{"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/interactive-learning-of-intrinsic-and","title":"Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation","arxiv_id":null,"date":"2023-07-07","proceeding":"IEEE Transactions on Image Processing 2023 7","authors":["Qi Bi","ShaoDi You","Theo Gevers"],"abstract":"Scene appearance changes drastically throughout the day. Existing semantic segmentation methods mainly focus on well-lit daytime scenarios and are not well designed to cope with such great appearance changes. Naively using domain adaption\r\ndoes not solve this problem because it usually learns a fixed mapping between the source and target domain and thus have\r\nlimited generalization capability on all-day scenarios (i.e., from dawn to night).\r\nIn this paper, in contrast to existing methods, we tackle this challenge from the perspective of image formulation itself, where the image appearance is determined by both intrinsic (e.g., semantic category, structure) and extrinsic (e.g., lighting)\r\nproperties. To this end, we propose a novel intrinsic-extrinsic interactive learning strategy. The key idea is to interact between intrinsic and extrinsic representations during the learning process under spatial-wise guidance. In this way, the intrinsic representation becomes more stable and, at the same time, the extrinsic representation gets better at depicting the changes. Consequently, the refined image representation is more robust to generate pixel-wise predictions for all-day scenarios. To achieve this, we propose an All-in-One Segmentation Network (AO-SegNet) in an end-to-end manner.\r\nLarge scale experiments are conducted on three real datasets (Mapillary, BDD100K and ACDC) and our proposed synthetic All-day CityScapes dataset. The proposed AO-SegNet shows a significant performance gain against the state-of-the-art under a variety of CNN and ViT backbones on all the datasets.","url_abs":"https://ieeexplore.ieee.org/abstract/document/10176286","url_pdf":"https://ieeexplore.ieee.org/abstract/document/10176286","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":"interactive-learning-of-intrinsic-and","repo_url":"https://github.com/BiQiWHU/All-day-CityScapes-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"all-day-semantic-segmentation","task_name":"All-day Semantic Segmentation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[{"slug":"all-day-cityscapes","name":"All-day CityScapes","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/all-day-semantic-segmentation-on-all-day","task":"All-day Semantic Segmentation","dataset":"All-day CityScapes","model":"AO-SegNet (Swin-Base)","rank_in_archive_order":1,"of":3,"metrics":{"mIoU":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-mapillary-val","task":"Semantic Segmentation","dataset":"Mapillary val","model":"AO-SegNet","rank_in_archive_order":1,"of":8,"metrics":{"mIoU":"76.0"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}