{"url":"/task/thermal-image-segmentation","name":"Thermal Image Segmentation","slug":"thermal-image-segmentation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":84,"papers_with_code":70,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/thermal-image-segmentation-on-mfn-dataset","slug":"thermal-image-segmentation-on-mfn-dataset","dataset":"MFN Dataset","dataset_url":"/dataset/mfnet","rows_in_archive":55,"metrics":["mIOU","Frame (fps)"],"first_row_in_archive_order":{"model":"RoadFormer+ (ConvNeXt-L)","paper_title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","paper_url":"/paper/roadformer-delivering-rgb-x-scene-parsing","paper_date":"2024-07-31","arxiv_id":"2407.21631","code_links":[],"syntology":null}},{"leaderboard":"/sota/thermal-image-segmentation-on-pst900","slug":"thermal-image-segmentation-on-pst900","dataset":"PST900","dataset_url":"/dataset/pst900","rows_in_archive":22,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SHIFNet","paper_title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","paper_url":"/paper/unveiling-the-potential-of-segment-anything","paper_date":"2025-03-04","arxiv_id":"2503.02581","code_links":[{"title":"iasakit3t/shifnet","url":"https://github.com/iasakit3t/shifnet"}],"syntology":null}},{"leaderboard":"/sota/thermal-image-segmentation-on-rgb-t-glass","slug":"thermal-image-segmentation-on-rgb-t-glass","dataset":"RGB-T-Glass-Segmentation","dataset_url":null,"rows_in_archive":22,"metrics":["MAE"],"first_row_in_archive_order":{"model":"RGB-T-Glass-Segmentation","paper_title":"Glass Segmentation with RGB-Thermal Image Pairs","paper_url":"/paper/glass-segmentation-with-rgb-thermal-image","paper_date":"2022-04-12","arxiv_id":"2204.05453","code_links":[{"title":"dong-huo/rgb-t-glass-segmentation","url":"https://github.com/dong-huo/rgb-t-glass-segmentation"}],"syntology":null}},{"leaderboard":"/sota/thermal-image-segmentation-on-noisy-rs-rgb-t","slug":"thermal-image-segmentation-on-noisy-rs-rgb-t","dataset":"Noisy RS RGB-T Dataset","dataset_url":null,"rows_in_archive":6,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CMNeXt (B4)","paper_title":"Delivering Arbitrary-Modal Semantic Segmentation","paper_url":"/paper/delivering-arbitrary-modal-semantic","paper_date":"2023-03-02","arxiv_id":"2303.01480","code_links":[{"title":"jamycheung/DELIVER","url":"https://github.com/jamycheung/DELIVER"}],"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/thermal-image-segmentation-on-kp-day-night","slug":"thermal-image-segmentation-on-kp-day-night","dataset":"KP day-night","dataset_url":null,"rows_in_archive":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"HAPNet","paper_title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","paper_url":"/paper/hapnet-toward-superior-rgb-thermal-scene","paper_date":"2024-04-04","arxiv_id":"2404.03527","code_links":[{"title":"LiJiahang617/HAPNet","url":"https://github.com/LiJiahang617/HAPNet"}],"syntology":null}},{"leaderboard":"/sota/thermal-image-segmentation-on-scut-seg","slug":"thermal-image-segmentation-on-scut-seg","dataset":"SCUT-Seg Dataset","dataset_url":null,"rows_in_archive":1,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"FTNet","paper_title":"FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation","paper_url":"/paper/ftnet-feature-transverse-network-for-thermal","paper_date":"2021-10-26","arxiv_id":null,"code_links":[{"title":"shreyaskamathkm/FTNet","url":"https://github.com/shreyaskamathkm/FTNet"}],"syntology":null}},{"leaderboard":"/sota/thermal-image-segmentation-on-soda-dataset","slug":"thermal-image-segmentation-on-soda-dataset","dataset":"SODA Dataset","dataset_url":null,"rows_in_archive":1,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"FTNet","paper_title":"FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation","paper_url":"/paper/ftnet-feature-transverse-network-for-thermal","paper_date":"2021-10-26","arxiv_id":null,"code_links":[{"title":"shreyaskamathkm/FTNet","url":"https://github.com/shreyaskamathkm/FTNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/mfnet","name":"MFNet","full_name":"","num_papers_in_archive":87},{"url":"/dataset/pst900","name":"PST900","full_name":null,"num_papers_in_archive":35},{"url":"/dataset/charlotte-thermalface","name":"Charlotte-ThermalFace","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ms2-dataset-rgb-nir-thermal-images-lidar-gps","name":"Multi-Spectral Stereo Dataset  (RGB, NIR, thermal images, LiDAR, GPS/IMU)","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/2d-object-detection","name":"2D Object Detection"},{"url":"/task/scene-segmentation","name":"Scene Segmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":70,"tagged_in_all":84,"items":[{"url":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","arxiv_id":"1505.04597","repositories_listed":487,"syntology":{"n":757,"n_ran":510,"n_unverified":247,"n_pointer_only":426}},{"url":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","repositories_listed":80,"syntology":{"n":207,"n_ran":108,"n_unverified":99,"n_pointer_only":43}},{"url":"/paper/rethinking-atrous-convolution-for-semantic","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","date":"2017-06-17","arxiv_id":"1706.05587","repositories_listed":77,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","arxiv_id":"1511.00561","repositories_listed":74,"syntology":{"n":44,"n_ran":9,"n_unverified":35,"n_pointer_only":10}},{"url":"/paper/pyramid-scene-parsing-network","title":"Pyramid Scene Parsing