{"url":"/sota/weakly-supervised-semantic-segmentation-on","task":{"name":"Weakly-Supervised Semantic Segmentation","url":"/task/weakly-supervised-semantic-segmentation","note":null},"dataset":{"name":"PASCAL VOC 2012 val","url":null},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":"The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset  consists of images and their corresponding\r\npixel-level class-specific annotations (expensive pixel-level annotations). However, in the\r\nweakly-supervised setting, the dataset consists of images and corresponding annotations that\r\nare relatively easy to obtain, such as tags/labels of objects present in the image.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.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":["Mean IoU"],"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"}},"counts":{"rows":73,"rows_with_code":72,"rows_with_paper_page":73,"rows_dated":73,"rows_using_additional_data":12},"rows":[{"rank_in_archive_order":1,"model":"SemPLeS (Swin-L)","metrics":{"Mean IoU":"83.4"},"uses_additional_data":false,"paper_date":"2024-01-22","paper":"/paper/semples-semantic-prompt-learning-for-weakly","paper_url":"https://arxiv.org/abs/2401.11791v4","paper_title":"Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation","code":"https://github.com/nvlabs/semples","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"FMA-WSSS (Swin-L)","metrics":{"Mean IoU":"82.6"},"uses_additional_data":false,"paper_date":"2023-12-06","paper":"/paper/foundation-model-assisted-weakly-supervised","paper_url":"https://arxiv.org/abs/2312.03585v2","paper_title":"Foundation Model Assisted Weakly Supervised Semantic Segmentation","code":"https://github.com/HAL-42/FMA-WSSS","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"DHR (Swin-L, Mask2Former)","metrics":{"Mean IoU":"82.3"},"uses_additional_data":false,"paper_date":"2024-03-30","paper":"/paper/dhr-dual-features-driven-hierarchical","paper_url":"https://arxiv.org/abs/2404.00380v2","paper_title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","code":"https://github.com/shjo-april/DHR","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":4,"model":"CoSA (SWIN-B, multi-stage)","metrics":{"Mean IoU":"81.4"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/weakly-supervised-co-training-with-swapping","paper_url":"https://arxiv.org/abs/2402.17891v2","paper_title":"Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation","code":"https://github.com/youshyee/cosa","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"WeakTr (ViT-S, multi-stage)","metrics":{"Mean IoU":"78.4"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/weaktr-exploring-plain-vision-transformer-for","paper_url":"https://arxiv.org/abs/2304.01184v2","paper_title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation","code":"https://github.com/hustvl/weaktr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MARS (ResNet-101, multi-stage)","metrics":{"Mean IoU":"77.7"},"uses_additional_data":false,"paper_date":"2023-04-19","paper":"/paper/mars-model-agnostic-biased-object-removal","paper_url":"https://arxiv.org/abs/2304.09913v1","paper_title":"MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation","code":"https://github.com/shjo-april/mars","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"WSSS-SAM(ResNet-101, multi-stage)","metrics":{"Mean IoU":"77.2"},"uses_additional_data":true,"paper_date":"2023-05-02","paper":"/paper/an-alternative-to-wsss-an-empirical-study-of","paper_url":"https://arxiv.org/abs/2305.01586v2","paper_title":"An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems","code":"https://github.com/weixuansun/wsss_sam","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"CoSA (ViT-B, single-stage)","metrics":{"Mean IoU":"76.4"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/weakly-supervised-co-training-with-swapping","paper_url":"https://arxiv.org/abs/2402.17891v2","paper_title":"Weakly Supervised Co-training with Swapping Assignments for Semantic Segmentation","code":"https://github.com/youshyee/cosa","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"QA-CLIMS","metrics":{"Mean IoU":"75.6"},"uses_additional_data":true,"paper_date":"2024-01-18","paper":"/paper/question-answer-cross-language-image-matching","paper_url":"https://arxiv.org/abs/2401.09883v1","paper_title":"Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation","code":"https://github.com/cvi-szu/qa-clims","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"ISIM (ResNeSt-200)","metrics":{"Mean IoU":"74.90"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/isim-iterative-self-improved-model-for-weakly","paper_url":"https://arxiv.org/abs/2211.12455v2","paper_title":"ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation","code":"https://github.com/cenkbircanoglu/isim","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"RS+EPM (ResNet-101, multi-stage)","metrics":{"Mean