012.2197589 – ident: ref82 doi: 10.1109/TGRS.2018.2805286 – ident: ref62 doi: 10.1007/s00500-016-2246-3 – ident: ref58 doi: 10.1145/2660859.2660946 – ident: ref79 doi: 10.1109/LGRS.2018.2817361 – ident: ref4 doi: 10.1109/MGRS.2013.2244672 – ident: ref27 doi: 10.1016/j.patcog.2010.01.016 – ident: ref47 doi: 10.1117/12.2245011 – ident: ref69 doi: 10.1109/ICIP.2017.8297014 – ident: ref22 doi: 10.1109/TGRS.2004.842481 – ident: ref51 doi: 10.1109/TGRS.2016.2543748 – ident: ref25 doi: 10.1109/JSTARS.2014.2304304 – ident: ref60 doi: 10.1109/JSTARS.2016.2517204 – ident: ref14 doi: 10.1109/LGRS.2005.846011 – ident: ref66 doi: 10.1109/CVPR.2016.90 – start-page: 147 year: 1992 ident: ref17 article-title: Discrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm publication-title: Proc Summaries 3rd Annu JPL Airborne Geoscience Workshop – volume: 62 start-page: 115 year: 2002 ident: ref20 article-title: Principal component analysis for hyperspectral image classification publication-title: Surveying and Land Information Science – ident: ref64 doi: 10.1109/ICALIP.2018.8455251 – ident: ref33 doi: 10.1109/LGRS.2005.857031 – ident: ref32 doi: 10.1109/LGRS.2004.837009 – volume: 3 start-page: 473 year: 2016 ident: ref3 article-title: Semantic segmentation of aerial images with an ensemble of CNNs publication-title: ISPRS Ann Photogramm Remote Sens Spatial Inf Sci doi: 10.5194/isprsannals-III-3-473-2016 – ident: ref46 doi: 10.1155/2016/3632943 – ident: ref11 doi: 10.1016/j.rse.2007.12.015 – start-page: 448 year: 0 ident: ref76 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proceedings of the 32nd Intl Conf on Machine Learning – ident: ref72 doi: 10.1162/neco.1989.1.4.541 – ident: ref36 doi: 10.3390/rs9030196 – ident: ref1 doi: 10.1007/978-3-319-54181-5_12 – ident: ref41 doi: 10.1109/TGRS.2009.2037898 – ident: ref26 doi: 10.1109/IGARSS.2016.7729675 – ident: ref59 doi: 10.1109/JSTARS.2014.2329330 – ident: ref35 doi: 10.1016/j.patcog.2011.03.035 – ident: ref38 doi: 10.1109/WHISPERS.2015.8075378 – volume: 15 start-page: 1929 year: 2014 ident: ref75 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learning Res – ident: ref56 doi: 10.1109/JSTARS.2015.2388577 – volume: 62 start-page: 1025 year: 1996 ident: ref10 article-title: Image-based atmospheric corrections: Revisited and improved publication-title: Photogrammetric Eng Remote Sens – ident: ref9 doi: 10.1080/01431169408954055 – ident: ref29 doi: 10.1109/TGRS.2015.2513424 – volume: 3584 start-page: 1 year: 0 ident: ref24 article-title: Support vector machines hyperspectral remote sensing classification publication-title: Proc SPIE – ident: ref55 doi: 10.1109/ICIP.2014.7026039 |
| SSID | ssj0000851918 |
| Score | 2.6090791 |
| Snippet | In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to... In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the... |
| SourceID | hal crossref ieee |
| SourceType | Open Access Repository Enrichment Source Index Database Publisher |
| StartPage | 159 |
| SubjectTerms | Computer Science Computer Vision and Pattern Recognition Deep learning Hyperspectral imaging Machine learning Neural and Evolutionary Computing Sensors Spatial resolution |
| Title | Deep Learning for Classification of Hyperspectral Data: A Comparative Review |
| URI | https://ieeexplore.ieee.org/document/8738045 https://hal.science/hal-02104998 |
| Volume | 7 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2168-6831 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000851918 issn: 2473-2397 databaseCode: RIE dateStart: 20130101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD5sQ9EXL5vivBHEJ7Eubbqm8W1sbntQES_gW2mSMyfINuY22L83SWtVEMG3EtIL-Rq-c3IuH8ApautXxaEXGfr3DAWgJyVSTxrblgkdMdTUiU3w29v4-VncleC8qIVBRJd8hhf20sXy9VjN7VFZI-YsNiZIGcqcR1mtVnGeYk0H4Y7zgpAzLzA8mwcxfSoaN737B5vHJS4CYSg9Yj9oqDy0SZDf1FUcuXQ3__dZW7CRG5GklaG-DSUcVWEt1zMfLquw2nOCvcsaXHcQJyTvovpCjIlKnA6mzRByoJDxgPSNM5rVXE7NYzvpLL0kLdL-agxOshDCDjx1rx7bfS9XUPBUENOZFwlkodtkSivdTIMwTYUvUGoa6VD6apCaHSukZGbNFAYKmz7jWkaYGmxRsV2ojMYj3APCBVfNiAufaREaZjWWWzygVKUYSoxR1YF-Lmii8vbiVuXiLXFuBhWJxSCxGCQ5BnU4K26ZZL01_pp8YlAq5tmu2P3WdWLHrNtqHLd44dehZuEpZuXI7P8-fADr9g1Z4tchVGbTOR7BilrMXt-nx-73-gDn48uJ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxFH7YqtSLu1jXIJ7EqZlJZom34laxFnGB3oZJ8qqCtKW2gv_eJDOOCiJ4G0JmId-E77285QPYR239qoR7kaF_z1AAelIi9aSxbZnQEUNNndhE3Okk3a64mYLDshYGEV3yGTbspYvl64Ga2KOyoyRmiTFBKjAdch7QvFqrPFGxxoNwB3oBj5kXGKYtwpg-FUfXF7d3NpNLNAJhSD1iP4io8mTTIL_pqzh6OV_434ctwnxhRpJmjvsSTGF_GWqFovnT-zLMXjjJ3vcVaJ8iDknRR_WRGCOVOCVMmyPkYCGDHmkZdzSvuhyZx55m4-yYNMnJV2twkgcRVuHh_Oz-pOUVGgqeChI69iKBjLttprTSYRbwLBO-QKlppLn0VS8ze1ZIycyaKQwUhj6LtYwwM-iiYmtQ7Q_6uA4kFrEKo1j4TAtuuNXYbkmPUpUhl5igqgP9XNBUFQ3Grc7FS-ocDSpSi0FqMUgLDOpwUN4yzLtr_DV5z6BUzrN9sVvNdmrHrONqXLfkza_DioWnnFUgs_H78C7UWvfX7bR92bnahDn7tjwNbAuq49EEt2FGvY2fX0c77lf7AKjdztA |
| 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=Deep+Learning+for+Classification+of+Hyperspectral+Data%3A+A+Comparative+Review&rft.jtitle=IEEE+geoscience+and+remote+sensing+magazine&rft.au=Audebert%2C+Nicolas&rft.au=Le+Saux%2C+Bertrand&rft.au=Lefevre%2C+Sebastien&rft.date=2019-06-01&rft.issn=2473-2397&rft.eissn=2168-6831&rft.volume=7&rft.issue=2&rft.spage=159&rft.epage=173&rft_id=info:doi/10.1109%2FMGRS.2019.2912563&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_MGRS_2019_2912563 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2473-2397&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2473-2397&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2473-2397&client=summon |