{"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/defrcn-decoupled-faster-r-cnn-for-few-shot","title":"DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection","arxiv_id":"2108.09017","date":"2021-08-20","proceeding":"ICCV 2021 10","authors":["Limeng Qiao","Yuxuan Zhao","Zhiyuan Li","Xi Qiu","Jianan Wu","Chi Zhang"],"abstract":"Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community. Most existing approaches employ the Faster R-CNN as basic detection framework, yet, due to the lack of tailored considerations for data-scarce scenario, their performance is often not satisfactory. In this paper, we look closely into the conventional Faster R-CNN and analyze its contradictions from two orthogonal perspectives, namely multi-stage (RPN vs. RCNN) and multi-task (classification vs. localization). To resolve these issues, we propose a simple yet effective architecture, named Decoupled Faster R-CNN (DeFRCN). To be concrete, we extend Faster R-CNN by introducing Gradient Decoupled Layer for multi-stage decoupling and Prototypical Calibration Block for multi-task decoupling. The former is a novel deep layer with redefining the feature-forward operation and gradient-backward operation for decoupling its subsequent layer and preceding layer, and the latter is an offline prototype-based classification model with taking the proposals from detector as input and boosting the original classification scores with additional pairwise scores for calibration. Extensive experiments on multiple benchmarks show our framework is remarkably superior to other existing approaches and establishes a new state-of-the-art in few-shot literature.","url_abs":"https://arxiv.org/abs/2108.09017v1","url_pdf":"https://arxiv.org/pdf/2108.09017v1.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":"defrcn-decoupled-faster-r-cnn-for-few-shot","repo_url":"https://github.com/er-muyue/defrcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"defrcn-decoupled-faster-r-cnn-for-few-shot","repo_url":"https://github.com/nvakhoa/mpad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"cross-domain-few-shot-object-detection","task_name":"Cross-Domain Few-Shot Object Detection"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"DeFRCN","rank_in_archive_order":11,"of":16,"metrics":{" mAP":"15.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"DeFRCN","rank_in_archive_order":7,"of":15,"metrics":{"mAP":"22.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"DeFRCN","rank_in_archive_order":9,"of":16,"metrics":{"mAP":"12.1"},"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":"DeFRCN","rank_in_archive_order":6,"of":7,"metrics":{"AP":"9.3"},"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":"DeFRCN","rank_in_archive_order":13,"of":33,"metrics":{"AP":"18.5"},"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":"DeFRCN","rank_in_archive_order":12,"of":25,"metrics":{"AP":"22.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.09017","atlas_url":"https://app.syntology.ai/?focus=2108.09017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09017"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/er-muyue/defrcn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvakhoa/mpad","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"4869aa3fc4a92bd7","entry":"GradientDecoupleLayer","repo":"er-muyue/defrcn","repo_kind":"official","path":"defrcn/modeling/meta_arch/gdl.py","file_url":"https://github.com/er-muyue/defrcn/blob/HEAD/defrcn/modeling/meta_arch/gdl.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":"4869aa3fc4a92bd7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}