{"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/masqclip-for-open-vocabulary-universal-image","title":"MasQCLIP for Open-Vocabulary Universal Image Segmentation","arxiv_id":null,"date":"2023-01-01","proceeding":"ICCV 2023 1","authors":["Xin Xu","Tianyi Xiong","Zheng Ding","Zhuowen Tu"],"abstract":"    We present a new method for open-vocabulary universal image segmentation, which is capable of performing instance, semantic, and panoptic segmentation under a unified framework. Our approach, called MasQCLIP, seamlessly integrates with a pre-trained CLIP model by utilizing its dense features, thereby circumventing the need for extensive parameter training. MasQCLIP emphasizes two new aspects when building an image segmentation method with a CLIP model: 1) a student-teacher module to deal with masks of the novel (unseen) classes by distilling information from the base (seen) classes; 2) a fine-tuning process to update model parameters for the queries Q within the CLIP model. Thanks to these two simple and intuitive designs, MasQCLIP is able to achieve state-of-the-art performances with a substantial gain over the competing methods by a large margin across all three tasks, including open-vocabulary instance, semantic, and panoptic segmentation. Project page is at https://masqclip.github.io/.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2023/html/Xu_MasQCLIP_for_Open-Vocabulary_Universal_Image_Segmentation_ICCV_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2023/papers/Xu_MasQCLIP_for_Open-Vocabulary_Universal_Image_Segmentation_ICCV_2023_paper.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":"masqclip-for-open-vocabulary-universal-image","repo_url":"https://github.com/mlpc-ucsd/MasQCLIP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-ade20k","task":"Panoptic Segmentation","dataset":"ADE20K","model":"MasQCLIP","rank_in_archive_order":1,"of":1,"metrics":{"PQ":"23.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}