{"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/visda-the-visual-domain-adaptation-challenge","title":"VisDA: The Visual Domain Adaptation Challenge","arxiv_id":"1710.06924","date":"2017-10-18","proceeding":null,"authors":["Xingchao Peng","Ben Usman","Neela Kaushik","Judy Hoffman","Dequan Wang","Kate Saenko"],"abstract":"We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a\nlarge-scale testbed for unsupervised domain adaptation across visual domains.\nUnsupervised domain adaptation aims to solve the real-world problem of domain\nshift, where machine learning models trained on one domain must be transferred\nand adapted to a novel visual domain without additional supervision. The\nVisDA2017 challenge is focused on the simulation-to-reality shift and has two\nassociated tasks: image classification and image segmentation. The goal in both\ntracks is to first train a model on simulated, synthetic data in the source\ndomain and then adapt it to perform well on real image data in the unlabeled\ntest domain. Our dataset is the largest one to date for cross-domain object\nclassification, with over 280K images across 12 categories in the combined\ntraining, validation and testing domains. The image segmentation dataset is\nalso large-scale with over 30K images across 18 categories in the three\ndomains. We compare VisDA to existing cross-domain adaptation datasets and\nprovide a baseline performance analysis using various domain adaptation models\nthat are currently popular in the field.","url_abs":"http://arxiv.org/abs/1710.06924v2","url_pdf":"http://arxiv.org/pdf/1710.06924v2.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":"visda-the-visual-domain-adaptation-challenge","repo_url":"https://github.com/VisionLearningGroup/taskcv-2017-public","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"visda-the-visual-domain-adaptation-challenge","repo_url":"https://github.com/szubing/uniood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[{"slug":"visda-2017","name":"VisDA-2017","full_name":"VisDA-2017"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.06924","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}