{"url":"/dataset/syn2real","name":"Syn2Real","full_name":"Syn2Real","description_markdown":"**Syn2Real**, a synthetic-to-real visual domain adaptation benchmark meant to encourage further development of robust domain transfer methods. The goal is to train a model on a synthetic \"source\" domain and then update it so that its performance improves on a real \"target\" domain, without using any target annotations. It includes three tasks, illustrated in figures above: the more traditional closed-set classification task with a known set of categories; the less studied open-set classification task with unknown object categories in the target domain; and the object detection task, which involves localizing instances of objects by predicting their bounding boxes and corresponding class labels.\r\n\r\nSource: [Syn2Real](https://ai.bu.edu/syn2real/)\r\nImage Source: [https://ai.bu.edu/syn2real/](https://ai.bu.edu/syn2real/)","description_withheld":null,"homepage":"https://ai.bu.edu/syn2real/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/syn2real-a-new-benchmark-forsynthetic-to-real","title":"Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation","first_author":"Xingchao Peng","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Synthetic-to-Real Translation","url":"/task/synthetic-to-real-translation","datasets_with_task":"/datasets/task/synthetic-to-real-translation"}],"languages":[],"variants":["Syn2Real-C","Syn2Real"],"data_loaders":[],"num_papers_in_archive":15,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/synthetic-to-real-translation-on-syn2real-c","task":"Synthetic-to-Real Translation","dataset_variant":"Syn2Real-C","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DADA","paper":"/paper/discriminative-adversarial-domain-adaptation","metrics":{"Accuracy":"79.8"},"code_links":[{"title":"huitangtang/DADA-AAAI2020","url":"https://github.com/huitangtang/DADA-AAAI2020"},{"title":"monkey0head/Domain_Adaptation_thesis","url":"https://github.com/monkey0head/Domain_Adaptation_thesis"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/discriminative-adversarial-domain-adaptation","title":"Discriminative Adversarial Domain Adaptation","date":"2019-11-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsupervised-visual-domain-adaptation-a-deep","title":"Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach","date":"2019-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maximum-classifier-discrepancy-for","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","date":"2017-12-07","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adversarial-dropout-regularization","title":"Adversarial Dropout Regularization","date":"2017-11-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","rows_on_this_dataset":1,"code_links":484,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":377,"samples_ran":230,"samples_unverified":147,"pointer_only_for_licence":187,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/domain-adversarial-training-of-neural","title":"Domain-Adversarial Training of Neural Networks","date":"2015-05-28","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":52,"samples_ran":33,"samples_unverified":19,"pointer_only_for_licence":22,"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":4,"samples_harvested":432,"samples_ran":264,"samples_unverified":168,"pointer_only_for_licence":210,"papers_with_no_sample_that_ran":1,"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."}