IoU":"74.4"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/recurseed-and-certainmix-for-weakly","paper_url":"https://arxiv.org/abs/2204.06754v4","paper_title":"RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks","code":"https://github.com/shjo-april/recurseed_and_edgepredictmix","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"FBR","metrics":{"Mean IoU":"74.2"},"uses_additional_data":true,"paper_date":"2024-06-22","paper":"/paper/fine-grained-background-representation-for","paper_url":"https://arxiv.org/abs/2406.15755v1","paper_title":"Fine-grained Background Representation for Weakly Supervised Semantic Segmentation","code":"https://github.com/YininKorea/FBR","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"WeakTr (DeiT-S, multi-stage)","metrics":{"Mean IoU":"74.0"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/weaktr-exploring-plain-vision-transformer-for","paper_url":"https://arxiv.org/abs/2304.01184v2","paper_title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation","code":"https://github.com/hustvl/weaktr","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"CLIP-ES(DeepLabV2-ResNet101)","metrics":{"Mean IoU":"73.8"},"uses_additional_data":false,"paper_date":"2022-12-16","paper":"/paper/clip-is-also-an-efficient-segmenter-a-text","paper_url":"https://arxiv.org/abs/2212.09506v3","paper_title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","code":"https://github.com/linyq2117/clip-es","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"BECO(DeepLabV3Plus+MiT-B2)","metrics":{"Mean IoU":"73.7"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/boundary-enhanced-co-training-for-weakly","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Rong_Boundary-Enhanced_Co-Training_for_Weakly_Supervised_Semantic_Segmentation_CVPR_2023_paper.html","paper_title":"Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation","code":"https://github.com/ShenghaiRong/BECO","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"T2MDiffusion(DeepLabV2-ResNet101)","metrics":{"Mean IoU":"73.3"},"uses_additional_data":true,"paper_date":"2023-09-08","paper":"/paper/from-text-to-mask-localizing-entities-using","paper_url":"https://arxiv.org/abs/2309.04109v2","paper_title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","code":"https://github.com/Big-Brother-Pikachu/Text2Mask","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"PPC (w/ EPS)","metrics":{"Mean IoU":"72.3"},"uses_additional_data":true,"paper_date":"2021-10-14","paper":"/paper/weakly-supervised-semantic-segmentation-by-3","paper_url":"https://arxiv.org/abs/2110.07110v3","paper_title":"Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast","code":"https://github.com/usr922/wseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"RCA","metrics":{"Mean IoU":"72.2"},"uses_additional_data":false,"paper_date":"2022-03-17","paper":"/paper/regional-semantic-contrast-and-aggregation","paper_url":"https://arxiv.org/abs/2203.09653v2","paper_title":"Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation","code":"https://github.com/maeve07/rca","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"ORANDNet","metrics":{"Mean IoU":"72.2"},"uses_additional_data":false,"paper_date":"2024-06-28","paper":"/paper/precision-matters-precision-aware-ensemble","paper_url":"https://arxiv.org/abs/2406.19638v1","paper_title":"Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation","code":"https://github.com/engineerJPark/ORANDNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"L2G (ResNet101, DeepLab-v2)","metrics":{"Mean IoU":"72.1"},"uses_additional_data":true,"paper_date":"2022-04-07","paper":"/paper/l2g-a-simple-local-to-global-knowledge","paper_url":"https://arxiv.org/abs/2204.03206v1","paper_title":"L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation","code":"https://github.com/pengtaojiang/l2g","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"BECO(DeepLabV3Plus+R101)","metrics":{"Mean IoU":"72.1"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/boundary-enhanced-co-training-for-weakly","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Rong_Boundary-Enhanced_Co-Training_for_Weakly_Supervised_Semantic_Segmentation_CVPR_2023_paper.html","paper_title":"Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation","code":"https://github.com/ShenghaiRong/BECO","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Puzzle-CAM (ResNeSt-269)","metrics":{"Mean IoU":"71.9"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/puzzle-cam-improved-localization-via-matching","paper_url":"https://arxiv.org/abs/2101.11253v4","paper_title":"Puzzle-CAM: Improved localization via matching partial and full features","code":"https://github.com/shjo-april/puzzlecam","n_code_links":4,"syntology":null},{"rank_in_archive_order":23,"model":"ACR (DeepLabV1-ResNet38)","metrics":{"Mean IoU":"71.9"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/weakly-supervised-semantic-segmentation-via-3","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Kweon_Weakly_Supervised_Semantic_Segmentation_via_Adversarial_Learning_of_Classifier_and_CVPR_2023_paper.html","paper_title":"Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor","code":"https://github.com/sangrockeg/acr","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"GETAM(vit-hybrid)","metrics":{"Mean