{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/seesaw-loss-for-long-tailed-instance","title":"Seesaw Loss for Long-Tailed Instance Segmentation","arxiv_id":"2008.10032","date":"2020-08-23","proceeding":"CVPR 2021 1","authors":["Jiaqi Wang","Wenwei Zhang","Yuhang Zang","Yuhang Cao","Jiangmiao Pang","Tao Gong","Kai Chen","Ziwei Liu","Chen Change Loy","Dahua Lin"],"abstract":"Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail. Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories. The overwhelming gradients of negative samples on tail classes lead to a biased learning process for classifiers. Consequently, objects of tail categories are more likely to be misclassified as backgrounds or head categories. To tackle this problem, we propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., mitigation factor and compensation factor. The mitigation factor reduces punishments to tail categories w.r.t. the ratio of cumulative training instances between different categories. Meanwhile, the compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories. We conduct extensive experiments on Seesaw Loss with mainstream frameworks and different data sampling strategies. With a simple end-to-end training pipeline, Seesaw Loss obtains significant gains over Cross-Entropy Loss, and achieves state-of-the-art performance on LVIS dataset without bells and whistles. Code is available at https://github.com/open-mmlab/mmdetection.","url_abs":"https://arxiv.org/abs/2008.10032v4","url_pdf":"https://arxiv.org/pdf/2008.10032v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"seesaw-loss-for-long-tailed-instance","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"seesaw-loss-for-long-tailed-instance","repo_url":"https://github.com/bamps53/SeesawLoss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"seesaw-loss-for-long-tailed-instance","repo_url":"https://github.com/MindCode-4/code-13/tree/main/SeesawLoss-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"seesaw-loss-for-long-tailed-instance","repo_url":"https://github.com/MindCode-4/code-8/tree/main/SeesawLoss-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"seesaw-loss-for-long-tailed-instance","repo_url":"https://github.com/MindCode-4/code-9/tree/main/Scalable-Sharpness-Aware-Minimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"seesaw-loss","method_name":"Seesaw Loss"}],"datasets_introduced":[],"methods_introduced":[{"slug":"seesaw-loss","name":"Seesaw Loss","full_name":"Seesaw Loss"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2008.10032","atlas_url":"https://app.syntology.ai/?focus=2008.10032","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2008.10032"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2008.10032\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2008.10032"},"call":"get_concepts_for_paper(arxiv_id=\"2008.10032\")"}],"by_repo":[{"repo":"open-mmlab/mmdetection","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02361"],"harvested_for_calls":[{"arxiv_id":"2401.02361","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02361"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02361\")"}]},{"repo":"bamps53/SeesawLoss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindCode-4/code-13","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.08663"],"harvested_for_calls":[{"arxiv_id":"2212.08663","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.08663"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.08663\")"}]},{"repo":"MindCode-4/code-8","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.13843"],"harvested_for_calls":[{"arxiv_id":"2103.13843","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.13843"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.13843\")"}]},{"repo":"MindCode-4/code-9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.09609"],"harvested_for_calls":[{"arxiv_id":"2210.09609","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.09609"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.09609\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"46ac5a145170ddc7b1abd500800a311387fc5b8a1867ba9db6fcd1dad817d220","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}