{"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/cat-seg-cost-aggregation-for-open-vocabulary","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","arxiv_id":"2303.11797","date":"2023-03-21","proceeding":"CVPR 2024 1","authors":["Seokju Cho","Heeseong Shin","Sunghwan Hong","Anurag Arnab","Paul Hongsuck Seo","Seungryong Kim"],"abstract":"Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work, we introduce a novel cost-based approach to adapt vision-language foundation models, notably CLIP, for the intricate task of semantic segmentation. Through aggregating the cosine similarity score, i.e., the cost volume between image and text embeddings, our method potently adapts CLIP for segmenting seen and unseen classes by fine-tuning its encoders, addressing the challenges faced by existing methods in handling unseen classes. Building upon this, we explore methods to effectively aggregate the cost volume considering its multi-modal nature of being established between image and text embeddings. Furthermore, we examine various methods for efficiently fine-tuning CLIP.","url_abs":"https://arxiv.org/abs/2303.11797v2","url_pdf":"https://arxiv.org/pdf/2303.11797v2.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":"cat-seg-cost-aggregation-for-open-vocabulary","repo_url":"https://github.com/KU-CVLAB/CAT-Seg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cat-seg-cost-aggregation-for-open-vocabulary","repo_url":"https://github.com/blumenstiel/CAT-Seg-MESS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cat-seg-cost-aggregation-for-open-vocabulary","repo_url":"https://github.com/openrobotlab/ov_parts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"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"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-2","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-150","model":"CAT-Seg","rank_in_archive_order":4,"of":23,"metrics":{"mIoU":"37.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-3","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-847","model":"CAT-Seg","rank_in_archive_order":4,"of":19,"metrics":{"mIoU":"16.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-7","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-459","model":"CAT-Seg","rank_in_archive_order":4,"of":15,"metrics":{"mIoU":"23.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-1","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-59","model":"CAT-Seg","rank_in_archive_order":3,"of":24,"metrics":{"mIoU":"63.3"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"CAT-Seg","rank_in_archive_order":4,"of":20,"metrics":{"mIoU":"97.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-9","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20b","model":"CAT-Seg","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"82.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11797","atlas_url":"https://app.syntology.ai/?focus=2303.11797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11797"}},"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/openrobotlab/ov_parts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KU-CVLAB/CAT-Seg","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/blumenstiel/CAT-Seg-MESS","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":1,"ran_fixture":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"cat_seg/modeling/transformer/model.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/modeling/transformer/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":"6935590148878098","entry":"loadAde20K","repo":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"datasets/prepare_ade20k_full.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/datasets/prepare_ade20k_full.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":"6935590148878098"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"cat_seg/modeling/backbone/swin.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/modeling/backbone/swin.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":"f9fd6241d935f07b"}},{"code_sha256_prefix":"80c66c535be6f491","entry":"window_partition","repo":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"cat_seg/modeling/transformer/model.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/modeling/transformer/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80c66c535be6f491"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"cat_seg/modeling/backbone/swin.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/modeling/backbone/swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"58cc9ff3bf75e753","entry":"nested_tensor_from_tensor_list","repo":"KU-CVLAB/CAT-Seg","repo_kind":"official","path":"cat_seg/utils/misc.py","file_url":"https://github.com/KU-CVLAB/CAT-Seg/blob/HEAD/cat_seg/utils/misc.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":"58cc9ff3bf75e753"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}