{"url":"/sota/few-shot-semantic-segmentation-on-fss-1000-5","task":{"name":"Few-Shot Semantic Segmentation","url":"/task/few-shot-image-segmentation","note":null},"dataset":{"name":"FSS-1000 (5-shot)","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Few-shot semantic segmentation (FSS) learns to segment target objects in query image given few pixel-wise annotated support image.","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":["Mean IoU","FB-IoU","mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher","FB-IoU":"higher","mIoU":null}},"counts":{"rows":22,"rows_with_code":22,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DACM (ResNet-101)","metrics":{"Mean IoU":"91.7"},"uses_additional_data":false,"paper_date":"2022-07-30","paper":"/paper/doubly-deformable-aggregation-of-covariance","paper_url":"https://arxiv.org/abs/2208.00306v1","paper_title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","code":"https://github.com/shadowxzt/dacm-few-shot.pytorch","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"DACM (ResNet-50)","metrics":{"Mean IoU":"91.6"},"uses_additional_data":false,"paper_date":"2022-07-30","paper":"/paper/doubly-deformable-aggregation-of-covariance","paper_url":"https://arxiv.org/abs/2208.00306v1","paper_title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","code":"https://github.com/shadowxzt/dacm-few-shot.pytorch","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"VAT (ResNet-101)","metrics":{"FB-IoU":"94.4","Mean IoU":"90.8"},"uses_additional_data":false,"paper_date":"2022-07-22","paper":"/paper/cost-aggregation-with-4d-convolutional-swin","paper_url":"https://arxiv.org/abs/2207.10866v1","paper_title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","code":"https://github.com/Seokju-Cho/Volumetric-Aggregation-Transformer","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":9,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"VAT (ResNet-50)","metrics":{"FB-IoU":"94.2","Mean IoU":"90.7"},"uses_additional_data":false,"paper_date":"2022-07-22","paper":"/paper/cost-aggregation-with-4d-convolutional-swin","paper_url":"https://arxiv.org/abs/2207.10866v1","paper_title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","code":"https://github.com/Seokju-Cho/Volumetric-Aggregation-Transformer","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":9,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"VAT","metrics":{"Mean IoU":"90.6"},"uses_additional_data":false,"paper_date":"2021-12-22","paper":"/paper/cost-aggregation-is-all-you-need-for-few-shot","paper_url":"https://arxiv.org/abs/2112.11685v1","paper_title":"Cost Aggregation Is All You Need for Few-Shot Segmentation","code":"https://github.com/Seokju-Cho/Volumetric-Aggregation-Transformer","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"VAT (HM, ResNet-101)","metrics":{"Mean IoU":"90.5"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/hmfs-hybrid-masking-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2203.12826v2","paper_title":"HM: Hybrid Masking for Few-Shot Segmentation","code":"https://github.com/moonsh/hm-hybrid-masking","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"DCAMA (Swin-B)","metrics":{"FB-IoU":"94.1","Mean IoU":"90.4"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/dense-cross-query-and-support-attention","paper_url":"https://arxiv.org/abs/2207.08549v1","paper_title":"Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation","code":"https://github.com/pawn-sxy/dcama","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":8,"model":"VAT (HM, ResNet-50)","metrics":{"Mean IoU":"89.9"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/hmfs-hybrid-masking-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2203.12826v2","paper_title":"HM: Hybrid Masking for Few-Shot Segmentation","code":"https://github.com/moonsh/hm-hybrid-masking","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"SegGPT (ViT)","metrics":{"Mean IoU":"89.3"},"uses_additional_data":false,"paper_date":"2023-04-06","paper":"/paper/seggpt-segmenting-everything-in-context","paper_url":"https://arxiv.org/abs/2304.03284v1","paper_title":"SegGPT: Segmenting Everything In Context","code":"https://github.com/baaivision/painter","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"DCAMA (ResNet-101)","metrics":{"FB-IoU":"93.1","Mean IoU":"89.1"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/dense-cross-query-and-support-attention","paper_url":"https://arxiv.org/abs/2207.08549v1","paper_title":"Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation","code":"https://github.com/pawn-sxy/dcama","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":11,"model":"GF-SAM (DINOv2)","metrics":{"Mean