{"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/fine-grained-image-text-correspondence-with","title":"Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation","arxiv_id":"2501.09688","date":"2025-01-16","proceeding":"CVPR 2025 1","authors":["Jiho Choi","Seonho Lee","Minhyun Lee","Seungho Lee","Hyunjung Shim"],"abstract":"Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficulty in aligning part-level image-text correspondence, and (2) the lack of structural understanding in segmenting object parts. To address these issues, we propose PartCATSeg, a novel framework that integrates object-aware part-level cost aggregation, compositional loss, and structural guidance from DINO. Our approach employs a disentangled cost aggregation strategy that handles object and part-level costs separately, enhancing the precision of part-level segmentation. We also introduce a compositional loss to better capture part-object relationships, compensating for the limited part annotations. Additionally, structural guidance from DINO features improves boundary delineation and inter-part understanding. Extensive experiments on Pascal-Part-116, ADE20K-Part-234, and PartImageNet datasets demonstrate that our method significantly outperforms state-of-the-art approaches, setting a new baseline for robust generalization to unseen part categories.","url_abs":"https://arxiv.org/abs/2501.09688v1","url_pdf":"https://arxiv.org/pdf/2501.09688v1.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":"fine-grained-image-text-correspondence-with","repo_url":"https://github.com/kaist-cvml/part-catseg","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"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.09688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.09688"}},"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-catseg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":5,"ran_fixture":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":0,"samples":[{"code_sha256_prefix":"0d5505bd782b4a89","entry":"elu_feature_map","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"baselines/modeling/transformer/obj_part_cat_seg_model.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/baselines/modeling/transformer/obj_part_cat_seg_model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"code_sha256_prefix":"dd8f7751ef859581","entry":"infer_metric_tags_from_eval_results","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml/part-catseg/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/part-catseg","repo_kind":"official","path":"datasets/partimagenet_preprocess.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/datasets/partimagenet_preprocess.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":"26175e73e7041e86"}},{"code_sha256_prefix":"a4491b45d19b7a39","entry":"parse_keras_history","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml/part-catseg/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":"a4491b45d19b7a39"}},{"code_sha256_prefix":"ee588a4e50fa1acd","entry":"preprocess_partimagenet","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"datasets/partimagenet_preprocess.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/datasets/partimagenet_preprocess.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":"ee588a4e50fa1acd"}},{"code_sha256_prefix":"993ae96666b00cb5","entry":"window_partition","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"baselines/modeling/transformer/obj_part_cat_seg_model.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/baselines/modeling/transformer/obj_part_cat_seg_model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"993ae96666b00cb5"}},{"code_sha256_prefix":"265c72d3ccc64544","entry":"window_reverse","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"baselines/modeling/transformer/obj_part_cat_seg_model.py","file_url":"https://github.com/kaist-cvml/part-catseg/blob/HEAD/baselines/modeling/transformer/obj_part_cat_seg_model.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":"265c72d3ccc64544"}},{"code_sha256_prefix":"f4075cdecbb730c5","entry":"check_imports","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml/part-catseg/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":"f4075cdecbb730c5"}},{"code_sha256_prefix":"00cc853a73f3aeb6","entry":"get_relative_import_files","repo":"kaist-cvml/part-catseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml/part-catseg/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/part-catseg","repo_kind":"official","path":"transformers/dynamic_module_utils.py","file_url":"https://github.com/kaist-cvml/part-catseg/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/part-catseg","repo_kind":"official","path":"transformers/modelcard.py","file_url":"https://github.com/kaist-cvml/part-catseg/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}