{"url":"/sota/hyperspectral-image-classification-on-pavia","task":{"name":"Hyperspectral Image Classification","url":"/task/hyperspectral-image-classification","note":null},"dataset":{"name":"Pavia University","url":"/dataset/pavia-university"},"category":"Computer Vision","categories":["Adversarial","Computer Vision"],"category_note":null,"description":"**Hyperspectral Image Classification** is a task in the field of remote sensing and computer vision. It involves the classification of pixels in hyperspectral images into different classes based on their spectral signature. Hyperspectral images contain information about the reflectance of objects in hundreds of narrow, contiguous wavelength bands, making them useful for a wide range of applications, including mineral mapping, vegetation analysis, and urban land-use mapping. The goal of this task is to accurately identify and classify different types of objects in the image, such as soil, vegetation, water, and buildings, based on their spectral properties.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification](https://arxiv.org/pdf/1810.12563v1.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["OA@15perclass","Overall Accuracy","AA@200","Kappa@200","OA@200","AA@5%perclass","Kappa@1%","Kappa@5%perclass","OA@5%perclass","AA@1%perclass","Kappa@1%perclass","OA@1%perclass"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"OA@15perclass":null,"Overall Accuracy":"higher","AA@200":null,"Kappa@200":null,"OA@200":null,"AA@5%perclass":null,"Kappa@1%":null,"Kappa@5%perclass":null,"OA@5%perclass":null,"AA@1%perclass":null,"Kappa@1%perclass":null,"OA@1%perclass":null}},"counts":{"rows":33,"rows_with_code":28,"rows_with_paper_page":33,"rows_dated":33,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RPNet-RF","metrics":{"OA@15perclass":"95.60"},"uses_additional_data":false,"paper_date":"2023-02-23","paper":"/paper/small-sample-hyperspectral-image","paper_url":"https://doi.org/10.3390/s23052499","paper_title":"Small Sample Hyperspectral Image Classification Based on the Random Patches Network and Recursive Filtering","code":"https://github.com/UchaevD/RPNet-RF","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"TC-GAN","metrics":{"OA@15perclass":"93.20±0.59"},"uses_additional_data":false,"paper_date":"2022-07-16","paper":"/paper/generative-adversarial-networks-based-on-1","paper_url":"https://doi.org/10.3390/rs14143426","paper_title":"Generative Adversarial Networks Based on Transformer Encoder and Convolution Block for Hyperspectral Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"HyLITE","metrics":{"OA@15perclass":"91.28"},"uses_additional_data":false,"paper_date":"2023-09-04","paper":"/paper/locality-aware-hyperspectral-classification","paper_url":"https://arxiv.org/abs/2309.01561v1","paper_title":"Locality-Aware Hyperspectral Classification","code":"https://github.com/zhoufangqin/hylite","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DCFSL","metrics":{"OA@15perclass":"90.71±0.56"},"uses_additional_data":false,"paper_date":"2022-06-30","paper":"/paper/graph-information-aggregation-cross-domain","paper_url":"https://doi.org/10.1109/TNNLS.2022.3185795","paper_title":"Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image Classification","code":"https://github.com/YuxiangZhang-BIT/IEEE_TNNLS_Gia-CFSL","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"IFRF","metrics":{"OA@15perclass":"88.38"},"uses_additional_data":false,"paper_date":"2013-09-16","paper":"/paper/feature-extraction-of-hyperspectral-images","paper_url":"https://doi.org/10.1109/TGRS.2013.2275613","paper_title":"Feature Extraction of Hyperspectral Images With Image Fusion and Recursive Filtering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"S-DMM","metrics":{"OA@15perclass":"88.30±1.03"},"uses_additional_data":false,"paper_date":"2019-10-30","paper":"/paper/deep-metric-learning-based-feature-embedding","paper_url":"https://doi.org/10.1109/TGRS.2019.2946318","paper_title":"Deep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification","code":"https://github.com/szubing/S-DMM","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"RPNet","metrics":{"OA@15perclass":"84.92"},"uses_additional_data":false,"paper_date":"2018-05-22","paper":"/paper/hyperspectral-image-classification-via-a","paper_url":"https://doi.org/10.1016/j.isprsjprs.2018.05.014","paper_title":"Hyperspectral image classification via a random patches network","code":"https://github.com/YonghaoXu/RPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"3D VS-CNN","metrics":{"OA@15perclass":"81.63±1.81"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/hyperspectral-image-classification-of","paper_url":"http://doi.org/10.1088/1742-6596/1549/5/052011","paper_title":"Hyperspectral Image Classification of Convolutional Neural Network Combined with Valuable Samples","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"2D-CNN","metrics":{"OA@15perclass":"77.53±1.50"},"uses_additional_data":false,"paper_date":"2015-07-26","paper":"/paper/deep-supervised-learning-for-hyperspectral","paper_url":"https://doi.org/10.1109/IGARSS.2015.7326945","paper_title":"Deep