{"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/understanding-multi-granularity-for-open","title":"Understanding Multi-Granularity for Open-Vocabulary Part Segmentation","arxiv_id":"2406.11384","date":"2024-06-17","proceeding":null,"authors":["Jiho Choi","Seonho Lee","Seungho Lee","Minhyun Lee","Hyunjung Shim"],"abstract":"Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies. Our study highlights the inherent complexities of part segmentation due to intricate boundaries and diverse granularity, reflecting the knowledge-based nature of part identification. To address these challenges, we propose PartCLIPSeg, a novel framework utilizing generalized parts and object-level contexts to mitigate the lack of generalization in fine-grained parts. PartCLIPSeg integrates competitive part relationships and attention control, alleviating ambiguous boundaries and underrepresented parts. Experimental results demonstrate that PartCLIPSeg outperforms existing state-of-the-art OVPS methods, offering refined segmentation and an advanced understanding of part relationships within images. Through extensive experiments, our model demonstrated a significant improvement over the state-of-the-art models on the Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets.","url_abs":"https://arxiv.org/abs/2406.11384v3","url_pdf":"https://arxiv.org/pdf/2406.11384v3.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":"understanding-multi-granularity-for-open","repo_url":"https://github.com/kaist-cvml-lab/part-clipseg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"understanding-multi-granularity-for-open","repo_url":"https://github.com/kaist-cvml/part-clipseg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"open-vocabulary-semantic-segmentation-1","task_name":"Open-Vocabulary Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.11384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11384"}},"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/kaist-cvml/part-clipseg","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaist-cvml-lab/part-clipseg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":15,"ran":11,"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":"41b007e677e02ece","entry":"clipseg_loss","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/models/clipseg/modeling_clipseg.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/modeling_clipseg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41b007e677e02ece"}},{"code_sha256_prefix":"4675779aec92d6c0","entry":"contrastive_loss","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/models/clipseg/modeling_clipseg.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/modeling_clipseg.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"code_sha256_prefix":"5168a172bbb363a5","entry":"convert_pytorch_state_dict_to_flax","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/modeling_flax_pytorch_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5168a172bbb363a5"}},{"code_sha256_prefix":"7f278ee4020690d8","entry":"convert_state_dict","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f278ee4020690d8"}},{"code_sha256_prefix":"3677a1331007ac04","entry":"get_clipseg_config","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3677a1331007ac04"}},{"code_sha256_prefix":"dd8f7751ef859581","entry":"infer_metric_tags_from_eval_results","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/modelcard.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd8f7751ef859581"}},{"code_sha256_prefix":"26175e73e7041e86","entry":"load_imagenet_labels","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"datasets/partimagenet_preprocess.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/datasets/partimagenet_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26175e73e7041e86"}},{"code_sha256_prefix":"a4491b45d19b7a39","entry":"parse_keras_history","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/modelcard.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4491b45d19b7a39"}},{"code_sha256_prefix":"ee588a4e50fa1acd","entry":"preprocess_partimagenet","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"datasets/partimagenet_preprocess.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/datasets/partimagenet_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee588a4e50fa1acd"}},{"code_sha256_prefix":"f58ed61ea5ae630b","entry":"rename_key","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f58ed61ea5ae630b"}},{"code_sha256_prefix":"61779b0406a59cfc","entry":"rename_key_and_reshape_tensor","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/modeling_flax_pytorch_utils.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/modeling_flax_pytorch_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61779b0406a59cfc"}},{"code_sha256_prefix":"f4075cdecbb730c5","entry":"check_imports","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4075cdecbb730c5"}},{"code_sha256_prefix":"00cc853a73f3aeb6","entry":"get_relative_import_files","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00cc853a73f3aeb6"}},{"code_sha256_prefix":"450aeffe7f80f917","entry":"get_relative_imports","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/dynamic_module_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"450aeffe7f80f917"}},{"code_sha256_prefix":"ec7b1528a936234d","entry":"is_hf_dataset","repo":"kaist-cvml-lab/part-clipseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml-lab/part-clipseg/blob/HEAD/transformers/modelcard.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec7b1528a936234d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}