{"url":"/dataset/places205","name":"Places205","full_name":null,"description_markdown":"The **Places205** dataset is a large-scale scene-centric dataset with 205 common scene categories. The training dataset contains around 2,500,000 images from these categories. In the training set, each scene category has the minimum 5,000 and maximum 15,000 images. The validation set contains 100 images per category (a total of 20,500 images), and the testing set includes 200 images per category (a total of 41,000 images).\r\n\r\nSource: [Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs](https://arxiv.org/abs/1610.01119)\r\nImage Source: [http://places.csail.mit.edu/browser.html](http://places.csail.mit.edu/browser.html)","description_withheld":null,"homepage":"http://places.csail.mit.edu/downloadData.html","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-deep-features-for-scene-recognition","title":"Learning Deep Features for Scene Recognition using Places Database","first_author":"Bolei Zhou","url":null},"license":{"name":"CC BY","url":"http://places.csail.mit.edu/index.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Cross-Domain Few-Shot","url":"/task/cross-domain-few-shot","datasets_with_task":"/datasets/task/cross-domain-few-shot"},{"name":"Scene Recognition","url":"/task/scene-recognition","datasets_with_task":"/datasets/task/scene-recognition"}],"languages":[],"variants":["Places205","Places"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/places205-dataset","frameworks":["tf","pytorch"]}],"num_papers_in_archive":525,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset_variant":"Places205","rows":15,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"InternImage-H","paper":"/paper/internimage-exploring-large-scale-vision","metrics":{"Top 1 Accuracy":"71.7%"},"code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","date":"2022-05-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boosting-discriminative-visual-representation","title":"Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup","date":"2021-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","rows_on_this_dataset":1,"code_links":58,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":137,"samples_ran":71,"samples_unverified":66,"pointer_only_for_licence":73,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/automix-unveiling-the-power-of-mixup","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","date":"2021-03-24","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/barlow-twins-self-supervised-learning-via","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","date":"2021-03-04","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":21,"samples_unverified":5,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-pretraining-of-visual","title":"Self-supervised Pretraining of Visual Features in the Wild","date":"2021-03-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-learning-of-visual-features-by","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","date":"2020-06-17","rows_on_this_dataset":2,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":13,"samples_unverified":4,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bootstrap-your-own-latent-a-new-approach-to","title":"Bootstrap your own latent: A new approach to self-supervised Learning","date":"2020-06-13","rows_on_this_dataset":1,"code_links":31,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":79,"samples_ran":62,"samples_unverified":17,"pointer_only_for_licence":46,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-baselines-with-momentum-contrastive","title":"Improved Baselines with Momentum Contrastive Learning","date":"2020-03-09","rows_on_this_dataset":1,"code_links":36,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":43,"samples_ran":8,"samples_unverified":35,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","rows_on_this_dataset":1,"code_links":96,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":137,"samples_ran":79,"samples_unverified":58,"pointer_only_for_licence":52,"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":8,"samples_harvested":449,"samples_ran":260,"samples_unverified":189,"pointer_only_for_licence":197,"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."}