{"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/llmdet-learning-strong-open-vocabulary-object","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","arxiv_id":"2501.18954","date":"2025-01-31","proceeding":"CVPR 2025 1","authors":["Shenghao Fu","Qize Yang","Qijie Mo","Junkai Yan","Xihan Wei","Jingke Meng","Xiaohua Xie","Wei-Shi Zheng"],"abstract":"Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://github.com/iSEE-Laboratory/LLMDet.","url_abs":"https://arxiv.org/abs/2501.18954v1","url_pdf":"https://arxiv.org/pdf/2501.18954v1.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":"llmdet-learning-strong-open-vocabulary-object","repo_url":"https://github.com/isee-laboratory/llmdet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.18954","atlas_url":"https://app.syntology.ai/?focus=2501.18954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18954"}},"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/isee-laboratory/llmdet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/iSEE-Laboratory/LLMDet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"d23bffc29f903730","entry":"build_position_encoding","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/modeling_grounding_dino.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/modeling_grounding_dino.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":false,"mcp_get_code":{"code_sha256":"d23bffc29f903730"}},{"code_sha256_prefix":"efe1bd8c76f379b2","entry":"convert","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/mmdet2groundingdino_swinb.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/mmdet2groundingdino_swinb.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":false,"mcp_get_code":{"code_sha256":"efe1bd8c76f379b2"}},{"code_sha256_prefix":"c46ca7d3f1ac011c","entry":"convert","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/mmdet2groundingdino_swinl.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/mmdet2groundingdino_swinl.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":false,"mcp_get_code":{"code_sha256":"c46ca7d3f1ac011c"}},{"code_sha256_prefix":"15f1a18a67bb2717","entry":"convert","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/mmdet2groundingdino_swint.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/mmdet2groundingdino_swint.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":false,"mcp_get_code":{"code_sha256":"15f1a18a67bb2717"}},{"code_sha256_prefix":"bfe48aa05b77c044","entry":"correct_unfold_norm_order","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/mmdet2groundingdino_swinb.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/mmdet2groundingdino_swinb.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":false,"mcp_get_code":{"code_sha256":"bfe48aa05b77c044"}},{"code_sha256_prefix":"0e17e0caa4296807","entry":"correct_unfold_reduction_order","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/mmdet2groundingdino_swinb.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/mmdet2groundingdino_swinb.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":false,"mcp_get_code":{"code_sha256":"0e17e0caa4296807"}},{"code_sha256_prefix":"b6822336792e87db","entry":"drop_path","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/modeling_grounding_dino.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/modeling_grounding_dino.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":false,"mcp_get_code":{"code_sha256":"b6822336792e87db"}},{"code_sha256_prefix":"dd825809bb047f90","entry":"get_grounding_dino_config","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/convert_grounding_dino_to_hf.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/convert_grounding_dino_to_hf.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":false,"mcp_get_code":{"code_sha256":"dd825809bb047f90"}},{"code_sha256_prefix":"a33b07b3d99cefd1","entry":"multi_scale_deformable_attention","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/modeling_grounding_dino.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/modeling_grounding_dino.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":false,"mcp_get_code":{"code_sha256":"a33b07b3d99cefd1"}},{"code_sha256_prefix":"112e742f763af291","entry":"preprocess_caption","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/convert_grounding_dino_to_hf.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/convert_grounding_dino_to_hf.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":false,"mcp_get_code":{"code_sha256":"112e742f763af291"}},{"code_sha256_prefix":"2a19105a1a733f72","entry":"create_rename_keys","repo":"iSEE-Laboratory/LLMDet","repo_kind":"official","path":"hf_model/convert_grounding_dino_to_hf.py","file_url":"https://github.com/iSEE-Laboratory/LLMDet/blob/HEAD/hf_model/convert_grounding_dino_to_hf.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":false,"mcp_get_code":{"code_sha256":"2a19105a1a733f72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}