supervised learning for hyperspectral data classification through convolutional neural networks","code":"https://github.com/swalpa/Classification-of-Hyperspectral-Image","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CA-GAN","metrics":{"OA@15perclass":"76.81±0.91"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/generative-adversarial-networks-based-on-2","paper_url":"https://doi.org/10.3390/rs12071149","paper_title":"Generative Adversarial Networks Based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"HSI-BERT","metrics":{"OA@15perclass":"75.31±1.59"},"uses_additional_data":false,"paper_date":"2019-09-04","paper":"/paper/hsi-bert-hyperspectral-image-classification","paper_url":"https://doi.org/10.1109/TGRS.2019.2934760","paper_title":"HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"3D-CNN","metrics":{"OA@15perclass":"75.24±0.84"},"uses_additional_data":false,"paper_date":"2017-01-13","paper":"/paper/spectral-spatial-classification-of-2","paper_url":"https://doi.org/10.3390/rs9010067","paper_title":"Spectral–Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network","code":"https://github.com/nshaud/DeepHyperX","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"JigsawHSI","metrics":{"Overall Accuracy":"100.00"},"uses_additional_data":false,"paper_date":"2022-06-06","paper":"/paper/jigsawhsi-a-network-for-hyperspectral-image","paper_url":"https://arxiv.org/abs/2206.02327v3","paper_title":"JigsawHSI: a network for Hyperspectral Image classification","code":"https://github.com/jmoraga-mines/jigsawhsi","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"STNet","metrics":{"Overall Accuracy":"100"},"uses_additional_data":false,"paper_date":"2025-06-10","paper":"/paper/hyperspectral-image-classification-via","paper_url":"https://arxiv.org/abs/2506.08324v1","paper_title":"Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating","code":"https://github.com/leeguandong/STNet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"WCNet","metrics":{"Overall Accuracy":"100"},"uses_additional_data":false,"paper_date":"2025-04-15","paper":"/paper/3d-wavelet-convolutions-with-extended","paper_url":"https://arxiv.org/abs/2504.10795v1","paper_title":"3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification","code":"https://github.com/leeguandong/WCNet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"SpectralNET","metrics":{"Overall Accuracy":"99.99%"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/spectralnet-exploring-spatial-spectral","paper_url":"https://arxiv.org/abs/2104.00341v1","paper_title":"SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification","code":"https://github.com/tanmay-ty/SpectralNET","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"Deep Matrix Capsules","metrics":{"Overall Accuracy":"99.99%"},"uses_additional_data":false,"paper_date":"2023-02-02","paper":"/paper/hyperspectral-image-classification-using-deep","paper_url":"https://ieeexplore.ieee.org/document/10028853","paper_title":"Hyperspectral Image Classification Using Deep Matrix Capsules","code":"https://github.com/DeepMatrixCapsules/DeepMatrixCapsules","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"KANet","metrics":{"Overall Accuracy":"99.99"},"uses_additional_data":false,"paper_date":"2025-04-21","paper":"/paper/dynamic-3d-kan-convolution-with-adaptive-grid","paper_url":"https://arxiv.org/abs/2504.15155v1","paper_title":"Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification","code":"https://github.com/leeguandong/KANet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"SGDSCNet","metrics":{"Overall Accuracy":"99.99"},"uses_additional_data":false,"paper_date":"2025-04-06","paper":"/paper/spatial-geometry-enhanced-3d-dynamic-snake","paper_url":"https://arxiv.org/abs/2504.04463v1","paper_title":"Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification","code":"https://github.com/leeguandong/SGDSCNet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"MVNet","metrics":{"Overall Accuracy":"99.98"},"uses_additional_data":false,"paper_date":"2025-07-06","paper":"/paper/mvnet-hyperspectral-remote-sensing-image","paper_url":"https://arxiv.org/abs/2507.04409v1","paper_title":"MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture","code":"https://github.com/leeguandong/MVNet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"EKGNet","metrics":{"Overall Accuracy":"99.98"},"uses_additional_data":false,"paper_date":"2025-04-17","paper":"/paper/expert-kernel-generation-network-driven-by","paper_url":"https://arxiv.org/abs/2504.13045v1","paper_title":"Expert Kernel Generation Network Driven by Contextual Mapping for Hyperspectral Image Classification","code":"https://github.com/leeguandong/EKGNet-for-HSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"SSDGL","metrics":{"Kappa@1%":"0.9996","Overall