{"url":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":{"name":"Few-Shot Semantic Segmentation","url":"/task/few-shot-image-segmentation","note":null},"dataset":{"name":"COCO-20i (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","learnable parameters (million)"],"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","learnable parameters (million)":null}},"counts":{"rows":81,"rows_with_code":72,"rows_with_paper_page":81,"rows_dated":81,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SegGPT (ViT)","metrics":{"Mean IoU":"67.9"},"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":10,"n_unverified":0,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"GF-SAM (DINOv2)","metrics":{"Mean IoU":"66.8"},"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":3,"model":"PGMA-Net (ResNet-101)","metrics":{"FB-IoU":"79.4","Mean IoU":"61.8"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/visual-and-textual-prior-guided-mask-assemble","paper_url":"https://arxiv.org/abs/2308.07539v1","paper_title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"Matcher(DINOv2)","metrics":{"Mean IoU":"60.7"},"uses_additional_data":false,"paper_date":"2023-05-22","paper":"/paper/matcher-segment-anything-with-one-shot-using","paper_url":"https://arxiv.org/abs/2305.13310v2","paper_title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","code":"https://github.com/aim-uofa/matcher","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DiffewS(SD2.1)","metrics":{"Mean IoU":"60.7"},"uses_additional_data":false,"paper_date":"2024-10-03","paper":"/paper/unleashing-the-potential-of-the-diffusion","paper_url":"https://arxiv.org/abs/2410.02369v3","paper_title":"Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation","code":"https://github.com/aim-uofa/diffews","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":6,"model":"HMNet (ResNet-50)","metrics":{"FB-IoU":"77.6","Mean IoU":"58.9"},"uses_additional_data":false,"paper_date":"2024-09-29","paper":"/paper/hybrid-mamba-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2409.19613v1","paper_title":"Hybrid Mamba for Few-Shot Segmentation","code":"https://github.com/sam1224/hmnet","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":7,"model":"FPTrans (DeiT-B/16)","metrics":{"Mean IoU":"58.9"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/feature-proxy-transformer-for-few-shot","paper_url":"https://arxiv.org/abs/2210.06908v1","paper_title":"Feature-Proxy Transformer for Few-Shot Segmentation","code":"https://github.com/jarvis73/fptrans","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"DCAMA (Swin-B)","metrics":{"FB-IoU":"76.9","Mean IoU":"58.3"},"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":9,"model":"DGPNet (ResNet-101)","metrics":{"Mean IoU":"57.9"},"uses_additional_data":false,"paper_date":"2021-10-07","paper":"/paper/dense-gaussian-processes-for-few-shot","paper_url":"https://arxiv.org/abs/2110.03674v2","paper_title":"Dense Gaussian Processes for Few-Shot Segmentation","code":"https://github.com/joakimjohnander/dgpnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"AENet (ResNet-50)","metrics":{"FB-IoU":"78.5","Mean IoU":"57.1"},"uses_additional_data":false,"paper_date":"2024-07-13","paper":"/paper/eliminating-feature-ambiguity-for-few-shot","paper_url":"https://arxiv.org/abs/2407.09842v1","paper_title":"Eliminating Feature Ambiguity for Few-Shot Segmentation","code":"https://github.com/sam1224/aenet","n_code_links":1,"syntology":{"n_ran":20,"n_unverified":4,"n_samples":24,"n_pointer_only_licence":24}},{"rank_in_archive_order":11,"model":"PGMA-Net (ResNet-50)","metrics":{"FB-IoU":"76.7","Mean IoU":"57.1"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/visual-and-textual-prior-guided-mask-assemble","paper_url":"https://arxiv.org/abs/2308.07539v1","paper_title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"SCCAN (ResNet-101)","metrics":{"FB-IoU":"74.8","Mean IoU":"57"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/self-calibrated-cross-attention-network-for","paper_url":"https://arxiv.org/abs/2308.09294v1","paper_title":"Self-Calibrated Cross Attention Network for Few-Shot Segmentation","code":"https://github.com/sam1224/sccan","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":13,"model":"MSANet (ResNet-101)","metrics":{"FB-IoU":"56.8","Mean IoU":"56.3"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/msanet-multi-similarity-and-attention-1","paper_url":"https://arxiv.org/abs/2206.09667v1","paper_title":"MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation","code":"https://github.com/AIVResearch/MSANet","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"DGPNet (ResNet-50)","metrics":{"Mean IoU":"56.2"},"uses_additional_data":false,"paper_date":"2021-10-07","paper":"/paper/dense-gaussian-processes-for-few-shot","paper_url":"https://arxiv.org/abs/2110.03674v2","paper_title":"Dense Gaussian Processes for Few-Shot Segmentation","code":"https://github.com/joakimjohnander/dgpnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"HDMNet (ResNet-50)","metrics":{"FB-IoU":"77.7","Mean IoU":"56"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/hierarchical-dense-correlation-distillation","paper_url":"https://arxiv.org/abs/2303.14652v1","paper_title":"Hierarchical Dense Correlation Distillation for Few-Shot Segmentation","code":"https://github.com/pbihao/hdmnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"MSDNet (ResNet-101)","metrics":{"FB-IoU":"75.1","Mean IoU":"55.3","learnable parameters (million)":"1.5"},"uses_additional_data":false,"paper_date":"2024-09-17","paper":"/paper/msdnet-multi-scale-decoder-for-few-shot","paper_url":"https://arxiv.org/abs/2409.11316v2","paper_title":"MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping","code":"https://github.com/amirrezafateh/msdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"ProtoFormer (ResNet-101)","metrics":{"FB-IoU":"74.6","Mean IoU":"54.7"},"uses_additional_data":false,"paper_date":"2022-11-27","paper":"/paper/prototype-as-query-for-few-shot-semantic","paper_url":"https://arxiv.org/abs/2211.14764v1","paper_title":"Prototype as Query for Few Shot Semantic Segmentation","code":"https://github.com/leileicao/protoformer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"HMNet (VGG-16)","metrics":{"FB-IoU":"75.5","Mean IoU":"54.5"},"uses_additional_data":false,"paper_date":"2024-09-29","paper":"/paper/hybrid-mamba-for-few-shot-segmentation","paper_url":"https://arxiv.org/abs/2409.19613v1","paper_title":"Hybrid Mamba for Few-Shot Segmentation","code":"https://github.com/sam1224/hmnet","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":19,"model":"MSDNet (ResNet-50)","metrics":{"FB-IoU":"74.5","Mean IoU":"54.5","learnable parameters (million)":"1.5"},"uses_additional_data":false,"paper_date":"2024-09-17","paper":"/paper/msdnet-multi-scale-decoder-for-few-shot","paper_url":"https://arxiv.org/abs/2409.11316v2","paper_title":"MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping","code":"https://github.com/amirrezafateh/msdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"PFENet (SVF, ResNet-50)","metrics":{"Mean IoU":"54.38"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/singular-value-fine-tuning-few-shot-1","paper_url":"https://arxiv.org/abs/2206.06122v2","paper_title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","code":"https://github.com/syp2ysy/SVF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"SCCAN (ResNet-50)","metrics":{"FB-IoU":"74.2","Mean IoU":"53.9"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/self-calibrated-cross-attention-network-for","paper_url":"https://arxiv.org/abs/2308.09294v1","paper_title":"Self-Calibrated Cross Attention Network for Few-Shot Segmentation","code":"https://github.com/sam1224/sccan","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":22,"model":"BAM (SVF, ResNet-50)","metrics":{"Mean IoU":"53.87"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/singular-value-fine-tuning-few-shot-1","paper_url":"https://arxiv.org/abs/2206.06122v2","paper_title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","code":"https://github.com/syp2ysy/SVF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"FPTrans (ViT-B/16)","metrics":{"Mean IoU":"53.8"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/feature-proxy-transformer-for-few-shot","paper_url":"https://arxiv.org/abs/2210.06908v1","paper_title":"Feature-Proxy Transformer for Few-Shot Segmentation","code":"https://github.com/jarvis73/fptrans","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"ProtoFormer (ResNet-50)","metrics":{"FB-IoU":"73.3","Mean IoU":"53.4"},"uses_additional_data":false,"paper_date":"2022-11-27","paper":"/paper/prototype-as-query-for-few-shot-semantic","paper_url":"https://arxiv.org/abs/2211.14764v1","paper_title":"Prototype as Query for Few Shot Semantic Segmentation","code":"https://github.com/leileicao/protoformer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"IPRNet (ResNet-101)","metrics":{"Mean IoU":"53.3"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/interclass-prototype-relation-for-few-shot","paper_url":"https://arxiv.org/abs/2211.08681v1","paper_title":"Interclass Prototype Relation for Few-Shot Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"AENet (VGG-16)","metrics":{"FB-IoU":"74.3","Mean IoU":"52.8"},"uses_additional_data":false,"paper_date":"2024-07-13","paper":"/paper/eliminating-feature-ambiguity-for-few-shot","paper_url":"https://arxiv.org/abs/2407.09842v1","paper_title":"Eliminating Feature Ambiguity for Few-Shot Segmentation","code":"https://github.com/sam1224/aenet","n_code_links":1,"syntology":{"n_ran":20,"n_unverified":4,"n_samples":24,"n_pointer_only_licence":24}},{"rank_in_archive_order":27,"model":"HDMNet (VGG-16)","metrics":{"Mean IoU":"52.4"},"uses_additional_data":false,"paper_date":"2023-03-26","paper":"/paper/hierarchical-dense-correlation-distillation","paper_url":"https://arxiv.org/abs/2303.14652v1","paper_title":"Hierarchical Dense Correlation Distillation for Few-Shot Segmentation","code":"https://github.com/pbihao/hdmnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"DCAMA (ResNet-101)","metrics":{"FB-IoU":"73.3","Mean IoU":"51.9","learnable parameters (million)":"47.7"},"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":29,"model":"QCLNet (ResNet-101)","metrics":{"Mean IoU":"51.9"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/quaternion-valued-correlation-learning-for","paper_url":"https://arxiv.org/abs/2305.07283v3","paper_title":"Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation","code":"https://github.com/zwzheng98/qclnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"MIANet (ResNet-50)","metrics":{"FB-IoU":"73.13","Mean IoU":"51.65"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/mianet-aggregating-unbiased-instance-and-1","paper_url":"https://arxiv.org/abs/2305.13864v1","paper_title":"MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation","code":"https://github.com/aldrich2y/mianet","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"BAM (ResNet-50)","metrics":{"Mean IoU":"51.16","learnable parameters (million)":"26.7"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/learning-what-not-to-segment-a-new","paper_url":"https://arxiv.org/abs/2203.07615v2","paper_title":"Learning What Not to Segment: A New Perspective on Few-Shot Segmentation","code":"https://github.com/chunbolang/BAM","n_code_links":1,"syntology":{"n_ran":15,"n_unverified":2,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"IPRNet (ResNet-50)","metrics":{"Mean IoU":"51.1"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/interclass-prototype-relation-for-few-shot","paper_url":"https://arxiv.org/abs/2211.08681v1","paper_title":"Interclass Prototype Relation for Few-Shot Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"MCE (ResNet-50)","metrics":{"Mean IoU":"51.04"},"uses_additional_data":false,"paper_date":"2023-08-22","paper":"/paper/masked-cross-image-encoding-for-few-shot","paper_url":"https://arxiv.org/abs/2308.11201v1","paper_title":"Masked Cross-image Encoding for Few-shot Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"MIANet (VGG-16)","metrics":{"FB-IoU":"73.81","Mean IoU":"51.03"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/mianet-aggregating-unbiased-instance-and-1","paper_url":"https://arxiv.org/abs/2305.13864v1","paper_title":"MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation","code":"https://github.com/aldrich2y/mianet","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"ASNet (HM, ResNet-101)","metrics":{"FB-IoU":"73.3","Mean IoU":"50.6"},"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":36,"model":"HSNet (HM, ResNet-101)","metrics":{"FB-IoU":"72.9","Mean IoU":"50.6"},"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":37,"model":"MSANet (ResNet-50)","metrics":{"FB-IoU":"53.67","Mean IoU":"50.47"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/msanet-multi-similarity-and-attention-1","paper_url":"https://arxiv.org/abs/2206.09667v1","paper_title":"MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation","code":"https://github.com/AIVResearch/MSANet","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":38,"model":"SSP (ResNet-101)","metrics":{"Mean IoU":"50.2"},"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":39,"model":"QCLNet (ResNet-50)","metrics":{"Mean IoU":"50"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/quaternion-valued-correlation-learning-for","paper_url":"https://arxiv.org/abs/2305.07283v3","paper_title":"Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation","code":"https://github.com/zwzheng98/qclnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"HSNet (ResNet-101)","metrics":{"FB-IoU":"72.4","Mean IoU":"49.5","learnable parameters (million)":"2.5"},"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":41,"model":"ASNet","metrics":{"Mean