{"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/fsce-few-shot-object-detection-via","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","arxiv_id":"2103.05950","date":"2021-03-10","proceeding":"CVPR 2021 1","authors":["Bo Sun","Banghuai Li","Shengcai Cai","Ye Yuan","Chi Zhang"],"abstract":"Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive approaches. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intra-class compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https: //github.com/MegviiDetection/FSCE","url_abs":"https://arxiv.org/abs/2103.05950v2","url_pdf":"https://arxiv.org/pdf/2103.05950v2.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":"fsce-few-shot-object-detection-via","repo_url":"https://github.com/MegviiDetection/FSCE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fsce-few-shot-object-detection-via","repo_url":"https://github.com/megvii-research/fsce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-domain-few-shot-object-detection","task_name":"Cross-Domain Few-Shot Object Detection"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"image-augmentation","task_name":"Image Augmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"FSCE","rank_in_archive_order":10,"of":16,"metrics":{" mAP":"15.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"FSCE","rank_in_archive_order":8,"of":15,"metrics":{"mAP":"21.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"FSCE","rank_in_archive_order":10,"of":16,"metrics":{"mAP":"12.0"},"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":"FSCE","rank_in_archive_order":25,"of":33,"metrics":{"AP":"11.1"},"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":"FSCE","rank_in_archive_order":16,"of":25,"metrics":{"AP":"15.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.05950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05950"}},"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/MegviiDetection/FSCE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-research/fsce","reach":{"status":"unanswered"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"a99e005b92d2d1b4","entry":"SupConLoss","repo":"MegviiDetection/FSCE","repo_kind":"official","path":"fsdet/modeling/contrastive_loss.py","file_url":"https://github.com/MegviiDetection/FSCE/blob/HEAD/fsdet/modeling/contrastive_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a99e005b92d2d1b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}