{"url":"/dataset/places365","name":"Places365","full_name":null,"description_markdown":"The **Places365** dataset is a scene recognition dataset. It is composed of 10 million images comprising 434 scene classes. There are two versions of the dataset: Places365-Standard with 1.8 million train and 36000 validation images from K=365 scene classes, and Places365-Challenge-2016, in which the size of the training set is increased up to 6.2 million extra images, including 69 new scene classes (leading to a total of 8 million train images from 434 scene classes).\r\n\r\nSource: [Semantic-Aware Scene Recognition](https://arxiv.org/abs/1909.02410)\r\nImage Source: [Places](http://places2.csail.mit.edu/index.html)","description_withheld":null,"homepage":"http://places2.csail.mit.edu/","introduced_date":"2019-09-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/semantic-aware-scene-recognition","title":"Semantic-Aware Scene Recognition","first_author":"Alejandro López-Cifuentes","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Out-of-Distribution Detection","url":"/task/out-of-distribution-detection","datasets_with_task":"/datasets/task/out-of-distribution-detection"},{"name":"Image Inpainting","url":"/task/image-inpainting","datasets_with_task":"/datasets/task/image-inpainting"},{"name":"Scene Recognition","url":"/task/scene-recognition","datasets_with_task":"/datasets/task/scene-recognition"},{"name":"Image Outpainting","url":"/task/image-outpainting","datasets_with_task":"/datasets/task/image-outpainting"},{"name":"Scene Classification","url":"/task/scene-classification","datasets_with_task":"/datasets/task/scene-classification"}],"languages":[],"variants":["Places365-Standard","Places365","ImageNet-1k vs Places","ImageNet-1k vs Curated OODs (avg.)"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.Places365.html","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/places365_small","frameworks":["tf","jax"]}],"num_papers_in_archive":65,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-12","task":"Out-of-Distribution Detection","dataset_variant":"ImageNet-1k vs Curated OODs (avg.)","rows":16,"metrics":["FPR95","AUROC"],"first_row_in_archive_order":{"model":"NNGuide (RegNet)","paper":"/paper/nearest-neighbor-guidance-for-out-of-1","metrics":{"AUROC":"95.42","FPR95":"17.97"},"code_links":[{"title":"jingkang50/openood","url":"https://github.com/jingkang50/openood"},{"title":"roomo7time/nnguide","url":"https://github.com/roomo7time/nnguide"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-places365","task":"Image Classification","dataset_variant":"Places365","rows":7,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"Top 1 Accuracy":"65.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-places365-standard","task":"Image Classification","dataset_variant":"Places365-Standard","rows":4,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"SWAG (ViT H/14)","paper":"/paper/revisiting-weakly-supervised-pre-training-of","metrics":{"Top 1 Accuracy":"60.7"},"code_links":[{"title":"facebookresearch/SWAG","url":"https://github.com/facebookresearch/SWAG"},{"title":"Expedit-LargeScale-Vision-Transformer/Expedit-SWAG","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-SWAG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-classification-on-places365-standard","task":"Scene Classification","dataset_variant":"Places365-Standard","rows":2,"metrics":["Top 1 Error","Top 5 Error"],"first_row_in_archive_order":{"model":"WaveMix","paper":"/paper/wavemix-lite-a-resource-efficient-neural","metrics":{"Top 1 Error":"43.55"},"code_links":[{"title":"pranavphoenix/WaveMix","url":"https://github.com/pranavphoenix/WaveMix"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-recognition-on-places365","task":"Scene Recognition","dataset_variant":"Places365","rows":2,"metrics":["Top 1 Accuracy","Top 5 Accuracy"],"first_row_in_archive_order":{"model":"FOSNet","paper":"/paper/fosnet-an-end-to-end-trainable-deep-neural","metrics":{"Top 1 Accuracy":"60.14","Top 5 Accuracy":"88.86"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-inpainting-on-places365","task":"Image Inpainting","dataset_variant":"Places365","rows":1,"metrics":["L1 error"],"first_row_in_archive_order":{"model":"GGLA","paper":"/paper/global-and-local-attention-based-free-form","metrics":{"L1 error":"1.20"},"code_links":[{"title":"SayedNadim/Global-and-Local-Attention-Based-Free-Form-Image-Inpainting","url":"https://github.com/SayedNadim/Global-and-Local-Attention-Based-Free-Form-Image-Inpainting"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-outpainting-on-places365-standard","task":"Image Outpainting","dataset_variant":"Places365-Standard","rows":1,"metrics":["L1","MSE","Adversarial"],"first_row_in_archive_order":{"model":"Residual Encoder","paper":"/paper/enhanced-residual-networks-for-context-based","metrics":{"Adversarial":"0.0941","L1":"0.08","MSE":"0.7814"},"code_links":[{"title":"etarthur/Outpainting","url":"https://github.com/etarthur/Outpainting"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/scaling-for-training-time-and-post-hoc-out-of","title":"Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement","date":"2023-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/nearest-neighbor-guidance-for-out-of-1","title":"Nearest Neighbor Guidance for Out-of-Distribution Detection","date":"2023-09-26","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unleashing-mask-explore-the-intrinsic-out-of","title":"Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability","date":"2023-06-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/detecting-out-of-distribution-data-through-in","title":"Detecting Out-of-distribution Data through In-distribution Class Prior","date":"2023-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/line-out-of-distribution-detection-by","title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","date":"2023-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":8,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/visual-representation-learning-from-unlabeled","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","date":"2023-03-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/out-of-distribution-detection-with-implicit","title":"Out-of-distribution Detection with Implicit Outlier Transformation","date":"2023-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/non-parametric-outlier-synthesis","title":"Non-Parametric Outlier Synthesis","date":"2023-03-06","rows_on_this_dataset":1,"code_links":1,"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/rethinking-out-of-distribution-ood-detection","title":"Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need","date":"2023-02-06","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/decoupling-maxlogit-for-out-of-distribution","title":"Decoupling MaxLogit for Out-of-Distribution Detection","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/delving-into-out-of-distribution-detection","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","date":"2022-11-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/boosting-out-of-distribution-detection-with","title":"Boosting Out-of-distribution Detection with Typical Features","date":"2022-10-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/extremely-simple-activation-shaping-for-out","title":"Extremely Simple Activation Shaping for Out-of-Distribution Detection","date":"2022-09-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rankfeat-rank-1-feature-removal-for-out-of","title":"RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection","date":"2022-09-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wavemix-lite-a-resource-efficient-neural","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","date":"2022-05-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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/revisiting-weakly-supervised-pre-training-of","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","date":"2022-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/on-the-effectiveness-of-sparsification-for","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","date":"2021-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":8,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/mos-towards-scaling-out-of-distribution","title":"MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space","date":"2021-05-05","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/global-and-local-attention-based-free-form","title":"Global and Local Attention-Based Free-Form Image Inpainting","date":"2020-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhanced-residual-networks-for-context-based","title":"Enhanced Residual Networks for Context-based Image Outpainting","date":"2020-05-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-aware-scene-recognition","title":"Semantic-Aware Scene Recognition","date":"2019-09-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fosnet-an-end-to-end-trainable-deep-neural","title":"FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition","date":"2019-07-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-cnns-meet-global-covariance-pooling","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","date":"2019-04-15","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":3,"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":14,"samples_harvested":222,"samples_ran":110,"samples_unverified":112,"pointer_only_for_licence":79,"papers_with_no_sample_that_ran":3,"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."}