{"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/partglee-a-foundation-model-for-recognizing","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","arxiv_id":"2407.16696","date":"2024-07-23","proceeding":null,"authors":["Junyi Li","Junfeng Wu","Weizhi Zhao","Song Bai","Xiang Bai"],"abstract":"We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segmentation, and grounding of instances at any granularity in the open world scenario. Specifically, we propose a Q-Former to construct the hierarchical relationship between objects and parts, parsing every object into corresponding semantic parts. By incorporating a large amount of object-level data, the hierarchical relationships can be extended, enabling PartGLEE to recognize a rich variety of parts. We conduct comprehensive studies to validate the effectiveness of our method, PartGLEE achieves the state-of-the-art performance across various part-level tasks and obtain competitive results on object-level tasks. The proposed PartGLEE significantly enhances hierarchical modeling capabilities and part-level perception over our previous GLEE model. Further analysis indicates that the hierarchical cognitive ability of PartGLEE is able to facilitate a detailed comprehension in images for mLLMs. The model and code will be released at https://provencestar.github.io/PartGLEE-Vision/ .","url_abs":"https://arxiv.org/abs/2407.16696v1","url_pdf":"https://arxiv.org/pdf/2407.16696v1.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":"partglee-a-foundation-model-for-recognizing","repo_url":"https://github.com/ProvenceStar/PartGLEE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.16696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16696"}},"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/ProvenceStar/PartGLEE","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":"95771c1a2d8346b7","entry":"agg_lang_feat","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/PartGLEE_Model.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/PartGLEE_Model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95771c1a2d8346b7"}},{"code_sha256_prefix":"0a459f2a34c97b68","entry":"all_gather_grad","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/language/loss.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/language/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a459f2a34c97b68"}},{"code_sha256_prefix":"670bf62deb1d06af","entry":"load_opt_from_config_files","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/train_net.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/train_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"670bf62deb1d06af"}},{"code_sha256_prefix":"130323eef819c472","entry":"rand_sample","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/PartGLEE_Model.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/PartGLEE_Model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"130323eef819c472"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/criterion.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/criterion.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"dd39a2e351222354","entry":"vl_contrastive_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/language/loss.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/language/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd39a2e351222354"}},{"code_sha256_prefix":"beb800ea8ce01e03","entry":"vl_multilabel_contrastive_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/language/loss.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/language/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"beb800ea8ce01e03"}},{"code_sha256_prefix":"bc2cb481a75c370d","entry":"batch_dice_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/matcher.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc2cb481a75c370d"}},{"code_sha256_prefix":"1edd24985036b0bf","entry":"batch_sigmoid_ce_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/matcher.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/matcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1edd24985036b0bf"}},{"code_sha256_prefix":"89f75e54ff128be0","entry":"dice_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/criterion.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"89f75e54ff128be0"}},{"code_sha256_prefix":"d0c61e8dba511aa3","entry":"sigmoid_ce_loss","repo":"ProvenceStar/PartGLEE","repo_kind":"official","path":"projects/PartGLEE/partglee/models/criterion.py","file_url":"https://github.com/ProvenceStar/PartGLEE/blob/HEAD/projects/PartGLEE/partglee/models/criterion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0c61e8dba511aa3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}