IoU":"88.9"},"uses_additional_data":false,"paper_date":"2024-10-09","paper":"/paper/bridge-the-points-graph-based-few-shot","paper_url":"https://arxiv.org/abs/2410.06964v2","paper_title":"Bridge the Points: Graph-based Few-shot Segment Anything Semantically","code":"https://github.com/ANDYZAQ/GF-SAM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"DCAMA (ResNet-50)","metrics":{"FB-IoU":"92.9","Mean IoU":"88.8"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/dense-cross-query-and-support-attention","paper_url":"https://arxiv.org/abs/2207.08549v1","paper_title":"Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation","code":"https://github.com/pawn-sxy/dcama","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":13,"model":"SSP","metrics":{"Mean IoU":"88.6"},"uses_additional_data":false,"paper_date":"2022-07-23","paper":"/paper/self-support-few-shot-semantic-segmentation","paper_url":"https://arxiv.org/abs/2207.11549v1","paper_title":"Self-Support Few-Shot Semantic Segmentation","code":"https://github.com/fanq15/ssp","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"HSNet (HM, ResNet-101)","metrics":{"Mean IoU":"88.5"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/hmfs-hybrid-masking-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2203.12826v2","paper_title":"HM: Hybrid Masking for Few-Shot Segmentation","code":"https://github.com/moonsh/hm-hybrid-masking","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"HSNet (ResNet-101)","metrics":{"Mean IoU":"88.5"},"uses_additional_data":false,"paper_date":"2021-04-04","paper":"/paper/hypercorrelation-squeeze-for-few-shot","paper_url":"https://arxiv.org/abs/2104.01538v3","paper_title":"Hypercorrelation Squeeze for Few-Shot Segmentation","code":"https://github.com/juhongm999/hsnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"HSNet (HM, ResNet-50)","metrics":{"Mean IoU":"88"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/hmfs-hybrid-masking-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2203.12826v2","paper_title":"HM: Hybrid Masking for Few-Shot Segmentation","code":"https://github.com/moonsh/hm-hybrid-masking","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"Annotation-free FSS (With Annotation,ResNet-50)","metrics":{"Mean IoU":"87.9"},"uses_additional_data":false,"paper_date":"2023-07-26","paper":"/paper/self-supervised-few-shot-learning-for-1","paper_url":"https://arxiv.org/abs/2307.14446v1","paper_title":"Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach","code":"https://github.com/mindflow-institue/annotation_free_fewshot","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"HSNet (ResNet-50)","metrics":{"Mean IoU":"87.8"},"uses_additional_data":false,"paper_date":"2021-04-04","paper":"/paper/hypercorrelation-squeeze-for-few-shot","paper_url":"https://arxiv.org/abs/2104.01538v3","paper_title":"Hypercorrelation Squeeze for Few-Shot Segmentation","code":"https://github.com/juhongm999/hsnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"Annotation-free FSS (Without Annotation,ResNet-50)","metrics":{"Mean IoU":"86.8"},"uses_additional_data":false,"paper_date":"2023-07-26","paper":"/paper/self-supervised-few-shot-learning-for-1","paper_url":"https://arxiv.org/abs/2307.14446v1","paper_title":"Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach","code":"https://github.com/mindflow-institue/annotation_free_fewshot","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"HSNet (VGG-16)","metrics":{"Mean IoU":"85.8"},"uses_additional_data":false,"paper_date":"2021-04-04","paper":"/paper/hypercorrelation-squeeze-for-few-shot","paper_url":"https://arxiv.org/abs/2104.01538v3","paper_title":"Hypercorrelation Squeeze for Few-Shot Segmentation","code":"https://github.com/juhongm999/hsnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"FSS-1000 (VGG-16)","metrics":{"Mean IoU":"80.12"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/fss-1000-a-1000-class-dataset-for-few-shot","paper_url":"https://arxiv.org/abs/1907.12347v2","paper_title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","code":"https://github.com/HKUSTCV/FSS-1000","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"EfficientLab + PRN","metrics":{"mIoU":"84.1"},"uses_additional_data":false,"paper_date":"2022-11-12","paper":"/paper/threshnet-segmentation-refinement-inspired-by","paper_url":"https://arxiv.org/abs/2211.06560v3","paper_title":"PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization","code":"https://github.com/savinay95n/PatchRefineNet","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":14,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":25,"n_unverified":18,"n_samples":43,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":46,"n_unverified":32,"n_samples":78,"n_pointer_only_licence":27,"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"}}}