{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/learning-to-annotate-part-segmentation-with-1","title":"Learning to Annotate Part Segmentation with Gradient Matching","arxiv_id":"2211.03003","date":"2022-11-06","proceeding":"ICLR 2022 4","authors":["Yu Yang","Xiaotian Cheng","Hakan Bilen","Xiangyang Ji"],"abstract":"The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN and labelling the generated images with an automatic annotator. In particular, we formulate the annotator learning as a learning-to-learn problem. Given a pre-trained GAN, the annotator learns to label object parts in a set of randomly generated images such that a part segmentation model trained on these synthetic images with their predicted labels obtains low segmentation error on a small validation set of manually labelled images. We further reduce this nested-loop optimization problem to a simple gradient matching problem and efficiently solve it with an iterative algorithm. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images. Our method is evaluated with semi-supervised part segmentation tasks and significantly outperforms other semi-supervised competitors when the amount of labelled examples is extremely limited.","url_abs":"https://arxiv.org/abs/2211.03003v1","url_pdf":"https://arxiv.org/pdf/2211.03003v1.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":"learning-to-annotate-part-segmentation-with-1","repo_url":"https://github.com/yangyu12/lagm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.03003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03003"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/milesial/Pytorch-UNet","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyu12/lagm","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fc7aca119a00d268","entry":"GradientMatcher","repo":"yangyu12/lagm","repo_kind":"official","path":"training/loss.py","file_url":"https://github.com/yangyu12/lagm/blob/HEAD/training/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc7aca119a00d268"}},{"code_sha256_prefix":"40305d496ad82775","entry":"distance_wb","repo":"yangyu12/lagm","repo_kind":"official","path":"training/loss.py","file_url":"https://github.com/yangyu12/lagm/blob/HEAD/training/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40305d496ad82775"}},{"code_sha256_prefix":"fa28b5e7a248a1f8","entry":"gradient_matching","repo":"yangyu12/lagm","repo_kind":"official","path":"training/loss.py","file_url":"https://github.com/yangyu12/lagm/blob/HEAD/training/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa28b5e7a248a1f8"}},{"code_sha256_prefix":"63df326991f2f738","entry":"set_logging","repo":"yangyu12/lagm","repo_kind":"official","path":"downstream_seg.py","file_url":"https://github.com/yangyu12/lagm/blob/HEAD/downstream_seg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63df326991f2f738"}},{"code_sha256_prefix":"288e4b24566ba9c1","entry":"setup_snapshot_image_label_grid","repo":"yangyu12/lagm","repo_kind":"official","path":"annotate_seg.py","file_url":"https://github.com/yangyu12/lagm/blob/HEAD/annotate_seg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"288e4b24566ba9c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}