{"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/textregion-text-aligned-region-tokens-from","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","arxiv_id":"2505.23769","date":"2025-05-29","proceeding":null,"authors":["Yao Xiao","Qiqian Fu","Heyi Tao","Yuqun Wu","Zhen Zhu","Derek Hoiem"],"abstract":"Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like SAM2 offer precise spatial boundaries for objects. To this end, we propose TextRegion, a simple, effective, and training-free framework that combines the strengths of image-text models and SAM2 to generate powerful text-aligned region tokens. These tokens enable detailed visual understanding while preserving open-vocabulary capabilities. They can be directly applied to various downstream tasks, including open-world semantic segmentation, referring expression comprehension, and grounding. We conduct extensive evaluations and consistently achieve superior or competitive performance compared to state-of-the-art training-free methods. Additionally, our framework is compatible with many image-text models, making it highly practical and easily extensible as stronger models emerge. Code is available at: https://github.com/avaxiao/TextRegion.","url_abs":"https://arxiv.org/abs/2505.23769v1","url_pdf":"https://arxiv.org/pdf/2505.23769v1.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":"textregion-text-aligned-region-tokens-from","repo_url":"https://github.com/avaxiao/TextRegion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-comprehension","task_name":"Referring Expression Comprehension"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation-with","task_name":"Unsupervised Semantic Segmentation with Language-image Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-4","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"ADE20K","model":"TextRegion","rank_in_archive_order":2,"of":13,"metrics":{"Mean IoU (val)":"27.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-9","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"COCO-Stuff-171","model":"TextRegion","rank_in_archive_order":2,"of":12,"metrics":{"mIoU":"31.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-8","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL Context-59","model":"TextRegion","rank_in_archive_order":2,"of":12,"metrics":{"mIoU":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-12","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL Context-60","model":"TextRegion","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-11","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL VOC","model":"TextRegion","rank_in_archive_order":2,"of":10,"metrics":{"mIoU":"73.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-7","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PascalVOC-20","model":"TextRegion","rank_in_archive_order":2,"of":10,"metrics":{"mIoU":"89.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.23769","atlas_url":"https://app.syntology.ai/?focus=2505.23769","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}