{"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/detect-every-thing-with-few-examples","title":"Detect Everything with Few Examples","arxiv_id":"2309.12969","date":"2023-09-22","proceeding":null,"authors":["Xinyu Zhang","YuHan Liu","Yuting Wang","Abdeslam Boularias"],"abstract":"Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototype classifiers, we propose to use prototypes to project ViT features into a subspace that is robust to overfitting on base classes. We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS. DE-ViT establishes new state-of-the-art results on all benchmarks. Notably, for COCO, DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms few-shot SoTA by 17 box APr. Further, we evaluate DE-ViT with a real robot by building a pick-and-place system for sorting novel objects based on example images. The videos of our robot demonstrations, the source code and the models of DE-ViT can be found at https://mlzxy.github.io/devit.","url_abs":"https://arxiv.org/abs/2309.12969v4","url_pdf":"https://arxiv.org/pdf/2309.12969v4.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":"detect-every-thing-with-few-examples","repo_url":"https://github.com/mlzxy/devit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary 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","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"one-shot-object-detection","task_name":"One-Shot Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"DE-ViT-FT","rank_in_archive_order":6,"of":16,"metrics":{" mAP":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"DE-ViT(w/o FT)","rank_in_archive_order":15,"of":16,"metrics":{" mAP":"9.2"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"DE-ViT-FT","rank_in_archive_order":5,"of":10,"metrics":{" mAP":"40.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"DE-ViT(w/o FT)","rank_in_archive_order":10,"of":10,"metrics":{" mAP":"11.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"DE-ViT-FT","rank_in_archive_order":6,"of":15,"metrics":{"mAP":"25.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"DE-ViT(w/o FT)","rank_in_archive_order":13,"of":15,"metrics":{"mAP":"8.4"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"DE-ViT-FT","rank_in_archive_order":6,"of":10,"metrics":{"mAP":"21.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"DE-ViT(w/o FT)","rank_in_archive_order":9,"of":10,"metrics":{"mAP":"2.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-neu","task":"Cross-Domain Few-Shot Object Detection","dataset":"NEU-DET","model":"DE-ViT-FT","rank_in_archive_order":6,"of":10,"metrics":{"mAP":"8.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-neu","task":"Cross-Domain Few-Shot Object Detection","dataset":"NEU-DET","model":"DE-ViT(w/o FT)","rank_in_archive_order":9,"of":10,"metrics":{"mAP":"1.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"DE-ViT-FT","rank_in_archive_order":14,"of":16,"metrics":{"mAP":"5.4"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"DE-ViT(w/o FT)","rank_in_archive_order":15,"of":16,"metrics":{"mAP":"3.1"},"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":"DE-ViT","rank_in_archive_order":3,"of":33,"metrics":{"AP":"34.0"},"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":"DE-ViT","rank_in_archive_order":3,"of":25,"metrics":{"AP":"34"},"uses_additional_data":false},{"leaderboard":"/sota/one-shot-object-detection-on-coco","task":"One-Shot Object Detection","dataset":"COCO (Common Objects in Context)","model":"DE-ViT","rank_in_archive_order":2,"of":4,"metrics":{"AP 0.5":"28.4"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"DE-ViT","rank_in_archive_order":7,"of":28,"metrics":{"AP novel-LVIS base training":"34.3"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"DE-ViT","rank_in_archive_order":2,"of":32,"metrics":{"AP 0.5":"50"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.12969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12969"}},"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/mlzxy/devit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":15,"unverified":5},"by_repo_kind":{"official":{"samples":20,"ran":15,"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":"009912c75c8c77cf","entry":"box_cxcywh_to_xyxy","repo":"mlzxy/devit","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/regionprop.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"009912c75c8c77cf"}},{"code_sha256_prefix":"88d32e10c27e7a12","entry":"box_xyxy_clamp","repo":"mlzxy/devit","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/regionprop.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88d32e10c27e7a12"}},{"code_sha256_prefix":"db78cfc20095f3a8","entry":"box_xyxy_to_cxcywh","repo":"mlzxy/devit","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/regionprop.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db78cfc20095f3a8"}},{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"7b7f6e4aa28b1a69","entry":"convert_basic_clip_names","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/checkpoint/clip_model_loading.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":"7b7f6e4aa28b1a69"}},{"code_sha256_prefix":"e36f87059208bb7e","entry":"convert_c2_detectron_names","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e36f87059208bb7e"}},{"code_sha256_prefix":"376248f5d186a885","entry":"convert_clip_names","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/checkpoint/clip_model_loading.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":"376248f5d186a885"}},{"code_sha256_prefix":"1bec3241f0f82f89","entry":"elementwise_box_iou","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1bec3241f0f82f89"}},{"code_sha256_prefix":"761e870ed51af37c","entry":"generalized_box_iou","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit_update.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit_update.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"761e870ed51af37c"}},{"code_sha256_prefix":"a38f5f94b0a19b1b","entry":"interpolate","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit.py","link_basis":"first_harvest_node","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":"a38f5f94b0a19b1b"}},{"code_sha256_prefix":"9d4bd1f443b65407","entry":"mask_sinkhorn","repo":"mlzxy/devit","repo_kind":"official","path":"lib/prototype_learner.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/prototype_learner.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":"9d4bd1f443b65407"}},{"code_sha256_prefix":"2e81e6f4cd544f1b","entry":"parse_rec","repo":"mlzxy/devit","repo_kind":"official","path":"lib/voc_eval.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/voc_eval.py","link_basis":"first_harvest_node","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":"2e81e6f4cd544f1b"}},{"code_sha256_prefix":"847c0c0c48d84c9e","entry":"sigmoid_ce_loss","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit_update.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit_update.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"847c0c0c48d84c9e"}},{"code_sha256_prefix":"f8c7f9605872c11b","entry":"sinkhorn","repo":"mlzxy/devit","repo_kind":"official","path":"lib/prototype_learner.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/prototype_learner.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":"f8c7f9605872c11b"}},{"code_sha256_prefix":"a6d455c6f04f93d3","entry":"voc_eval","repo":"mlzxy/devit","repo_kind":"official","path":"lib/voc_eval.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/voc_eval.py","link_basis":"first_harvest_node","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":"a6d455c6f04f93d3"}},{"code_sha256_prefix":"ac2638463572c152","entry":"align_and_update_state_dicts","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/checkpoint/c2_model_loading.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":"ac2638463572c152"}},{"code_sha256_prefix":"0bd7b0a60b4069f9","entry":"align_and_update_state_dicts_for_CLIP","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/checkpoint/clip_model_loading.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":"0bd7b0a60b4069f9"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit_update.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit_update.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":"89f75e54ff128be0"}},{"code_sha256_prefix":"bfc4e32519b5ef25","entry":"generalized_box_iou","repo":"mlzxy/devit","repo_kind":"official","path":"detectron2/modeling/meta_arch/devit.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/detectron2/modeling/meta_arch/devit.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":"bfc4e32519b5ef25"}},{"code_sha256_prefix":"611c47c44c424dba","entry":"voc_ap","repo":"mlzxy/devit","repo_kind":"official","path":"lib/voc_eval.py","file_url":"https://github.com/mlzxy/devit/blob/HEAD/lib/voc_eval.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":"611c47c44c424dba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}