{"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/frustratingly-simple-few-shot-object","title":"Frustratingly Simple Few-Shot Object Detection","arxiv_id":"2003.06957","date":"2020-03-16","proceeding":"ICML 2020 1","authors":["Xin Wang","Thomas E. Huang","Trevor Darrell","Joseph E. Gonzalez","Fisher Yu"],"abstract":"Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.","url_abs":"https://arxiv.org/abs/2003.06957v1","url_pdf":"https://arxiv.org/pdf/2003.06957v1.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":"frustratingly-simple-few-shot-object","repo_url":"https://github.com/ucbdrive/few-shot-object-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"frustratingly-simple-few-shot-object","repo_url":"https://github.com/MegviiDetection/FSCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"frustratingly-simple-few-shot-object","repo_url":"https://github.com/fsna2022/fsna","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"frustratingly-simple-few-shot-object","repo_url":"https://github.com/lexisnexis-risk-open-source/ledetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"frustratingly-simple-few-shot-object","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":"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":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"TFA w/cos","rank_in_archive_order":12,"of":16,"metrics":{" mAP":"14.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"TFA w/cos","rank_in_archive_order":10,"of":15,"metrics":{"mAP":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"TFA w/cos","rank_in_archive_order":11,"of":16,"metrics":{"mAP":"11.8"},"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":"TFA(w/cos)","rank_in_archive_order":27,"of":33,"metrics":{"AP":"10.0"},"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":"TFA(w/fc)","rank_in_archive_order":28,"of":33,"metrics":{"AP":"10.0"},"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":"TFA w/ cos","rank_in_archive_order":20,"of":25,"metrics":{"AP":"13.7"},"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":"TFA w/ fc","rank_in_archive_order":21,"of":25,"metrics":{"AP":"13.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.06957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06957"}},"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/ucbdrive/few-shot-object-detection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"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/fsna2022/fsna","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lexisnexis-risk-open-source/ledetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-research/fsce","reach":{"status":"unanswered"}}],"summary":{"ran":3,"unverified":8},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":8,"ran":3,"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":11,"samples":[{"code_sha256_prefix":"0df9d3b583fbc6cb","entry":"batched_nms","repo":"fsna2022/fsna","repo_kind":"listed","path":"fsdet/layers/nms.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/fsdet/layers/nms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0df9d3b583fbc6cb"}},{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"fsna2022/fsna","repo_kind":"listed","path":"fsdet/checkpoint/c2_model_loading.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/fsdet/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"52810b504f0d1066","entry":"convert_c2_detectron_names","repo":"fsna2022/fsna","repo_kind":"listed","path":"fsdet/checkpoint/c2_model_loading.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/fsdet/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"52810b504f0d1066"}},{"code_sha256_prefix":"4f2e083714266b7f","entry":"batched_nms_rotated","repo":"fsna2022/fsna","repo_kind":"listed","path":"fsdet/layers/nms.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/fsdet/layers/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4f2e083714266b7f"}},{"code_sha256_prefix":"4d2207f311202a82","entry":"get_checkpoint_url","repo":"ucbdrive/few-shot-object-detection","repo_kind":"official","path":"fsdet/model_zoo/model_zoo.py","file_url":"https://github.com/ucbdrive/few-shot-object-detection/blob/HEAD/fsdet/model_zoo/model_zoo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4d2207f311202a82"}},{"code_sha256_prefix":"2556b24697336491","entry":"get_config_file","repo":"ucbdrive/few-shot-object-detection","repo_kind":"official","path":"fsdet/model_zoo/model_zoo.py","file_url":"https://github.com/ucbdrive/few-shot-object-detection/blob/HEAD/fsdet/model_zoo/model_zoo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2556b24697336491"}},{"code_sha256_prefix":"38620a135673712c","entry":"get_last_conv_name","repo":"fsna2022/fsna","repo_kind":"listed","path":"demo/demo_cam.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/demo/demo_cam.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"38620a135673712c"}},{"code_sha256_prefix":"3bcacfe0d4442213","entry":"get_save_path_seeds","repo":"ucbdrive/few-shot-object-detection","repo_kind":"official","path":"datasets/prepare_coco_few_shot.py","file_url":"https://github.com/ucbdrive/few-shot-object-detection/blob/HEAD/datasets/prepare_coco_few_shot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3bcacfe0d4442213"}},{"code_sha256_prefix":"aad0696f7f4b3825","entry":"get_save_path_seeds","repo":"fsna2022/fsna","repo_kind":"listed","path":"datasets/prepare_coco_few_shot.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/datasets/prepare_coco_few_shot.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"aad0696f7f4b3825"}},{"code_sha256_prefix":"1c319eab8e23735d","entry":"nms_rotated","repo":"fsna2022/fsna","repo_kind":"listed","path":"fsdet/layers/nms.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/fsdet/layers/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1c319eab8e23735d"}},{"code_sha256_prefix":"98c9585c74cb0160","entry":"norm_image","repo":"fsna2022/fsna","repo_kind":"listed","path":"demo/demo_cam.py","file_url":"https://github.com/fsna2022/fsna/blob/HEAD/demo/demo_cam.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"98c9585c74cb0160"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}