{"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/curriculum-domain-adaptation-for-semantic","title":"Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes","arxiv_id":"1707.09465","date":"2017-07-29","proceeding":"ICCV 2017 10","authors":["Yang Zhang","Philip David","Boqing Gong"],"abstract":"During the last half decade, convolutional neural networks (CNNs) have\ntriumphed over semantic segmentation, which is one of the core tasks in many\napplications such as autonomous driving. However, to train CNNs requires a\nconsiderable amount of data, which is difficult to collect and laborious to\nannotate. Recent advances in computer graphics make it possible to train CNNs\non photo-realistic synthetic imagery with computer-generated annotations.\nDespite this, the domain mismatch between the real images and the synthetic\ndata cripples the models' performance. Hence, we propose a curriculum-style\nlearning approach to minimize the domain gap in urban scenery semantic\nsegmentation. The curriculum domain adaptation solves easy tasks first to infer\nnecessary properties about the target domain; in particular, the first task is\nto learn global label distributions over images and local distributions over\nlandmark superpixels. These are easy to estimate because images of urban scenes\nhave strong idiosyncrasies (e.g., the size and spatial relations of buildings,\nstreets, cars, etc.). We then train a segmentation network while regularizing\nits predictions in the target domain to follow those inferred properties. In\nexperiments, our method outperforms the baselines on two datasets and two\nbackbone networks. We also report extensive ablation studies about our\napproach.","url_abs":"http://arxiv.org/abs/1707.09465v5","url_pdf":"http://arxiv.org/pdf/1707.09465v5.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":"curriculum-domain-adaptation-for-semantic","repo_url":"https://github.com/YangZhang4065/AdaptationSeg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"CDA","rank_in_archive_order":27,"of":28,"metrics":{"mIoU (13 classes)":"29.0"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CDA","rank_in_archive_order":72,"of":73,"metrics":{"mIoU":"28.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.09465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.09465"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YangZhang4065/AdaptationSeg","reach":null}],"summary":{"unverified":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"c707d2609c74b8a1","entry":"binarize_label","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c707d2609c74b8a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}