{"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/zero-shot-domain-adaptation-with-a-physics","title":"Zero-Shot Day-Night Domain Adaptation with a Physics Prior","arxiv_id":"2108.05137","date":"2021-08-11","proceeding":"ICCV 2021 10","authors":["Attila Lengyel","Sourav Garg","Michael Milford","Jan C. van Gemert"],"abstract":"We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering relevant test data is expensive and sometimes even impossible, we remove any reliance on test data imagery and instead exploit a visual inductive prior derived from physics-based reflection models for domain adaptation. We cast a number of color invariant edge detectors as trainable layers in a convolutional neural network and evaluate their robustness to illumination changes. We show that the color invariant layer reduces the day-night distribution shift in feature map activations throughout the network. We demonstrate improved performance for zero-shot day to night domain adaptation on both synthetic as well as natural datasets in various tasks, including classification, segmentation and place recognition.","url_abs":"https://arxiv.org/abs/2108.05137v2","url_pdf":"https://arxiv.org/pdf/2108.05137v2.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":"zero-shot-domain-adaptation-with-a-physics","repo_url":"https://github.com/Attila94/CIConv","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":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-24-7-tokyo","task":"Image Retrieval","dataset":"24/7 Tokyo","model":"CIConv","rank_in_archive_order":2,"of":3,"metrics":{"mAP":"88.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dark-zurich","task":"Semantic Segmentation","dataset":"Dark Zurich","model":"CIConv","rank_in_archive_order":14,"of":14,"metrics":{"mIoU":"34.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nighttime-driving","task":"Semantic Segmentation","dataset":"Nighttime Driving","model":"CIConv","rank_in_archive_order":12,"of":13,"metrics":{"mIoU":"41.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2108.05137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05137"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Attila94/CIConv","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8dfdda25a5589eb6","entry":"E_inv","repo":"Attila94/CIConv","repo_kind":"official","path":"method/ciconv2d.py","file_url":"https://github.com/Attila94/CIConv/blob/HEAD/method/ciconv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8dfdda25a5589eb6"}},{"code_sha256_prefix":"95c80b4569359d60","entry":"W_inv","repo":"Attila94/CIConv","repo_kind":"official","path":"method/ciconv2d.py","file_url":"https://github.com/Attila94/CIConv/blob/HEAD/method/ciconv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95c80b4569359d60"}},{"code_sha256_prefix":"e2b19dddf9d60ec6","entry":"gaussian_basis_filters","repo":"Attila94/CIConv","repo_kind":"official","path":"method/ciconv2d.py","file_url":"https://github.com/Attila94/CIConv/blob/HEAD/method/ciconv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2b19dddf9d60ec6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}