{"url":"/task/photo-to-rest-generalization","name":"Photo to Rest Generalization","slug":"photo-to-rest-generalization","description_markdown":"It is the practical scenario of training on set of easy-to-collect real photographs and evaluate on the rest of diverse-styled domains (art, cartoon, sketch). Photo-to-rest generalization is a special case of the single-source domain generalization (SSDG) task.\r\n\r\nUsing only real photographs for training is the only way for SSDG to be compatible with ImageNet pre-trained networks. For any other domain as source, access to the photo domain through ImageNet pre-training violates the hypothesis of the task of a single domain seen during training, taking the task closer to the multy-source domain generalization (MSDG). Finaly pre-training on imagenet, training on a non real photograph domain and testing on real photographs violates the SSDG hypothesis that the target domain should not be used during training.\r\n\r\nA large part of the generalization community chooses only this task over SSDG for pre-trained networks and for datasets that contain the photo domain.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":7,"papers_with_code":3,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/photo-to-rest-generalization-on-pacs","slug":"photo-to-rest-generalization-on-pacs","dataset":"PACS","dataset_url":"/dataset/pacs","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Crafting-Shifts(ResNet18)","paper_title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","paper_url":"/paper/crafting-distribution-shifts-for-validation","paper_date":"2024-09-29","arxiv_id":"2409.19774","code_links":[{"title":"nikosefth/crafting-shifts","url":"https://github.com/nikosefth/crafting-shifts"}],"syntology":null}},{"leaderboard":"/sota/photo-to-rest-generalization-on-minidomainnet","slug":"photo-to-rest-generalization-on-minidomainnet","dataset":"MiniDomainNet","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Crafting-Shifts(ResNet18)","paper_title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","paper_url":"/paper/crafting-distribution-shifts-for-validation","paper_date":"2024-09-29","arxiv_id":"2409.19774","code_links":[{"title":"nikosefth/crafting-shifts","url":"https://github.com/nikosefth/crafting-shifts"}],"syntology":null}}],"datasets":[{"url":"/dataset/pacs","name":"PACS","full_name":"Photo-Art-Cartoon-Sketch","num_papers_in_archive":668}],"subtasks":[],"parent_tasks":[{"url":"/task/single-source-domain-generalization","name":"Single-Source Domain Generalization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":7,"items":[{"url":"/paper/crafting-distribution-shifts-for-validation","title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","date":"2024-09-29","arxiv_id":"2409.19774","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-bayesian-augmentation-for-single","title":"Adversarial Bayesian Augmentation for Single-Source Domain Generalization","date":"2023-07-18","arxiv_id":"2307.09520","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/learning-to-diversify-for-single-domain","title":"Learning to Diversify for Single Domain Generalization","date":"2021-08-26","arxiv_id":"2108.11726","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}