IoU":"71.7"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/getam-gradient-weighted-element-wise","paper_url":"https://arxiv.org/abs/2112.02841v2","paper_title":"GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation","code":"https://github.com/weixuansun/GETAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"ADELE (DeepLabV1-ResNet38)","metrics":{"Mean IoU":"71.6"},"uses_additional_data":false,"paper_date":"2021-10-07","paper":"/paper/adaptive-early-learning-correction-for","paper_url":"https://arxiv.org/abs/2110.03740v2","paper_title":"Adaptive Early-Learning Correction for Segmentation from Noisy Annotations","code":"https://github.com/shengliu66/ELR","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"URN(Res2Net-101, no saliency, no RW)","metrics":{"Mean IoU":"71.2"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/uncertainty-estimation-via-response-scaling","paper_url":"https://arxiv.org/abs/2112.07431v1","paper_title":"Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation","code":"https://github.com/xmed-lab/urn","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"SFC(ResNet-101)","metrics":{"Mean IoU":"71.2"},"uses_additional_data":true,"paper_date":"2024-01-22","paper":"/paper/sfc-shared-feature-calibration-in-weakly","paper_url":"https://arxiv.org/abs/2401.11719v1","paper_title":"SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation","code":"https://github.com/barrett-python/sfc","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"ACR-WSSS(DeepLabV1-ResNet101)","metrics":{"Mean IoU":"71.2"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/all-pairs-consistency-learning-for-weakly","paper_url":"https://arxiv.org/abs/2308.04321v2","paper_title":"All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation","code":"https://github.com/opennlplab/acr_wsss","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"EPS(DeepLabV1-ResNet101)","metrics":{"Mean IoU":"71.0"},"uses_additional_data":true,"paper_date":"2021-05-19","paper":"/paper/railroad-is-not-a-train-saliency-as-pseudo-1","paper_url":"https://arxiv.org/abs/2105.08965v1","paper_title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","code":"https://github.com/halbielee/EPS","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":30,"model":"DRS (DeepLabV3Plus+R101)","metrics":{"Mean IoU":"71.0"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/discriminative-region-suppression-for-weakly","paper_url":"https://arxiv.org/abs/2103.07246v2","paper_title":"Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation","code":"https://github.com/qjadud1994/DRS","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"EPS(DeepLabV2-ResNet101)","metrics":{"Mean IoU":"70.9"},"uses_additional_data":true,"paper_date":"2021-05-19","paper":"/paper/railroad-is-not-a-train-saliency-as-pseudo-1","paper_url":"https://arxiv.org/abs/2105.08965v1","paper_title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","code":"https://github.com/halbielee/EPS","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":32,"model":"Infer-CAM(DeepLabV2-ResNet101)","metrics":{"Mean IoU":"70.8"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/inferring-the-class-conditional-response-map","paper_url":"https://arxiv.org/abs/2110.14309v1","paper_title":"Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation","code":"https://github.com/weixuansun/infercam","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"VWL-L (EMANet)","metrics":{"Mean IoU":"70.8"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/weakly-supervised-semantic-segmentation-with-1","paper_url":"https://arxiv.org/abs/2202.04812v1","paper_title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","code":"https://github.com/rulixiang/vwe/tree/master/v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"AMN (DeepLabV2-ResNet101, MS-COCO-pretrained weights)","metrics":{"Mean IoU":"70.7"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/threshold-matters-in-wsss-manipulating-the","paper_url":"https://arxiv.org/abs/2203.16045v1","paper_title":"Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds","code":"https://github.com/gaviotas/amn","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":35,"model":"W-OoD (WResNet-38)","metrics":{"Mean IoU":"70.7"},"uses_additional_data":false,"paper_date":"2022-03-08","paper":"/paper/weakly-supervised-semantic-segmentation-using-2","paper_url":"https://arxiv.org/abs/2203.03860v1","paper_title":"Weakly Supervised Semantic Segmentation using Out-of-Distribution Data","code":"https://github.com/naver-ai/w-ood","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"VWL-L","metrics":{"Mean IoU":"70.6"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/weakly-supervised-semantic-segmentation-with-1","paper_url":"https://arxiv.org/abs/2202.04812v1","paper_title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","code":"https://github.com/rulixiang/vwe/tree/master/v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"VWL-M","metrics":{"Mean