{"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/described-object-detection-liberating-object-1","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","arxiv_id":"2307.12813","date":"2023-07-24","proceeding":"NeurIPS 2023 11","authors":["Chi Xie","Zhao Zhang","Yixuan Wu","Feng Zhu","Rui Zhao","Shuang Liang"],"abstract":"Detecting objects based on language information is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper, we advance them to a more practical setting called Described Object Detection (DOD) by expanding category names to flexible language expressions for OVD and overcoming the limitation of REC only grounding the pre-existing object. We establish the research foundation for DOD by constructing a Description Detection Dataset ($D^3$). This dataset features flexible language expressions, whether short category names or long descriptions, and annotating all described objects on all images without omission. By evaluating previous SOTA methods on $D^3$, we find some troublemakers that fail current REC, OVD, and bi-functional methods. REC methods struggle with confidence scores, rejecting negative instances, and multi-target scenarios, while OVD methods face constraints with long and complex descriptions. Recent bi-functional methods also do not work well on DOD due to their separated training procedures and inference strategies for REC and OVD tasks. Building upon the aforementioned findings, we propose a baseline that largely improves REC methods by reconstructing the training data and introducing a binary classification sub-task, outperforming existing methods. Data and code are available at https://github.com/shikras/d-cube and related works are tracked in https://github.com/Charles-Xie/awesome-described-object-detection.","url_abs":"https://arxiv.org/abs/2307.12813v2","url_pdf":"https://arxiv.org/pdf/2307.12813v2.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":"described-object-detection-liberating-object-1","repo_url":"https://github.com/shikras/d-cube","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"described-object-detection","task_name":"Described 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":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/described-object-detection-on-description","task":"Described Object Detection","dataset":"Description Detection Dataset","model":"OFA-DOD-base","rank_in_archive_order":3,"of":8,"metrics":{"Intra-scenario ABS mAP":"15.4","Intra-scenario FULL mAP":"21.6","Intra-scenario PRES mAP":"23.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.12813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12813"}},"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/shikras/d-cube","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"d953ab774e3aaae0","entry":"convert_to_xywh","repo":"shikras/d-cube","repo_kind":"official","path":"scripts/eval_and_analysis_json.py","file_url":"https://github.com/shikras/d-cube/blob/HEAD/scripts/eval_and_analysis_json.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d953ab774e3aaae0"}},{"code_sha256_prefix":"c4f8858612f7d6d3","entry":"transform_json_boxes","repo":"shikras/d-cube","repo_kind":"official","path":"scripts/eval_and_analysis_json.py","file_url":"https://github.com/shikras/d-cube/blob/HEAD/scripts/eval_and_analysis_json.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c4f8858612f7d6d3"}},{"code_sha256_prefix":"755a67b8317caf1a","entry":"nbox_partition_json","repo":"shikras/d-cube","repo_kind":"official","path":"scripts/eval_and_analysis_json.py","file_url":"https://github.com/shikras/d-cube/blob/HEAD/scripts/eval_and_analysis_json.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"755a67b8317caf1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}