{"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/cross-domain-few-shot-object-detection-via","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector","arxiv_id":"2402.03094","date":"2024-02-05","proceeding":null,"authors":["Yuqian Fu","Yu Wang","Yixuan Pan","Lian Huai","Xingyu Qiu","Zeyu Shangguan","Tong Liu","Yanwei Fu","Luc van Gool","Xingqun Jiang"],"abstract":"This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundaries (IB) to understand the domain gap. Based on these measures, we establish a new benchmark named CD-FSOD to evaluate object detection methods, revealing that most of the current approaches fail to generalize across domains. Technically, we observe that the performance decline is associated with our proposed measures: style, ICV, and IB. Consequently, we propose several novel modules to address these issues. First, the learnable instance features align initial fixed instances with target categories, enhancing feature distinctiveness. Second, the instance reweighting module assigns higher importance to high-quality instances with slight IB. Third, the domain prompter encourages features resilient to different styles by synthesizing imaginary domains without altering semantic contents. These techniques collectively contribute to the development of the Cross-Domain Vision Transformer for CD-FSOD (CD-ViTO), significantly improving upon the base DE-ViT. Experimental results validate the efficacy of our model.","url_abs":"https://arxiv.org/abs/2402.03094v4","url_pdf":"https://arxiv.org/pdf/2402.03094v4.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":"cross-domain-few-shot-object-detection-via","repo_url":"https://github.com/lovelyqian/CDFSOD-benchmark","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cross-domain-few-shot-object-detection-via","repo_url":"https://github.com/LONGXUANX/CDFormer_code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"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":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"CD-ViTO","rank_in_archive_order":3,"of":16,"metrics":{" mAP":"60.5"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"CD-ViTO","rank_in_archive_order":4,"of":10,"metrics":{" mAP":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"CD-ViTO","rank_in_archive_order":4,"of":15,"metrics":{"mAP":"30.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"CD-ViTO","rank_in_archive_order":5,"of":10,"metrics":{"mAP":"22.3"},"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":"CD-ViTO","rank_in_archive_order":5,"of":10,"metrics":{"mAP":"12.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"CD-ViTO","rank_in_archive_order":13,"of":16,"metrics":{"mAP":"7.0"},"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":"CD-ViTO","rank_in_archive_order":2,"of":33,"metrics":{"AP":"35.3"},"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":"CD-ViTO","rank_in_archive_order":2,"of":25,"metrics":{"AP":"35.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.03094","atlas_url":"https://app.syntology.ai/?focus=2402.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03094"}},"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/lovelyqian/CDFSOD-benchmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LONGXUANX/CDFormer_code","reach":null}],"summary":{"ran":9,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/regionprop.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":"009912c75c8c77cf"}},{"code_sha256_prefix":"88d32e10c27e7a12","entry":"box_xyxy_clamp","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/regionprop.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":"88d32e10c27e7a12"}},{"code_sha256_prefix":"db78cfc20095f3a8","entry":"box_xyxy_to_cxcywh","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"lib/regionprop.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/regionprop.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":"db78cfc20095f3a8"}},{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"7b7f6e4aa28b1a69","entry":"convert_basic_clip_names","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b7f6e4aa28b1a69"}},{"code_sha256_prefix":"e36f87059208bb7e","entry":"convert_c2_detectron_names","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e36f87059208bb7e"}},{"code_sha256_prefix":"376248f5d186a885","entry":"convert_clip_names","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"376248f5d186a885"}},{"code_sha256_prefix":"9d4bd1f443b65407","entry":"mask_sinkhorn","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"lib/prototype_learner.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/prototype_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d4bd1f443b65407"}},{"code_sha256_prefix":"f8c7f9605872c11b","entry":"sinkhorn","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"lib/prototype_learner.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/blob/HEAD/lib/prototype_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8c7f9605872c11b"}},{"code_sha256_prefix":"ac2638463572c152","entry":"align_and_update_state_dicts","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac2638463572c152"}},{"code_sha256_prefix":"0bd7b0a60b4069f9","entry":"align_and_update_state_dicts_for_CLIP","repo":"lovelyqian/CDFSOD-benchmark","repo_kind":"official","path":"detectron2/checkpoint/clip_model_loading.py","file_url":"https://github.com/lovelyqian/CDFSOD-benchmark/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0bd7b0a60b4069f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}