{"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/domain-generalization-for-object-recognition","title":"Domain Generalization for Object Recognition with Multi-task Autoencoders","arxiv_id":"1508.07680","date":"2015-08-31","proceeding":"ICCV 2015 12","authors":["Muhammad Ghifary","W. Bastiaan Kleijn","Mengjie Zhang","David Balduzzi"],"abstract":"The problem of domain generalization is to take knowledge acquired from a\nnumber of related domains where training data is available, and to then\nsuccessfully apply it to previously unseen domains. We propose a new feature\nlearning algorithm, Multi-Task Autoencoder (MTAE), that provides good\ngeneralization performance for cross-domain object recognition.\n  Our algorithm extends the standard denoising autoencoder framework by\nsubstituting artificially induced corruption with naturally occurring\ninter-domain variability in the appearance of objects. Instead of\nreconstructing images from noisy versions, MTAE learns to transform the\noriginal image into analogs in multiple related domains. It thereby learns\nfeatures that are robust to variations across domains. The learnt features are\nthen used as inputs to a classifier.\n  We evaluated the performance of the algorithm on benchmark image recognition\ndatasets, where the task is to learn features from multiple datasets and to\nthen predict the image label from unseen datasets. We found that (denoising)\nMTAE outperforms alternative autoencoder-based models as well as the current\nstate-of-the-art algorithms for domain generalization.","url_abs":"http://arxiv.org/abs/1508.07680v1","url_pdf":"http://arxiv.org/pdf/1508.07680v1.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":"domain-generalization-for-object-recognition","repo_url":"https://github.com/facebookresearch/DomainBed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"domain-generalization-for-object-recognition","repo_url":"https://github.com/ghif/mtae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"domain-generalization-for-object-recognition","repo_url":"https://github.com/hlzhang109/ddg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.07680","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}