IoU":"49.5"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/integrative-few-shot-learning-for","paper_url":"https://arxiv.org/abs/2203.15712v2","paper_title":"Integrative Few-Shot Learning for Classification and Segmentation","code":"https://github.com/dahyun-kang/ifsl","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"PFENet (SVF, VGG-16)","metrics":{"Mean IoU":"49.49"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/singular-value-fine-tuning-few-shot-1","paper_url":"https://arxiv.org/abs/2206.06122v2","paper_title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","code":"https://github.com/syp2ysy/SVF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"HSNet (HM, ResNet-50)","metrics":{"FB-IoU":"72.2","Mean IoU":"49.4"},"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":44,"model":"DACM (VAT, ResNet-50)","metrics":{"FB-IoU":"72.9","Mean IoU":"49.2"},"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":45,"model":"BAM (SVF, VGG-16)","metrics":{"Mean IoU":"49.07"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/singular-value-fine-tuning-few-shot-1","paper_url":"https://arxiv.org/abs/2206.06122v2","paper_title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","code":"https://github.com/syp2ysy/SVF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"ASNet (HM, ResNet-50)","metrics":{"FB-IoU":"72.2","Mean IoU":"48.4"},"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":47,"model":"VAT (HM, ResNet-50)","metrics":{"FB-IoU":"71.8","Mean IoU":"48.3"},"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":48,"model":"DCAMA (ResNet-50)","metrics":{"FB-IoU":"71.7","Mean IoU":"48.3","learnable parameters (million)":"47.7"},"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":49,"model":"DACM (ResNet-50)","metrics":{"FB-IoU":"71.6","Mean IoU":"48.1"},"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":50,"model":"SiGCN (ResNet-50)","metrics":{"FB-IoU":"66.2","Mean IoU":"48"},"uses_additional_data":false,"paper_date":"2023-01-09","paper":"/paper/few-shot-semantic-segmentation-with-support","paper_url":"https://arxiv.org/abs/2301.03194v2","paper_title":"Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"VAT (ResNet-101)","metrics":{"FB-IoU":"72.4","Mean IoU":"47.9"},"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":12,"n_unverified":8,"n_samples":20,"n_pointer_only_licence":2}},{"rank_in_archive_order":52,"model":"VAT (ResNet-50)","metrics":{"Mean IoU":"47.9"},"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":53,"model":"IPMT (ResNet-101)","metrics":{"Mean IoU":"47.9"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/intermediate-prototype-mining-transformer-for","paper_url":"https://arxiv.org/abs/2210.06780v1","paper_title":"Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation","code":"https://github.com/liuyuanwei98/ipmt","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"FECANet (ResNet-50)","metrics":{"FB-IoU":"71.1","Mean IoU":"47.6"},"uses_additional_data":false,"paper_date":"2023-01-19","paper":"/paper/fecanet-boosting-few-shot-semantic","paper_url":"https://arxiv.org/abs/2301.08160v1","paper_title":"FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network","code":"https://github.com/nust-machine-intelligence-laboratory/fecanet","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"IPMT (ResNet-50)","metrics":{"Mean IoU":"47.5"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/intermediate-prototype-mining-transformer-for","paper_url":"https://arxiv.org/abs/2210.06780v1","paper_title":"Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation","code":"https://github.com/liuyuanwei98/ipmt","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"HSNet (ResNet-50)","metrics":{"FB-IoU":"70.7","Mean IoU":"46.9","learnable parameters (million)":"2.5"},"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":57,"model":"RePRI (CECE-M,ResNet-50)","metrics":{"Mean IoU":"46.9"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/clustered-patch-element-connection-for-few","paper_url":"https://arxiv.org/abs/2304.10093v3","paper_title":"Clustered-patch Element Connection for Few-shot Learning","code":"https://github.com/Layjins/CECNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"RePRI (CECE-T,ResNet-50)","metrics":{"Mean IoU":"46.7"},"uses_additional_data":false,"paper_date":"2023-04-20","paper":"/paper/clustered-patch-element-connection-for-few","paper_url":"https://arxiv.org/abs/2304.10093v3","paper_title":"Clustered-patch Element Connection for Few-shot Learning","code":"https://github.com/Layjins/CECNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"DCP (ResNet-50)","metrics":{"Mean IoU":"46.48"},"uses_additional_data":false,"paper_date":"2022-04-21","paper":"/paper/beyond-the-prototype-divide-and-conquer","paper_url":"https://arxiv.org/abs/2204.09903v2","paper_title":"Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation","code":"https://github.com/chunbolang/DCP","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":1,"n_samples":13,"n_pointer_only_licence":1}},{"rank_in_archive_order":60,"model":"APANet (ResNet-101)","metrics":{"Mean IoU":"46.4"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/apanet-adaptive-prototypes-alignment-network","paper_url":"https://arxiv.org/abs/2111.12263v2","paper_title":"APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"CyCTR (ResNet-50)","metrics":{"Mean IoU":"45.6","learnable parameters (million)":"15.4"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/few-shot-segmentation-via-cycle-consistent","paper_url":"https://arxiv.org/abs/2106.02320v4","paper_title":"Few-Shot Segmentation via Cycle-Consistent Transformer","code":"https://github.com/YanFangCS/CyCTR-Pytorch","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":62,"model":"MLC (ResNet-101)","metrics":{"Mean IoU":"45.1"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/mining-latent-classes-for-few-shot","paper_url":"https://arxiv.org/abs/2103.15402v3","paper_title":"Mining Latent Classes for Few-shot Segmentation","code":"https://github.com/LiheYoung/MiningFSS","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":63,"model":"IMR-HSNet (ResNet-50)","metrics":{"Mean IoU":"44.4"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/iterative-few-shot-semantic-segmentation-from","paper_url":"https://arxiv.org/abs/2303.05646v1","paper_title":"Iterative Few-shot Semantic Segmentation from Image Label Text","code":"https://github.com/whileherham/imr-hsnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":64,"model":"SSP (ResNet-50)","metrics":{"Mean IoU":"44.1"},"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":65,"model":"APANet (VGG-16)","metrics":{"Mean IoU":"43.2"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/apanet-adaptive-prototypes-alignment-network","paper_url":"https://arxiv.org/abs/2111.12263v2","paper_title":"APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":66,"model":"APANet (ResNet-50)","metrics":{"Mean IoU":"43"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/apanet-adaptive-prototypes-alignment-network","paper_url":"https://arxiv.org/abs/2111.12263v2","paper_title":"APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"ASGNet (ResNet-50)","metrics":{"FB-IoU":"66.96","Mean IoU":"42.48"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/adaptive-prototype-learning-and-allocation","paper_url":"https://arxiv.org/abs/2104.01893v2","paper_title":"Adaptive Prototype Learning and Allocation for Few-Shot Segmentation","code":"https://github.com/Reagan1311/ASGNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":68,"model":"CWT (ResNet-101)","metrics":{"Mean IoU":"42"},"uses_additional_data":false,"paper_date":"2021-08-06","paper":"/paper/simpler-is-better-few-shot-semantic","paper_url":"https://arxiv.org/abs/2108.03032v3","paper_title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","code":"https://github.com/zhiheLu/CWT-for-FSS","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":69,"model":"RePRI (ResNet-50)","metrics":{"Mean IoU":"41.6"},"uses_additional_data":false,"paper_date":"2020-12-11","paper":"/paper/few-shot-segmentation-without-meta-learning-a","paper_url":"https://arxiv.org/abs/2012.06166v2","paper_title":"Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?","code":"https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation","n_code_links":2,"syntology":null},{"rank_in_archive_order":70,"model":"FECANet (VGG-16)","metrics":{"FB-IoU":"67.7","Mean IoU":"41.5"},"uses_additional_data":false,"paper_date":"2023-01-19","paper":"/paper/fecanet-boosting-few-shot-semantic","paper_url":"https://arxiv.org/abs/2301.08160v1","paper_title":"FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network","code":"https://github.com/nust-machine-intelligence-laboratory/fecanet","n_code_links":1,"syntology":null},{"rank_in_archive_order":71,"model":"MLC (ResNet-50)","metrics":{"Mean IoU":"41.4"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/mining-latent-classes-for-few-shot","paper_url":"https://arxiv.org/abs/2103.15402v3","paper_title":"Mining Latent Classes for Few-shot Segmentation","code":"https://github.com/LiheYoung/MiningFSS","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"CWT (ResNet-50)","metrics":{"Mean