{"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/beyond-the-prototype-divide-and-conquer","title":"Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation","arxiv_id":"2204.09903","date":"2022-04-21","proceeding":null,"authors":["Chunbo Lang","Binfei Tu","Gong Cheng","Junwei Han"],"abstract":"Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the \"episode\" level, not just about the object cues themselves. Extensive experiments on PASCAL-5i and COCO-20i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5~10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.","url_abs":"https://arxiv.org/abs/2204.09903v2","url_pdf":"https://arxiv.org/pdf/2204.09903v2.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":"beyond-the-prototype-divide-and-conquer","repo_url":"https://github.com/chunbolang/DCP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"DCP (ResNet-50)","rank_in_archive_order":57,"of":85,"metrics":{"Mean IoU":"41.39"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"DCP (ResNet-50)","rank_in_archive_order":59,"of":81,"metrics":{"Mean IoU":"46.48"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"DCP (ResNet-50)","rank_in_archive_order":72,"of":105,"metrics":{"Mean IoU":"62.80"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-5","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"DCP (ResNet-50)","rank_in_archive_order":61,"of":96,"metrics":{"Mean IoU":"67.80"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.09903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09903"}},"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/chunbolang/DCP","reach":null}],"summary":{"ran":4,"ran_draft_wrong":8,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":1,"samples":[{"code_sha256_prefix":"deb925d25beba09d","entry":"ASPP","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deb925d25beba09d"}},{"code_sha256_prefix":"9b6cbc9dee558bd7","entry":"Bottleneck","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b6cbc9dee558bd7"}},{"code_sha256_prefix":"2da49133aa591f02","entry":"ResNet","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2da49133aa591f02"}},{"code_sha256_prefix":"7aefeb45456c2c53","entry":"VGG","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7aefeb45456c2c53"}},{"code_sha256_prefix":"df77cb77dfe58d6d","entry":"Weighted_GAP","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"df77cb77dfe58d6d"}},{"code_sha256_prefix":"ad7ba6c4e516607e","entry":"get_vgg16_layer","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"ad7ba6c4e516607e"}},{"code_sha256_prefix":"3817cebff2add9fb","entry":"make_layers","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"3817cebff2add9fb"}},{"code_sha256_prefix":"ae93e3b60685c29d","entry":"resnet101","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"ae93e3b60685c29d"}},{"code_sha256_prefix":"bacf5d53a01d1e64","entry":"resnet152","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"bacf5d53a01d1e64"}},{"code_sha256_prefix":"a5b336b54939f4de","entry":"resnet50","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"a5b336b54939f4de"}},{"code_sha256_prefix":"0902796de5cc0ba5","entry":"vgg16","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"0902796de5cc0ba5"}},{"code_sha256_prefix":"7495062bfa6820b8","entry":"vgg16_bn","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.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":"7495062bfa6820b8"}},{"code_sha256_prefix":"c7581a28a77f6859","entry":"OneModel","repo":"chunbolang/DCP","repo_kind":"official","path":"model/DCP.py","file_url":"https://github.com/chunbolang/DCP/blob/HEAD/model/DCP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7581a28a77f6859"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}