{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/detecting-twenty-thousand-classes-using-image","title":"Detecting Twenty-thousand Classes using Image-level Supervision","arxiv_id":"2201.02605","date":"2022-01-07","proceeding":null,"authors":["Xingyi Zhou","Rohit Girdhar","Armand Joulin","Philipp Krähenbühl","Ishan Misra"],"abstract":"Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as their datasets are larger and easier to collect. We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts. Unlike prior work, Detic does not need complex assignment schemes to assign image labels to boxes based on model predictions, making it much easier to implement and compatible with a range of detection architectures and backbones. Our results show that Detic yields excellent detectors even for classes without box annotations. It outperforms prior work on both open-vocabulary and long-tail detection benchmarks. Detic provides a gain of 2.4 mAP for all classes and 8.3 mAP for novel classes on the open-vocabulary LVIS benchmark. On the standard LVIS benchmark, Detic obtains 41.7 mAP when evaluated on all classes, or only rare classes, hence closing the gap in performance for object categories with few samples. For the first time, we train a detector with all the twenty-one-thousand classes of the ImageNet dataset and show that it generalizes to new datasets without finetuning. Code is available at \\url{https://github.com/facebookresearch/Detic}.","url_abs":"https://arxiv.org/abs/2201.02605v3","url_pdf":"https://arxiv.org/pdf/2201.02605v3.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":"detecting-twenty-thousand-classes-using-image","repo_url":"https://github.com/facebookresearch/Detic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cross-domain-few-shot-object-detection","task_name":"Cross-Domain Few-Shot Object Detection"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"Detic-FT","rank_in_archive_order":14,"of":16,"metrics":{" mAP":"12.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on","task":"Cross-Domain Few-Shot Object Detection","dataset":"Artaxor","model":"Detic(w/o FT)","rank_in_archive_order":16,"of":16,"metrics":{" mAP":"0.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"Detic-FT","rank_in_archive_order":8,"of":10,"metrics":{" mAP":"22.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-1","task":"Cross-Domain Few-Shot Object Detection","dataset":"Clipark1k","model":"Detic(w/o FT)","rank_in_archive_order":9,"of":10,"metrics":{" mAP":"11.4"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"Detic-FT","rank_in_archive_order":12,"of":15,"metrics":{"mAP":"15.4"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-2","task":"Cross-Domain Few-Shot Object Detection","dataset":"DIOR","model":"Detic(w/o FT)","rank_in_archive_order":15,"of":15,"metrics":{"mAP":"0.1"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"Detic-FT","rank_in_archive_order":7,"of":10,"metrics":{"mAP":"17.9"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-3","task":"Cross-Domain Few-Shot Object Detection","dataset":"DeepFish","model":"Detic(w/o FT)","rank_in_archive_order":10,"of":10,"metrics":{"mAP":"0.9"},"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":"Detic-FT","rank_in_archive_order":3,"of":10,"metrics":{"mAP":"16.8"},"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":"Detic(w/o FT)","rank_in_archive_order":10,"of":10,"metrics":{"mAP":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"Detic-FT","rank_in_archive_order":5,"of":16,"metrics":{"mAP":"16.8"},"uses_additional_data":false},{"leaderboard":"/sota/cross-domain-few-shot-object-detection-on-4","task":"Cross-Domain Few-Shot Object Detection","dataset":"UODD","model":"Detic(w/o FT)","rank_in_archive_order":16,"of":16,"metrics":{"mAP":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"Detic","rank_in_archive_order":25,"of":28,"metrics":{"AP novel-LVIS base training":"17.8"},"uses_additional_data":true},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"Detic","rank_in_archive_order":28,"of":32,"metrics":{"AP 0.5":"27.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on","task":"Open Vocabulary Object Detection","dataset":"OpenImages-v4","model":"Detic","rank_in_archive_order":2,"of":2,"metrics":{"AP 0.5":"42.2","mask AP50":"42.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.02605","atlas_url":"https://app.syntology.ai/?focus=2201.02605","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2201.02605"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.02605\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.02605"},"call":"get_concepts_for_paper(arxiv_id=\"2201.02605\")"}],"by_repo":[{"repo":"facebookresearch/Detic","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.10659"],"harvested_for_calls":[{"arxiv_id":"2410.10659","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.10659"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.10659\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0e5b10482f60e06ce6d4b1ad65900f7ea7ac4a70155440fa7e695c8fc286482d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}