IoU":"41.3"},"uses_additional_data":false,"paper_date":"2021-08-06","paper":"/paper/simpler-is-better-few-shot-semantic","paper_url":"https://arxiv.org/abs/2108.03032v3","paper_title":"Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer","code":"https://github.com/zhiheLu/CWT-for-FSS","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":73,"model":"PFENet (SCL, ResNet-101)","metrics":{"Mean IoU":"39.9"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/self-guided-and-cross-guided-learning-for-few","paper_url":"https://arxiv.org/abs/2103.16129v1","paper_title":"Self-Guided and Cross-Guided Learning for Few-Shot Segmentation","code":"https://github.com/zbf1991/SCL","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":74,"model":"PPNet (ResNet-50)","metrics":{"Mean IoU":"38.5","learnable parameters (million)":"31.5"},"uses_additional_data":false,"paper_date":"2020-07-13","paper":"/paper/part-aware-prototype-network-for-few-shot","paper_url":"https://arxiv.org/abs/2007.06309v3","paper_title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","code":"https://github.com/Xiangyi1996/PPNet-PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":75,"model":"PFENet (VGG-16)","metrics":{"FB-IoU":"61.6","Mean IoU":"37.7"},"uses_additional_data":false,"paper_date":"2020-08-04","paper":"/paper/prior-guided-feature-enrichment-network-for","paper_url":"https://arxiv.org/abs/2008.01449v1","paper_title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","code":"https://github.com/Jia-Research-Lab/PFENet","n_code_links":3,"syntology":null},{"rank_in_archive_order":76,"model":"PFENet (ResNet-101)","metrics":{"FB-IoU":"61.9","Mean IoU":"37.4","learnable parameters (million)":"10.3"},"uses_additional_data":false,"paper_date":"2020-08-04","paper":"/paper/prior-guided-feature-enrichment-network-for","paper_url":"https://arxiv.org/abs/2008.01449v1","paper_title":"Prior Guided Feature Enrichment Network for Few-Shot Segmentation","code":"https://github.com/Jia-Research-Lab/PFENet","n_code_links":3,"syntology":null},{"rank_in_archive_order":77,"model":"ASR (ResNet-50)","metrics":{"Mean IoU":"35.75"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/anti-aliasing-semantic-reconstruction-for-few","paper_url":"https://arxiv.org/abs/2106.00184v1","paper_title":"Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation","code":"https://github.com/Bibkiller/ASR","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":78,"model":"RPMM (ResNet-50)","metrics":{"Mean IoU":"35.5"},"uses_additional_data":false,"paper_date":"2020-08-10","paper":"/paper/prototype-mixture-models-for-few-shot","paper_url":"https://arxiv.org/abs/2008.03898v2","paper_title":"Prototype Mixture Models for Few-shot Semantic Segmentation","code":"https://github.com/Yang-Bob/PMMs","n_code_links":1,"syntology":null},{"rank_in_archive_order":79,"model":"PANet (VGG-16)","metrics":{"FB-IoU":"63.5","Mean IoU":"29.7"},"uses_additional_data":false,"paper_date":"2019-08-18","paper":"/paper/panet-few-shot-image-semantic-segmentation","paper_url":"https://arxiv.org/abs/1908.06391v2","paper_title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","code":"https://github.com/kaixin96/PANet","n_code_links":5,"syntology":null},{"rank_in_archive_order":80,"model":"FWB (ResNet-101)","metrics":{"Mean IoU":"23.65","learnable parameters (million)":"43"},"uses_additional_data":false,"paper_date":"2019-09-28","paper":"/paper/feature-weighting-and-boosting-for-few-shot","paper_url":"https://arxiv.org/abs/1909.13140v1","paper_title":"Feature Weighting and Boosting for Few-Shot Segmentation","code":"https://github.com/ducminhkhoi/Feature-Weighting-and-Boosting","n_code_links":1,"syntology":null},{"rank_in_archive_order":81,"model":"FWB (VGG-16)","metrics":{"Mean IoU":"22.63"},"uses_additional_data":false,"paper_date":"2019-09-28","paper":"/paper/feature-weighting-and-boosting-for-few-shot","paper_url":"https://arxiv.org/abs/1909.13140v1","paper_title":"Feature Weighting and Boosting for Few-Shot Segmentation","code":"https://github.com/ducminhkhoi/Feature-Weighting-and-Boosting","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 7,081 of the 9,623 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":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":41,"rows_with_any_sample_ran":31,"distinct_papers_with_graph_line":22,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":111,"n_unverified":33,"n_samples":144,"n_pointer_only_licence":64,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":173,"n_unverified":60,"n_samples":233,"n_pointer_only_licence":126,"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"}}}