{"url":"/dataset/visual-domain-decathlon","name":"Visual Domain Decathlon","full_name":"Visual Domain Decathlon","description_markdown":"The goal of this challenge is to solve simultaneously ten image classification problems representative of very different visual domains. The data for each domain is obtained from the following image classification benchmarks:\r\n\r\nImageNet  \r\nCIFAR-100  \r\nAircraft  \r\nDaimler pedestrian classification  \r\nDescribable textures  \r\nGerman traffic signs  \r\nOmniglot  \r\nSVHN  \r\nUCF101 Dynamic Images  \r\nVGG-Flowers  \r\n\r\nThe union of the images from the ten datasets is split in training, validation, and test subsets. Different domains contain different image categories as well as a different number of images.\r\n\r\nThe task is to train the best possible classifier to address all ten classification tasks using the training and validation subsets, apply the classifier to the test set, and send us the resulting annotation file for assessment. The winner will be determined based on a weighted average of the classification performance on each domain, using the scoring scheme described below. At test time, your model is allowed to know the ground-truth domain of each test image (ImageNet, CIFAR-100, ...) but, of course, not its category.","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/decathlon/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Continual Learning","url":"/task/continual-learning","datasets_with_task":"/datasets/task/continual-learning"}],"languages":[],"variants":["visual domain decathlon (10 tasks)","Visual Domain Decathlon"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/visual_domain_decathlon","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/continual-learning-on-visual-domain-decathlon","task":"Continual Learning","dataset_variant":"visual domain decathlon (10 tasks)","rows":14,"metrics":["decathlon discipline (Score)","Avg. Accuracy"],"first_row_in_archive_order":{"model":"NetTailor","paper":"/paper/nettailor-tuning-the-architecture-not-just-1","metrics":{"Avg. Accuracy":"79.64","decathlon discipline (Score)":"3744"},"code_links":[{"title":"pedro-morgado/nettailor","url":"https://github.com/pedro-morgado/nettailor"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/nettailor-tuning-the-architecture-not-just-1","title":"NetTailor: Tuning the Architecture, Not Just the Weights","date":"2019-06-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/depthwise-convolution-is-all-you-need-for","title":"Depthwise Convolution is All You Need for Learning Multiple Visual Domains","date":"2019-02-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/efficient-parametrization-of-multi-domain","title":"Efficient parametrization of multi-domain deep neural networks","date":"2018-03-27","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/piggyback-adapting-a-single-network-to","title":"Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights","date":"2018-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-multiple-visual-domains-with","title":"Learning multiple visual domains with residual adapters","date":"2017-05-22","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/incremental-learning-through-deep-adaptation","title":"Incremental Learning Through Deep Adaptation","date":"2017-05-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/universal-representationsthe-missing-link","title":"Universal representations:The missing link between faces, text, planktons, and cat breeds","date":"2017-01-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-without-forgetting","title":"Learning without Forgetting","date":"2016-06-29","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":9,"samples_unverified":6,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":18,"samples_ran":11,"samples_unverified":7,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}