{"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/aa-clip-enhancing-zero-shot-anomaly-detection","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","arxiv_id":"2503.06661","date":"2025-03-09","proceeding":"CVPR 2025 1","authors":["Wenxin Ma","Xu Zhang","Qingsong Yao","Fenghe Tang","Chenxu Wu","Yingtai Li","Rui Yan","Zihang Jiang","S. Kevin Zhou"],"abstract":"Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capabilities, its inherent Anomaly-Unawareness leads to limited discrimination between normal and abnormal features. To address this problem, we propose Anomaly-Aware CLIP (AA-CLIP), which enhances CLIP's anomaly discrimination ability in both text and visual spaces while preserving its generalization capability. AA-CLIP is achieved through a straightforward yet effective two-stage approach: it first creates anomaly-aware text anchors to differentiate normal and abnormal semantics clearly, then aligns patch-level visual features with these anchors for precise anomaly localization. This two-stage strategy, with the help of residual adapters, gradually adapts CLIP in a controlled manner, achieving effective AD while maintaining CLIP's class knowledge. Extensive experiments validate AA-CLIP as a resource-efficient solution for zero-shot AD tasks, achieving state-of-the-art results in industrial and medical applications. The code is available at https://github.com/Mwxinnn/AA-CLIP.","url_abs":"https://arxiv.org/abs/2503.06661v1","url_pdf":"https://arxiv.org/pdf/2503.06661v1.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":"aa-clip-enhancing-zero-shot-anomaly-detection","repo_url":"https://github.com/mwxinnn/aa-clip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"anomaly-localization","task_name":"Anomaly Localization"},{"task_slug":"lesion-detection","task_name":"Lesion Detection"},{"task_slug":"zero-shot-anomaly-detection","task_name":"zero-shot anomaly detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.06661","atlas_url":"https://app.syntology.ai/?focus=2503.06661","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}