IoU":"70.6"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/weakly-supervised-semantic-segmentation-with-1","paper_url":"https://arxiv.org/abs/2202.04812v1","paper_title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","code":"https://github.com/rulixiang/vwe/tree/master/v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"ISIM (ResNet-101)","metrics":{"Mean IoU":"70.51"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/isim-iterative-self-improved-model-for-weakly","paper_url":"https://arxiv.org/abs/2211.12455v2","paper_title":"ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation","code":"https://github.com/cenkbircanoglu/isim","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"DRS (DeepLabV2-R101)","metrics":{"Mean IoU":"70.4"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/discriminative-region-suppression-for-weakly","paper_url":"https://arxiv.org/abs/2103.07246v2","paper_title":"Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation","code":"https://github.com/qjadud1994/DRS","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"ViT-PCM","metrics":{"Mean IoU":"70.3"},"uses_additional_data":false,"paper_date":"2022-10-31","paper":"/paper/max-pooling-with-vision-transformers","paper_url":"https://arxiv.org/abs/2210.17400v1","paper_title":"Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation","code":"https://github.com/deepplants/vit-pcm","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"ClusterCAM","metrics":{"Mean IoU":"70.3"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/clustering-guided-class-activation-for-weakly","paper_url":"https://ieeexplore.ieee.org/abstract/document/10381698","paper_title":"Clustering-Guided Class Activation for Weakly Supervised Semantic Segmentation","code":"https://github.com/DCVL-WSSS/ClusterCAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"RIB+Sal (DeepLabV2-ResNet101)","metrics":{"Mean IoU":"70.2"},"uses_additional_data":true,"paper_date":"2021-10-13","paper":"/paper/reducing-information-bottleneck-for-weakly","paper_url":"https://arxiv.org/abs/2110.06530v1","paper_title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","code":"https://github.com/jbeomlee93/rib","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":43,"model":"URN(ScaleNet-101, no saliency, no RW)","metrics":{"Mean IoU":"70.1"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/uncertainty-estimation-via-response-scaling","paper_url":"https://arxiv.org/abs/2112.07431v1","paper_title":"Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation","code":"https://github.com/xmed-lab/urn","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"ICAM","metrics":{"Mean IoU":"70.1"},"uses_additional_data":false,"paper_date":"2022-03-23","paper":"/paper/activation-based-sampling-for-pixel-to-image","paper_url":"https://arxiv.org/abs/2203.12459v3","paper_title":"Importance Sampling CAMs for Weakly-Supervised Segmentation","code":"https://github.com/arvijj/icam","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"PMM(Res2Net101, no saliency, no RW)","metrics":{"Mean IoU":"70.0"},"uses_additional_data":false,"paper_date":"2021-08-30","paper":"/paper/pseudo-mask-matters-inweakly-supervised","paper_url":"https://arxiv.org/abs/2108.12995v2","paper_title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","code":"https://github.com/eli-yili/pmm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"URN(ResNet-101, no saliency, no RW)","metrics":{"Mean IoU":"69.5"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/uncertainty-estimation-via-response-scaling","paper_url":"https://arxiv.org/abs/2112.07431v1","paper_title":"Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation","code":"https://github.com/xmed-lab/urn","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"AMN (DeepLabV2-ResNet101)","metrics":{"Mean IoU":"69.5"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/threshold-matters-in-wsss-manipulating-the","paper_url":"https://arxiv.org/abs/2203.16045v1","paper_title":"Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds","code":"https://github.com/gaviotas/amn","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":48,"model":"RS+EPM (ResNet-50, single-stage)","metrics":{"Mean IoU":"69.5"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/recurseed-and-certainmix-for-weakly","paper_url":"https://arxiv.org/abs/2204.06754v4","paper_title":"RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks","code":"https://github.com/shjo-april/recurseed_and_edgepredictmix","n_code_links":2,"syntology":null},{"rank_in_archive_order":49,"model":"LIID (Res2Net-101)","metrics":{"Mean IoU":"69.4"},"uses_additional_data":false,"paper_date":"2020-09-10","paper":"/paper/leveraging-instance-image-and-dataset-level","paper_url":"https://ieeexplore.ieee.org/abstract/document/9193980","paper_title":"Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation","code":"https://github.com/yun-liu/LIID","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"URN(ResNet-38, no