{"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/boxinst-high-performance-instance","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","arxiv_id":"2012.02310","date":"2020-12-03","proceeding":"CVPR 2021 1","authors":["Zhi Tian","Chunhua Shen","Xinlong Wang","Hao Chen"],"abstract":"We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance with a simple design (e.g., dramatically improving previous best reported mask AP of 21.1% in Hsu et al. (2019) to 31.6% on the COCO dataset). Our core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself. The new loss functions can supervise the mask training without relying on mask annotations. This is made possible with two loss terms, namely, 1) a surrogate term that minimizes the discrepancy between the projections of the ground-truth box and the predicted mask; 2) a pairwise loss that can exploit the prior that proximal pixels with similar colors are very likely to have the same category label. Experiments demonstrate that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations. For example, without using any mask annotations, with a ResNet-101 backbone and 3x training schedule, we achieve 33.2% mask AP on COCO test-dev split (vs. 39.1% of the fully supervised counterpart). Our excellent experiment results on COCO and Pascal VOC indicate that our method dramatically narrows the performance gap between weakly and fully supervised instance segmentation. Code is available at: https://git.io/AdelaiDet","url_abs":"https://arxiv.org/abs/2012.02310v1","url_pdf":"https://arxiv.org/pdf/2012.02310v1.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":"boxinst-high-performance-instance","repo_url":"https://github.com/aim-uofa/AdelaiDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"boxinst-high-performance-instance","repo_url":"https://github.com/aim-uofa/adet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"box-supervised-instance-segmentation","task_name":"Box-supervised Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"weakly-supervised-instance-segmentation","task_name":"Weakly-supervised instance segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/box-supervised-instance-segmentation-on-coco","task":"Box-supervised Instance Segmentation","dataset":"COCO test-dev","model":"BoxInst","rank_in_archive_order":4,"of":7,"metrics":{"mask AP":"35.0"},"uses_additional_data":false},{"leaderboard":"/sota/box-supervised-instance-segmentation-on","task":"Box-supervised Instance Segmentation","dataset":"PASCAL VOC 2012 val","model":"BoxInst","rank_in_archive_order":2,"of":5,"metrics":{"AP_50":"61.4","AP_75":"37.0","mask AP":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-instance-segmentation-on-2","task":"Weakly-supervised instance segmentation","dataset":"COCO test-dev","model":"BoxInst (ResNet-101-DCN-BiFPN)","rank_in_archive_order":3,"of":7,"metrics":{"AP":"35.0","AP@50":"59.3","AP@75":"35.6","AP@L":"48.9","AP@M":"37.2","AP@S":"17.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-instance-segmentation-on-2","task":"Weakly-supervised instance segmentation","dataset":"COCO test-dev","model":"BoxInst (ResNet-101-BiFPN)","rank_in_archive_order":4,"of":7,"metrics":{"AP":"33.9","AP@50":"57.7","AP@75":"34.5","AP@L":"46.6","AP@M":"36.1","AP@S":"16.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-instance-segmentation-on-2","task":"Weakly-supervised instance segmentation","dataset":"COCO test-dev","model":"BoxInst (ResNet-101-FPN)","rank_in_archive_order":5,"of":7,"metrics":{"AP":"33.2","AP@50":"56.5","AP@75":"33.6","AP@L":"45.1","AP@M":"35.3","AP@S":"16.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-instance-segmentation-on-2","task":"Weakly-supervised instance segmentation","dataset":"COCO test-dev","model":"BoxInst (ResNet-50-FPN)","rank_in_archive_order":6,"of":7,"metrics":{"AP":"32.1","AP@50":"55.1","AP@75":"32.4","AP@L":"43.5","AP@M":"34.3","AP@S":"15.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.02310","atlas_url":"https://app.syntology.ai/?focus=2012.02310","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":"2012.02310"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.02310\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.02310"},"call":"get_concepts_for_paper(arxiv_id=\"2012.02310\")"}],"by_repo":[{"repo":"aim-uofa/AdelaiDet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aim-uofa/adet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"89fe202ae92226140fbaa1904ab56677520af1a8aebce8a2549835117458e2ca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}