{"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/explore-the-potential-of-clip-for-training","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","arxiv_id":"2407.08268","date":"2024-07-11","proceeding":null,"authors":["Tong Shao","Zhuotao Tian","Hang Zhao","Jingyong Su"],"abstract":"CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of \"global\" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase.","url_abs":"https://arxiv.org/abs/2407.08268v1","url_pdf":"https://arxiv.org/pdf/2407.08268v1.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":"explore-the-potential-of-clip-for-training","repo_url":"https://github.com/leaves162/cliptrase","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"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"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.08268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08268"}},"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/leaves162/cliptrase","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"c98e9a8121ce0499","entry":"get_image_name_list","repo":"leaves162/cliptrase","repo_kind":"official","path":"clip_self_correlation.py","file_url":"https://github.com/leaves162/cliptrase/blob/HEAD/clip_self_correlation.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":"c98e9a8121ce0499"}},{"code_sha256_prefix":"c266c766b74bafca","entry":"get_predefined_templates","repo":"leaves162/cliptrase","repo_kind":"official","path":"cliptrase_d2/cliptrase/model/utils.py","file_url":"https://github.com/leaves162/cliptrase/blob/HEAD/cliptrase_d2/cliptrase/model/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":"c266c766b74bafca"}},{"code_sha256_prefix":"1945566fa231150d","entry":"gt_transform","repo":"leaves162/cliptrase","repo_kind":"official","path":"clip_self_correlation.py","file_url":"https://github.com/leaves162/cliptrase/blob/HEAD/clip_self_correlation.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":"1945566fa231150d"}},{"code_sha256_prefix":"f55c8ae1a072eb4c","entry":"build_model","repo":"leaves162/cliptrase","repo_kind":"official","path":"clip_utils/model.py","file_url":"https://github.com/leaves162/cliptrase/blob/HEAD/clip_utils/model.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":"f55c8ae1a072eb4c"}},{"code_sha256_prefix":"d9bd04969645298d","entry":"get_image_and_gt","repo":"leaves162/cliptrase","repo_kind":"official","path":"clip_self_correlation.py","file_url":"https://github.com/leaves162/cliptrase/blob/HEAD/clip_self_correlation.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":"d9bd04969645298d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}