saliency, no RW)","metrics":{"Mean IoU":"69.4"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/uncertainty-estimation-via-response-scaling","paper_url":"https://arxiv.org/abs/2112.07431v1","paper_title":"Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation","code":"https://github.com/xmed-lab/urn","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"SLRNet","metrics":{"Mean IoU":"69.3"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/learning-self-supervised-low-rank-network-for","paper_url":"https://arxiv.org/abs/2203.10278v1","paper_title":"Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation","code":"https://github.com/DesertsP/SLRNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"SIPE (DeepLabV2-ResNet101, no saliency)","metrics":{"Mean IoU":"68.8"},"uses_additional_data":false,"paper_date":"2022-03-06","paper":"/paper/self-supervised-image-specific-prototype","paper_url":"https://arxiv.org/abs/2203.02909v1","paper_title":"Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation","code":"https://github.com/chenqi1126/sipe","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":53,"model":"WSGCN (MS-COCO-pre-trained weights)","metrics":{"Mean IoU":"68.7"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/weakly-supervised-image-semantic-segmentation","paper_url":"https://arxiv.org/abs/2103.16762v2","paper_title":"Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks","code":"https://github.com/Xavier-Pan/WSGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":54,"model":"PMM(ResNet38)","metrics":{"Mean IoU":"68.5"},"uses_additional_data":false,"paper_date":"2021-08-30","paper":"/paper/pseudo-mask-matters-inweakly-supervised","paper_url":"https://arxiv.org/abs/2108.12995v2","paper_title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","code":"https://github.com/eli-yili/pmm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":55,"model":"PMM(ResNet38, no saliency, no RW)","metrics":{"Mean IoU":"68.5"},"uses_additional_data":false,"paper_date":"2021-08-30","paper":"/paper/pseudo-mask-matters-inweakly-supervised","paper_url":"https://arxiv.org/abs/2108.12995v2","paper_title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","code":"https://github.com/eli-yili/pmm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"OC-CSE(ResNet38,no saliency)","metrics":{"Mean IoU":"68.4"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/unlocking-the-potential-of-ordinary","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Kweon_Unlocking_the_Potential_of_Ordinary_Classifier_Class-Specific_Adversarial_Erasing_Framework_ICCV_2021_paper.html","paper_title":"Unlocking the Potential of Ordinary Classifier: Class-Specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation","code":"https://github.com/kaist-vilab/oc-cse","n_code_links":1,"syntology":null},{"rank_in_archive_order":57,"model":"RIB (DeepLabV2-ResNet101)","metrics":{"Mean IoU":"68.3"},"uses_additional_data":false,"paper_date":"2021-10-13","paper":"/paper/reducing-information-bottleneck-for-weakly","paper_url":"https://arxiv.org/abs/2110.06530v1","paper_title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","code":"https://github.com/jbeomlee93/rib","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":58,"model":"GroupWSSS","metrics":{"Mean IoU":"68.2"},"uses_additional_data":false,"paper_date":"2020-12-09","paper":"/paper/group-wise-semantic-mining-for-weakly","paper_url":"https://arxiv.org/abs/2012.05007v1","paper_title":"Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation","code":"https://github.com/Lixy1997/Group-WSSS","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"AdvCAM (DeepLabV2-ResNet101)","metrics":{"Mean IoU":"68.1"},"uses_additional_data":false,"paper_date":"2021-03-16","paper":"/paper/anti-adversarially-manipulated-attributions","paper_url":"https://arxiv.org/abs/2103.08896v1","paper_title":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation","code":"https://github.com/jbeomlee93/AdvCAM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":60,"model":"LIID (ResNet-101, +24K SI)","metrics":{"Mean IoU":"67.8"},"uses_additional_data":true,"paper_date":"2020-09-10","paper":"/paper/leveraging-instance-image-and-dataset-level","paper_url":"https://ieeexplore.ieee.org/abstract/document/9193980","paper_title":"Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation","code":"https://github.com/yun-liu/LIID","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"CPN","metrics":{"Mean IoU":"67.8"},"uses_additional_data":false,"paper_date":"2021-08-09","paper":"/paper/complementary-patch-for-weakly-supervised","paper_url":"https://arxiv.org/abs/2108.03852v1","paper_title":"Complementary Patch for Weakly Supervised Semantic Segmentation","code":"https://github.com/Ferenas/CPN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":62,"model":"SLRNet(1-stage)","metrics":{"Mean