{"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/an-open-and-comprehensive-pipeline-for","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","arxiv_id":"2401.02361","date":"2024-01-04","proceeding":null,"authors":["Xiangyu Zhao","Yicheng Chen","Shilin Xu","Xiangtai Li","Xinjiang Wang","Yining Li","Haian Huang"],"abstract":"Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, which is built with the MMDetection toolbox. It adopts abundant vision datasets for pre-training and various detection and grounding datasets for fine-tuning. We give a comprehensive analysis of each reported result and detailed settings for reproduction. The extensive experiments on the benchmarks mentioned demonstrate that our MM-Grounding-DINO-Tiny outperforms the Grounding-DINO-Tiny baseline. We release all our models to the research community. Codes and trained models are released at https://github.com/open-mmlab/mmdetection/tree/main/configs/mm_grounding_dino.","url_abs":"https://arxiv.org/abs/2401.02361v2","url_pdf":"https://arxiv.org/pdf/2401.02361v2.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":"an-open-and-comprehensive-pipeline-for","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"an-open-and-comprehensive-pipeline-for","repo_url":"https://github.com/cszzshi/SimD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"described-object-detection","task_name":"Described Object Detection"},{"task_slug":"phrase-grounding","task_name":"Phrase Grounding"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/described-object-detection-on-description","task":"Described Object Detection","dataset":"Description Detection Dataset","model":"MM-Grounding-DINO","rank_in_archive_order":1,"of":8,"metrics":{"Intra-scenario ABS mAP":"26.0","Intra-scenario FULL mAP":"22.9","Intra-scenario PRES mAP":"21.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.02361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02361"}},"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/cszzshi/SimD","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":4,"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":"4e2dcdfe578946a0","entry":"check_link","repo":"open-mmlab/mmdetection","repo_kind":"official","path":".dev_scripts/check_links.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/.dev_scripts/check_links.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":"4e2dcdfe578946a0"}},{"code_sha256_prefix":"cc93fdc812eca8f7","entry":"check_url","repo":"open-mmlab/mmdetection","repo_kind":"official","path":".dev_scripts/check_links.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/.dev_scripts/check_links.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":"cc93fdc812eca8f7"}},{"code_sha256_prefix":"ae58b0731b1c3074","entry":"json_load","repo":"open-mmlab/mmdetection","repo_kind":"official","path":"projects/LabelStudio/backend_template/mmdetection.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/projects/LabelStudio/backend_template/mmdetection.py","link_basis":"first_harvest_node","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":"ae58b0731b1c3074"}},{"code_sha256_prefix":"3175ca3b1ec8c7b9","entry":"process_model_info","repo":"open-mmlab/mmdetection","repo_kind":"official","path":".dev_scripts/convert_test_benchmark_script.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/.dev_scripts/convert_test_benchmark_script.py","link_basis":"first_harvest_node","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":"3175ca3b1ec8c7b9"}},{"code_sha256_prefix":"fd08138d4bde9cfa","entry":"check_path","repo":"open-mmlab/mmdetection","repo_kind":"official","path":".dev_scripts/check_links.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/.dev_scripts/check_links.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":"fd08138d4bde9cfa"}},{"code_sha256_prefix":"8ff99a6bd2ebf598","entry":"ordered_yaml_dump","repo":"open-mmlab/mmdetection","repo_kind":"official","path":".dev_scripts/gather_models.py","file_url":"https://github.com/open-mmlab/mmdetection/blob/HEAD/.dev_scripts/gather_models.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":"8ff99a6bd2ebf598"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}