{"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/v3det-vast-vocabulary-visual-detection","title":"V3Det: Vast Vocabulary Visual Detection Dataset","arxiv_id":"2304.03752","date":"2023-04-07","proceeding":"ICCV 2023 1","authors":["Jiaqi Wang","Pan Zhang","Tao Chu","Yuhang Cao","Yujie Zhou","Tong Wu","Bin Wang","Conghui He","Dahua Lin"],"abstract":"Recent advances in detecting arbitrary objects in the real world are trained and evaluated on object detection datasets with a relatively restricted vocabulary. To facilitate the development of more general visual object detection, we propose V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images. V3Det has several appealing properties: 1) Vast Vocabulary: It contains bounding boxes of objects from 13,204 categories on real-world images, which is 10 times larger than the existing large vocabulary object detection dataset, e.g., LVIS. 2) Hierarchical Category Organization: The vast vocabulary of V3Det is organized by a hierarchical category tree which annotates the inclusion relationship among categories, encouraging the exploration of category relationships in vast and open vocabulary object detection. 3) Rich Annotations: V3Det comprises precisely annotated objects in 243k images and professional descriptions of each category written by human experts and a powerful chatbot. By offering a vast exploration space, V3Det enables extensive benchmarks on both vast and open vocabulary object detection, leading to new observations, practices, and insights for future research. It has the potential to serve as a cornerstone dataset for developing more general visual perception systems. V3Det is available at https://v3det.openxlab.org.cn/.","url_abs":"https://arxiv.org/abs/2304.03752v2","url_pdf":"https://arxiv.org/pdf/2304.03752v2.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":"v3det-vast-vocabulary-visual-detection","repo_url":"https://github.com/V3Det/Detectron2-V3Det","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"chatbot","task_name":"Chatbot"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.03752","atlas_url":"https://app.syntology.ai/?focus=2304.03752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03752"}},"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/V3Det/Detectron2-V3Det","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_fixture":2,"unverified":3},"by_repo_kind":{"listed":{"samples":11,"ran":8,"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":"d7527a665dfb8f27","entry":"batched_nms","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/nms.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/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":true,"mcp_get_code":{"code_sha256":"d7527a665dfb8f27"}},{"code_sha256_prefix":"cee8870d4fbccc39","entry":"ciou_loss","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/losses.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/layers/losses.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cee8870d4fbccc39"}},{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/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":"e36f87059208bb7e","entry":"convert_c2_detectron_names","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/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":"26f3066ead0d2eec","entry":"diou_loss","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/losses.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/layers/losses.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26f3066ead0d2eec"}},{"code_sha256_prefix":"406f84cf799ed34d","entry":"pad_masks","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","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":"406f84cf799ed34d"}},{"code_sha256_prefix":"d03592674030077f","entry":"paste_mask_in_image_old","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/layers/mask_ops.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":"d03592674030077f"}},{"code_sha256_prefix":"c0eac7dcd1335fa1","entry":"paste_masks_in_image","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/layers/mask_ops.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":"c0eac7dcd1335fa1"}},{"code_sha256_prefix":"ac2638463572c152","entry":"align_and_update_state_dicts","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/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":"627f9dec92f2462b","entry":"batched_nms_rotated","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/nms.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/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":true,"mcp_get_code":{"code_sha256":"627f9dec92f2462b"}},{"code_sha256_prefix":"d15c7cc7a28e4a67","entry":"nms_rotated","repo":"V3Det/Detectron2-V3Det","repo_kind":"listed","path":"detectron2/layers/nms.py","file_url":"https://github.com/V3Det/Detectron2-V3Det/blob/HEAD/detectron2/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":true,"mcp_get_code":{"code_sha256":"d15c7cc7a28e4a67"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}