{"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/decoupling-classifier-for-boosting-few-shot-1","title":"Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation","arxiv_id":"2505.14239","date":"2025-05-20","proceeding":"Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022) 2022 9","authors":["Bin-Bin Gao","Xiaochen Chen","Zhongyi Huang","Congchong Nie","Jun Liu","Jinxiang Lai","Guannan Jiang","Xi Wang","Chengjie Wang"],"abstract":"This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances. The existing methods severely suffer from bias classification because of the missing label issue which naturally exists in an instance-level few-shot scenario and is first formally proposed by us. Our analysis suggests that the standard classification head of most FSOD or FSIS models needs to be decoupled to mitigate the bias classification. Therefore, we propose an embarrassingly simple but effective method that decouples the standard classifier into two heads. Then, these two individual heads are capable of independently addressing clear positive samples and noisy negative samples which are caused by the missing label. In this way, the model can effectively learn novel classes while mitigating the effects of noisy negative samples. Without bells and whistles, our model without any additional computation cost and parameters consistently outperforms its baseline and state-of-the-art by a large margin on PASCAL VOC and MS-COCO benchmarks for FSOD and FSIS tasks. The Code is available at https://csgaobb.github.io/Projects/DCFS.","url_abs":"https://arxiv.org/abs/2505.14239v1","url_pdf":"https://arxiv.org/pdf/2505.14239v1.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":"decoupling-classifier-for-boosting-few-shot-1","repo_url":"https://github.com/gaobb/DCFS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-1-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (1-shot)","model":"DCFS","rank_in_archive_order":5,"of":7,"metrics":{"AP":"10.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-1-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (1-shot)","model":"DCFS","rank_in_archive_order":7,"of":7,"metrics":{"AP":"8.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (10-shot)","model":"DCFS","rank_in_archive_order":10,"of":33,"metrics":{"AP":"19.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-30-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (30-shot)","model":"DCFS","rank_in_archive_order":11,"of":25,"metrics":{"AP":"22.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.14239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14239"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaobb/DCFS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":2,"unverified":3},"by_repo_kind":{"named_in_paper":{"samples":7,"ran":4,"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":"d9def42110729a85","entry":"conv1x1","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/evaluation/archs/resnet.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/evaluation/archs/resnet.py","link_basis":"harvester_set","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":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/evaluation/archs/resnet.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/evaluation/archs/resnet.py","link_basis":"harvester_set","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":"160bb14bd76201b4"}},{"code_sha256_prefix":"9517da58a95bac43","entry":"filter_images_with_few_keypoints","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/dataloader/build.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/dataloader/build.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9517da58a95bac43"}},{"code_sha256_prefix":"4c8a4908e88089ef","entry":"filter_images_with_only_crowd_annotations","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/dataloader/build.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/dataloader/build.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c8a4908e88089ef"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/evaluation/calibration_layer.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/evaluation/calibration_layer.py","link_basis":"harvester_set","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":"73cecca9f3575f09"}},{"code_sha256_prefix":"236cab58a1cd1f88","entry":"inference_on_dataset","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/evaluation/evaluator.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/evaluation/evaluator.py","link_basis":"harvester_set","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":"236cab58a1cd1f88"}},{"code_sha256_prefix":"f6eff25d41b506dd","entry":"resnet18","repo":"gaobb/DCFS","repo_kind":"named_in_paper","path":"dcfs/evaluation/archs/resnet.py","file_url":"https://github.com/gaobb/DCFS/blob/HEAD/dcfs/evaluation/archs/resnet.py","link_basis":"harvester_set","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":"f6eff25d41b506dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}