IoU":"67.2"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/learning-self-supervised-low-rank-network-for","paper_url":"https://arxiv.org/abs/2203.10278v1","paper_title":"Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation","code":"https://github.com/DesertsP/SLRNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":63,"model":"SGAN","metrics":{"Mean IoU":"67.1"},"uses_additional_data":true,"paper_date":"2019-10-12","paper":"/paper/saliency-guided-self-attention-network-for","paper_url":"https://arxiv.org/abs/1910.05475v2","paper_title":"Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation","code":"https://github.com/yaoqi-zd/SGAN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":64,"model":"Puzzle-CAM (ResNeSt-101)","metrics":{"Mean IoU":"66.9"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/puzzle-cam-improved-localization-via-matching","paper_url":"https://arxiv.org/abs/2101.11253v4","paper_title":"Puzzle-CAM: Improved localization via matching partial and full features","code":"https://github.com/shjo-april/puzzlecam","n_code_links":4,"syntology":null},{"rank_in_archive_order":65,"model":"WSGCN (no Saliency map)","metrics":{"Mean IoU":"66.7"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/weakly-supervised-image-semantic-segmentation","paper_url":"https://arxiv.org/abs/2103.16762v2","paper_title":"Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks","code":"https://github.com/Xavier-Pan/WSGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"LIID (ResNet-101)","metrics":{"Mean IoU":"66.5"},"uses_additional_data":false,"paper_date":"2020-09-10","paper":"/paper/leveraging-instance-image-and-dataset-level","paper_url":"https://ieeexplore.ieee.org/abstract/document/9193980","paper_title":"Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation","code":"https://github.com/yun-liu/LIID","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"ResNet-101","metrics":{"Mean IoU":"66.2"},"uses_additional_data":false,"paper_date":"2020-07-03","paper":"/paper/mining-cross-image-semantics-for-weakly","paper_url":"https://arxiv.org/abs/2007.01947v2","paper_title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","code":"https://github.com/GuoleiSun/MCIS_wsss","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":68,"model":"SC-CAM-ResNet-101","metrics":{"Mean IoU":"66.1"},"uses_additional_data":false,"paper_date":"2020-08-03","paper":"/paper/weakly-supervised-semantic-segmentation-via-1","paper_url":"https://arxiv.org/abs/2008.01183v1","paper_title":"Weakly-Supervised Semantic Segmentation via Sub-category Exploration","code":"https://github.com/Juliachang/SC-CAM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":15,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":69,"model":"SEAM+CONTA","metrics":{"Mean IoU":"66.1"},"uses_additional_data":false,"paper_date":"2020-09-26","paper":"/paper/causal-intervention-for-weakly-supervised","paper_url":"https://arxiv.org/abs/2009.12547v2","paper_title":"Causal Intervention for Weakly-Supervised Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":70,"model":"OAA+","metrics":{"Mean IoU":"65.2"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/integral-object-mining-via-online-attention","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Jiang_Integral_Object_Mining_via_Online_Attention_Accumulation_ICCV_2019_paper.html","paper_title":"Integral Object Mining via Online Attention Accumulation","code":"https://github.com/PengtaoJiang/OAA-PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":71,"model":"SEAM-ResNet-38","metrics":{"Mean IoU":"64.5"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/self-supervised-equivariant-attention","paper_url":"https://arxiv.org/abs/2004.04581v1","paper_title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","code":"https://github.com/YudeWang/SEAM","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":72,"model":"ICD-ResNet-101","metrics":{"Mean IoU":"64.1"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/learning-integral-objects-with-intra-class","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Fan_Learning_Integral_Objects_With_Intra-Class_Discriminator_for_Weakly-Supervised_Semantic_Segmentation_CVPR_2020_paper.html","paper_title":"Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation","code":"https://github.com/js-fan/ICD","n_code_links":1,"syntology":null},{"rank_in_archive_order":73,"model":"IRNet (ResNet-50)","metrics":{"Mean IoU":"63.5"},"uses_additional_data":false,"paper_date":"2019-04-10","paper":"/paper/weakly-supervised-learning-of-instance","paper_url":"https://arxiv.org/abs/1904.05044v3","paper_title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","code":"https://github.com/jiwoon-ahn/irn","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}}],"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":29,"rows_with_any_sample_ran":21,"distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":46,"n_unverified":68,"n_samples":114,"n_pointer_only_licence":25,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":50,"n_unverified":82,"n_samples":132,"n_pointer_only_licence":32,"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"}}}