{"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/lp-ovod-open-vocabulary-object-detection-by","title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","arxiv_id":"2310.17109","date":"2023-10-26","proceeding":null,"authors":["Chau Pham","Truong Vu","Khoi Nguyen"],"abstract":"This paper addresses the challenging problem of open-vocabulary object detection (OVOD) where an object detector must identify both seen and unseen classes in test images without labeled examples of the unseen classes in training. A typical approach for OVOD is to use joint text-image embeddings of CLIP to assign box proposals to their closest text label. However, this method has a critical issue: many low-quality boxes, such as over- and under-covered-object boxes, have the same similarity score as high-quality boxes since CLIP is not trained on exact object location information. To address this issue, we propose a novel method, LP-OVOD, that discards low-quality boxes by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text. Experimental results on COCO affirm the superior performance of our approach over the state of the art, achieving $\\textbf{40.5}$ in $\\text{AP}_{novel}$ using ResNet50 as the backbone and without external datasets or knowing novel classes during training. Our code will be available at https://github.com/VinAIResearch/LP-OVOD.","url_abs":"https://arxiv.org/abs/2310.17109v2","url_pdf":"https://arxiv.org/pdf/2310.17109v2.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":"lp-ovod-open-vocabulary-object-detection-by","repo_url":"https://github.com/vinairesearch/lp-ovod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"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":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"LP-OVOD (OWL-ViT Proposals)","rank_in_archive_order":6,"of":32,"metrics":{"AP 0.5":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"LP-OVOD","rank_in_archive_order":13,"of":32,"metrics":{"AP 0.5":"40.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.17109","atlas_url":"https://app.syntology.ai/?focus=2310.17109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17109"}},"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/vinairesearch/lp-ovod","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"7ad5f4a1df44b76c","entry":"article","repo":"vinairesearch/lp-ovod","repo_kind":"official","path":"prepare/clip_utils.py","file_url":"https://github.com/vinairesearch/lp-ovod/blob/HEAD/prepare/clip_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7ad5f4a1df44b76c"}},{"code_sha256_prefix":"0fa78bdf28e34455","entry":"processed_name","repo":"vinairesearch/lp-ovod","repo_kind":"official","path":"prepare/clip_utils.py","file_url":"https://github.com/vinairesearch/lp-ovod/blob/HEAD/prepare/clip_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0fa78bdf28e34455"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}