Accuracy":"99.97%"},"uses_additional_data":false,"paper_date":"2021-05-29","paper":"/paper/a-spectral-spatial-dependent-global-learning","paper_url":"https://arxiv.org/abs/2105.14327v1","paper_title":"A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification","code":"https://github.com/dengweihuan/SSDGL","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"FSKNet","metrics":{"Overall Accuracy":"99.96%"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/faster-hyperspectral-image-classification","paper_url":"https://arxiv.org/abs/2202.06458v1","paper_title":"Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networks","code":"https://github.com/leeguandong/fsknet-for-hsi","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"A2S2K-ResNet","metrics":{"Overall Accuracy":"99.85"},"uses_additional_data":false,"paper_date":"2020-12-24","paper":"/paper/attention-based-adaptive-spectral-spatial","paper_url":"https://ieeexplore.ieee.org/document/9306920","paper_title":"Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification","code":"https://github.com/suvojit-0x55aa/A2S2K-ResNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"FPGA","metrics":{"AA@200":"99.83","Kappa@200":"0.9974","OA@200":"99.81","Overall Accuracy":"99.81%"},"uses_additional_data":false,"paper_date":"2020-11-11","paper":"/paper/fpga-fast-patch-free-global-learning-1","paper_url":"https://arxiv.org/abs/2011.05670v1","paper_title":"FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification","code":"https://github.com/Z-Zheng/FreeNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"CVSSN","metrics":{"AA@5%perclass":"99.52±0.17%","Kappa@5%perclass":"0.9957±0.0009","OA@5%perclass":"99.68±0.06%","Overall Accuracy":"99.68±0.06%"},"uses_additional_data":false,"paper_date":"2022-10-31","paper":"/paper/exploring-the-relationship-between-center-and","paper_url":"http://dx.doi.org/10.1109/tcsvt.2022.3218284","paper_title":"Exploring the Relationship between Center and Neighborhoods: Central Vector oriented Self-Similarity Network for Hyperspectral Image Classification","code":"https://github.com/lms-07/CVSSN","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"A-SPN","metrics":{"Overall Accuracy":"99.65%"},"uses_additional_data":false,"paper_date":"2021-01-14","paper":"/paper/attention-based-second-order-pooling-network","paper_url":"https://ieeexplore.ieee.org/document/9325094","paper_title":"Attention-Based Second-Order Pooling Network for Hyperspectral Image Classification","code":"https://github.com/ZhaohuiXue/A-SPN-release","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"WCRN","metrics":{"Overall Accuracy":"99.43%"},"uses_additional_data":false,"paper_date":"2018-07-22","paper":"/paper/wide-contextual-residual-network-with-active","paper_url":"https://ieeexplore.ieee.org/document/8517855","paper_title":"Wide Contextual Residual Network with Active Learning for Remote Sensing Image Classification","code":"https://github.com/codeRimoe/DL_for_RSIs","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"St-SS-pGRU","metrics":{"Overall Accuracy":"98.44%"},"uses_additional_data":false,"paper_date":"2018-10-30","paper":"/paper/shorten-spatial-spectral-rnn-with-parallel","paper_url":"http://arxiv.org/abs/1810.12563v1","paper_title":"Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification","code":"https://github.com/codeRimoe/DL_for_RSIs","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"AMS-M2ESL","metrics":{"AA@1%perclass":"97.86±0.47%","Kappa@1%perclass":"0.9747±0.0039","OA@1%perclass":"98.09±0.30%","Overall Accuracy":"98.09±0.30%"},"uses_additional_data":false,"paper_date":"2023-04-07","paper":"/paper/adaptive-mask-sampling-and-manifold-to","paper_url":"https://ieeexplore.ieee.org/abstract/document/10097620","paper_title":"Adaptive Mask Sampling and Manifold to Euclidean Subspace Learning with Distance Covariance Representation for Hyperspectral Image Classification","code":"https://github.com/lms-07/AMS-M2ESL","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"BASSNet","metrics":{"Overall Accuracy":"97.48%"},"uses_additional_data":false,"paper_date":"2016-12-01","paper":"/paper/bass-net-band-adaptive-spectral-spatial","paper_url":"http://arxiv.org/abs/1612.00144v2","paper_title":"BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification","code":"https://github.com/kaustubh0mani/BASS-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"DeepHyperX 3D  CNN","metrics":{"Overall Accuracy":"96.71"},"uses_additional_data":false,"paper_date":"2019-04-24","paper":"/paper/deep-learning-for-classification-of-1","paper_url":"http://arxiv.org/abs/1904.10674v1","paper_title":"Deep Learning for Classification of Hyperspectral Data: A Comparative Review","code":"https://github.com/nshaud/DeepHyperX","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"CNN-MRF","metrics":{"Overall Accuracy":"96.18"},"uses_additional_data":false,"paper_date":"2017-05-01","paper":"/paper/hyperspectral-image-classification-with-1","paper_url":"http://arxiv.org/abs/1705.00727v2","paper_title":"Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network","code":"https://github.com/xiangyongcao/CNN_HSIC_MRF","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}