{"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/guided-distillation-for-semi-supervised","title":"Guided Distillation for Semi-Supervised Instance Segmentation","arxiv_id":"2308.02668","date":"2023-08-03","proceeding":null,"authors":["Tariq Berrada","Camille Couprie","Karteek Alahari","Jakob Verbeek"],"abstract":"Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches leverage unlabeled data as an additional training signal that limits overfitting to the labeled samples. In this context, we present novel design choices to significantly improve teacher-student distillation models. In particular, we (i) improve the distillation approach by introducing a novel \"guided burn-in\" stage, and (ii) evaluate different instance segmentation architectures, as well as backbone networks and pre-training strategies. Contrary to previous work which uses only supervised data for the burn-in period of the student model, we also use guidance of the teacher model to exploit unlabeled data in the burn-in period. Our improved distillation approach leads to substantial improvements over previous state-of-the-art results. For example, on the Cityscapes dataset we improve mask-AP from 23.7 to 33.9 when using labels for 10\\% of images, and on the COCO dataset we improve mask-AP from 18.3 to 34.1 when using labels for only 1\\% of the training data.","url_abs":"https://arxiv.org/abs/2308.02668v2","url_pdf":"https://arxiv.org/pdf/2308.02668v2.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":"guided-distillation-for-semi-supervised","repo_url":"https://github.com/facebookresearch/guideddistillation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-instance-segmentation","task_name":"Semi-Supervised Instance Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-4","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 1% labeled data","model":"Guided Distillation (ResNet50)","rank_in_archive_order":1,"of":3,"metrics":{"mask AP":"21.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-7","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 10% labeled data","model":"Guided Distillation (ResNet50)","rank_in_archive_order":1,"of":3,"metrics":{"mask AP":"35.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-5","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 2% labeled data","model":"Guided Distillation (ResNet50)","rank_in_archive_order":1,"of":3,"metrics":{"mask AP":"25.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-6","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 5% labeled data","model":"Guided Distillation (ResNet50)","rank_in_archive_order":1,"of":3,"metrics":{"mask AP":"29.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.02668","atlas_url":"https://app.syntology.ai/?focus=2308.02668","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":"2308.02668"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.02668\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.02668"},"call":"get_concepts_for_paper(arxiv_id=\"2308.02668\")"}],"by_repo":[{"repo":"facebookresearch/guideddistillation","kind":"official","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":"3fb0eac370de020c8f1f1fd8284b7e464e6579c227f93acc539aa590cde47d82","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}