{"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/cross-domain-semantic-segmentation-via-domain","title":"Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer","arxiv_id":null,"date":"2020-06-01","proceeding":"CVPR 2020 6","authors":["Fengmao Lv"," Tao Liang"," Xiang Chen"," Guosheng Lin"],"abstract":"Exploiting photo-realistic synthetic data to train semantic segmentation models has received increasing attention over the past years. However, the domain mismatch between synthetic and real images will cause a significant performance drop when the model trained with synthetic images is directly applied to real-world scenarios. In this paper, we propose a new domain adaptation approach, called Pivot Interaction Transfer (PIT). Our method mainly focuses on constructing pivot information that is common knowledge shared across domains as a bridge to promote the adaptation of semantic segmentation model from synthetic domains to real-world domains. Specifically, we first infer the image-level category information about the target images, which is then utilized to facilitate pixel-level transfer for semantic segmentation, with the assumption that the interactive relation between the image-level category information and the pixel-level semantic information is invariant across domains. To this end, we propose a novel multi-level region expansion mechanism that aligns both the image-level and pixel-level information. Comprehensive experiments on the adaptation from both GTAV and SYNTHIA to Cityscapes clearly demonstrate the superiority of our method.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2020/html/Lv_Cross-Domain_Semantic_Segmentation_via_Domain-Invariant_Interactive_Relation_Transfer_CVPR_2020_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2020/papers/Lv_Cross-Domain_Semantic_Segmentation_via_Domain-Invariant_Interactive_Relation_Transfer_CVPR_2020_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":[],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","task":"Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"PIT (ResNet-101)","rank_in_archive_order":25,"of":33,"metrics":{"mIoU":"44.0"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","task":"Domain Adaptation","dataset":"SYNTHIA-to-Cityscapes","model":"PIT (VGG-16)","rank_in_archive_order":32,"of":33,"metrics":{"mIoU":"38.1"},"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}