{"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/mc-panda-mask-confidence-for-panoptic-domain","title":"MC-PanDA: Mask Confidence for Panoptic Domain Adaptation","arxiv_id":"2407.14110","date":"2024-07-19","proceeding":null,"authors":["Ivan Martinović","Josip Šarić","Siniša Šegvić"],"abstract":"Domain adaptive panoptic segmentation promises to resolve the long tail of corner cases in natural scene understanding. Previous state of the art addresses this problem with cross-task consistency, careful system-level optimization and heuristic improvement of teacher predictions. In contrast, we propose to build upon remarkable capability of mask transformers to estimate their own prediction uncertainty. Our method avoids noise amplification by leveraging fine-grained confidence of panoptic teacher predictions. In particular, we modulate the loss with mask-wide confidence and discourage back-propagation in pixels with uncertain teacher or confident student. Experimental evaluation on standard benchmarks reveals a substantial contribution of the proposed selection techniques. We report 47.4 PQ on Synthia to Cityscapes, which corresponds to an improvement of 6.2 percentage points over the state of the art. The source code is available at https://github.com/helen1c/MC-PanDA.","url_abs":"https://arxiv.org/abs/2407.14110v1","url_pdf":"https://arxiv.org/pdf/2407.14110v1.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":"mc-panda-mask-confidence-for-panoptic-domain","repo_url":"https://github.com/helen1c/mc-panda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-panoptic-synthia-to","task":"Domain Adaptation","dataset":"Panoptic SYNTHIA-to-Cityscapes","model":"MC-PanDA","rank_in_archive_order":1,"of":5,"metrics":{"mPQ":"47.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-panoptic-synthia-to-1","task":"Domain Adaptation","dataset":"Panoptic SYNTHIA-to-Mapillary","model":"MC-PanDA","rank_in_archive_order":1,"of":5,"metrics":{"mPQ":"38.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}