{"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/all-about-structure-adapting-structural","title":"All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation","arxiv_id":"1903.12212","date":"2019-03-26","proceeding":"CVPR 2019 6","authors":["Wei-Lun Chang","Hui-Po Wang","Wen-Hsiao Peng","Wei-Chen Chiu"],"abstract":"In this paper we tackle the problem of unsupervised domain adaptation for the\ntask of semantic segmentation, where we attempt to transfer the knowledge\nlearned upon synthetic datasets with ground-truth labels to real-world images\nwithout any annotation. With the hypothesis that the structural content of\nimages is the most informative and decisive factor to semantic segmentation and\ncan be readily shared across domains, we propose a Domain Invariant Structure\nExtraction (DISE) framework to disentangle images into domain-invariant\nstructure and domain-specific texture representations, which can further\nrealize image-translation across domains and enable label transfer to improve\nsegmentation performance. Extensive experiments verify the effectiveness of our\nproposed DISE model and demonstrate its superiority over several\nstate-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1903.12212v1","url_pdf":"http://arxiv.org/pdf/1903.12212v1.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":"all-about-structure-adapting-structural","repo_url":"https://github.com/a514514772/DISE-Domain-Invariant-Structure-Extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"Domain Invariant Structure Extraction","rank_in_archive_order":25,"of":28,"metrics":{"mIoU (13 classes)":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"DISE","rank_in_archive_order":60,"of":73,"metrics":{"mIoU":"45.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.12212","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}