{"url":"/dataset/ood-cv","name":"OOD-CV","full_name":"Out Of Distribution Generalization in Computer Vision","description_markdown":"Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on synthetic data or ignore the effects of individual nuisance factors. We introduce OOD-CV, a benchmark dataset that includes out-of-distribution examples of 10 object categories in terms of pose, shape, texture, context and the weather conditions, and enables benchmarking models for image classification, object detection, and 3D pose estimation. In addition to this novel dataset, we contribute extensive experiments using popular baseline methods, which reveal that: 1. Some nuisance factors have a much stronger negative effect on the performance compared to others, also depending on the vision task. 2. Current approaches to enhance robustness have only marginal effects, and can even reduce robustness. 3. We do not observe significant differences between convolutional and transformer architectures. We believe our dataset provides a rich test bed to study robustness and will help push forward research in this area.","description_withheld":null,"homepage":"https://www.ood-cv.org/","introduced_date":"2021-11-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/robin-a-benchmark-for-robustness-to","title":"OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images","first_author":"Bingchen Zhao","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"3D Pose Estimation","url":"/task/3d-pose-estimation","datasets_with_task":"/datasets/task/3d-pose-estimation"}],"languages":[],"variants":["OOD-CV"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-ood-cv","task":"Unsupervised Domain Adaptation","dataset_variant":"OOD-CV","rows":2,"metrics":["pi/6 accuracy","Accuracy (Top-1)"],"first_row_in_archive_order":{"model":"3DUDA","paper":"/paper/source-free-and-image-only-unsupervised","metrics":{"pi/6 accuracy":"94.0"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-bayesian-approach-to-ood-robustness-in","title":"A Bayesian Approach to OOD Robustness in Image Classification","date":"2024-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/source-free-and-image-only-unsupervised","title":"Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation","date":"2024-01-19","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}