{"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/dark-model-adaptation-semantic-image","title":"Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime","arxiv_id":"1810.02575","date":"2018-10-05","proceeding":null,"authors":["Dengxin Dai","Luc van Gool"],"abstract":"This work addresses the problem of semantic image segmentation of nighttime\nscenes. Although considerable progress has been made in semantic image\nsegmentation, it is mainly related to daytime scenarios. This paper proposes a\nnovel method to progressive adapt the semantic models trained on daytime\nscenes, along with large-scale annotations therein, to nighttime scenes via the\nbridge of twilight time -- the time between dawn and sunrise, or between sunset\nand dusk. The goal of the method is to alleviate the cost of human annotation\nfor nighttime images by transferring knowledge from standard daytime\nconditions. In addition to the method, a new dataset of road scenes is\ncompiled; it consists of 35,000 images ranging from daytime to twilight time\nand to nighttime. Also, a subset of the nighttime images are densely annotated\nfor method evaluation. Our experiments show that our method is effective for\nmodel adaptation from daytime scenes to nighttime scenes, without using extra\nhuman annotation.","url_abs":"http://arxiv.org/abs/1810.02575v1","url_pdf":"http://arxiv.org/pdf/1810.02575v1.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":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"nighttime-driving","name":"Nighttime Driving","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-nighttime-driving","task":"Semantic Segmentation","dataset":"Nighttime Driving","model":"DMAda","rank_in_archive_order":13,"of":13,"metrics":{"mIoU":"36.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.02575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}