Network","date":"2016-12-04","arxiv_id":"1612.01105","repositories_listed":67,"syntology":{"n":29,"n_ran":7,"n_unverified":22,"n_pointer_only":5}},{"url":"/paper/fully-convolutional-networks-for-semantic-1","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2014-11-14","arxiv_id":"1411.4038","repositories_listed":51,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/190807919","title":"Deep High-Resolution Representation Learning for Visual Recognition","date":"2019-08-20","arxiv_id":"1908.07919","repositories_listed":42,"syntology":{"n":34,"n_ran":3,"n_unverified":31,"n_pointer_only":16}},{"url":"/paper/unet-a-nested-u-net-architecture-for-medical","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","date":"2018-07-18","arxiv_id":"1807.10165","repositories_listed":34,"syntology":{"n":28,"n_ran":5,"n_unverified":23,"n_pointer_only":2}},{"url":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","arxiv_id":"2105.15203","repositories_listed":28,"syntology":{"n":86,"n_ran":48,"n_unverified":38,"n_pointer_only":15}},{"url":"/paper/fast-scnn-fast-semantic-segmentation-network","title":"Fast-SCNN: Fast Semantic Segmentation Network","date":"2019-02-12","arxiv_id":"1902.04502","repositories_listed":24,"syntology":{"n":32,"n_ran":0,"n_unverified":32,"n_pointer_only":0}},{"url":"/paper/bisenet-bilateral-segmentation-network-for","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","date":"2018-08-02","arxiv_id":"1808.00897","repositories_listed":21,"syntology":{"n":18,"n_ran":6,"n_unverified":12,"n_pointer_only":1}},{"url":"/paper/icnet-for-real-time-semantic-segmentation-on","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","date":"2017-04-27","arxiv_id":"1704.08545","repositories_listed":18,"syntology":null},{"url":"/paper/linknet-exploiting-encoder-representations","title":"LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation","date":"2017-06-14","arxiv_id":"1707.03718","repositories_listed":14,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/erfnet-efficient-residual-factorized-convnet","title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","date":"2017-10-09","arxiv_id":null,"repositories_listed":13,"syntology":null},{"url":"/paper/panoptic-feature-pyramid-networks","title":"Panoptic Feature Pyramid Networks","date":"2019-01-08","arxiv_id":"1901.02446","repositories_listed":12,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/dual-attention-network-for-scene-segmentation","title":"Dual Attention Network for Scene Segmentation","date":"2018-09-09","arxiv_id":"1809.02983","repositories_listed":12,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/context-encoding-for-semantic-segmentation","title":"Context Encoding for Semantic Segmentation","date":"2018-03-23","arxiv_id":"1803.08904","repositories_listed":12,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":7}},{"url":"/paper/segmenter-transformer-for-semantic","title":"Segmenter: Transformer for Semantic Segmentation","date":"2021-05-12","arxiv_id":"2105.05633","repositories_listed":8,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/understanding-convolution-for-semantic","title":"Understanding Convolution for Semantic Segmentation","date":"2017-02-27","arxiv_id":"1702.08502","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/efficient-rgb-d-semantic-segmentation-for","title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","date":"2020-11-13","arxiv_id":"2011.06961","repositories_listed":4,"syntology":null},{"url":"/paper/ccnet-criss-cross-attention-for-semantic","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","date":"2018-11-28","arxiv_id":"1811.11721","repositories_listed":4,"syntology":{"n":14,"n_ran":9,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/depth-aware-cnn-for-rgb-d-segmentation","title":"Depth-aware CNN for RGB-D Segmentation","date":"2018-03-19","arxiv_id":"1803.06791","repositories_listed":4,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/full-resolution-residual-networks-for","title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","date":"2016-11-24","arxiv_id":"1611.08323","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/paif-perception-aware-infrared-visible-image","title":"PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation","date":"2023-08-08","arxiv_id":"2308.03979","repositories_listed":3,"syntology":{"n":27,"n_ran":13,"n_unverified":14,"n_pointer_only":11}},{"url":"/paper/specificity-preserving-rgb-d-saliency","title":"Specificity-preserving RGB-D Saliency Detection","date":"2021-08-18","arxiv_id":"2108.08162","repositories_listed":3,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":14}},{"url":"/paper/learning-a-discriminative-feature-network-for","title":"Learning a Discriminative Feature Network for Semantic Segmentation","date":"2018-04-25","arxiv_id":"1804.09337","repositories_listed":3,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/multi-interactive-feature-learning-and-a-full","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","date":"2023-08-04","arxiv_id":"2308.02097","repositories_listed":2,"syntology":{"n":26,"n_ran":19,"n_unverified":7,"n_pointer_only":13}},{"url":"/paper/visual-saliency-transformer","title":"Visual Saliency Transformer","date":"2021-04-25","arxiv_id":"2104.12099","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/accurate-rgb-d-salient-object-detection-via","title":"Accurate RGB-D Salient Object Detection via Collaborative Learning","date":"2020-07-23","arxiv_id":"2007.11782","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/bi-directional-cross-modality-feature","title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","date":"2020-07-17","arxiv_id":"2007.09183","repositories_listed":2,"syntology":null}],"syntology_records":26,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}