{"url":"/dataset/mapillary-vistas-dataset","name":"Mapillary Vistas Dataset","full_name":null,"description_markdown":"Mapillary Vistas Dataset is a diverse street-level imagery dataset with pixel‑accurate and instance‑specific human annotations for understanding street scenes around the world.\r\n\r\nSource: [Mapillary Vistas Dataset](https://www.mapillary.com/dataset/vistas?lat=20&lng=0&z=1.5&pKey=pBBmjuJ8yU1r2ROYRzWmFg)\r\n\r\nImage Source: [Neuhold et al](https://openaccess.thecvf.com/content_ICCV_2017/papers/Neuhold_The_Mapillary_Vistas_ICCV_2017_paper.pdf)","description_withheld":null,"homepage":"https://www.mapillary.com/dataset/vistas?lat=20&lng=0&z=1.5&pKey=pBBmjuJ8yU1r2ROYRzWmFg","introduced_date":"2017-10-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-mapillary-vistas-dataset-for-semantic","title":"The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes","first_author":"Gerhard Neuhold","url":null},"license":{"name":"Custom (non-commercial)","url":"https://www.mapillary.com/dataset/assets/mapillary-object-dataset-research-use-license-2019.pdf"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Visual Place Recognition","url":"/task/visual-place-recognition","datasets_with_task":"/datasets/task/visual-place-recognition"},{"name":"Panoptic Segmentation","url":"/task/panoptic-segmentation","datasets_with_task":"/datasets/task/panoptic-segmentation"}],"languages":[],"variants":["Mapillary val","Mapillary Vistas Dataset"],"data_loaders":[{"repo":"https://github.com/facebookresearch/MaskFormer","url":"https://github.com/facebookresearch/MaskFormer","frameworks":["pytorch"]},{"repo":"https://github.com/takaniwa/dsnet","url":"https://github.com/takaniwa/dsnet","frameworks":["pytorch"]}],"num_papers_in_archive":101,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-place-recognition-on-mapillary-val","task":"Visual Place Recognition","dataset_variant":"Mapillary val","rows":18,"metrics":["Recall@1","Recall@5","Recall@10"],"first_row_in_archive_order":{"model":"QAA-DINOv2-B-8192","paper":"/paper/query-based-adaptive-aggregation-for-multi","metrics":{"Recall@1":"97.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/panoptic-segmentation-on-mapillary-val","task":"Panoptic Segmentation","dataset_variant":"Mapillary val","rows":13,"metrics":["PQ","mIoU","PQst","PQth"],"first_row_in_archive_order":{"model":"OneFormer (DiNAT-L, single-scale)","paper":"/paper/oneformer-one-transformer-to-rule-universal","metrics":{"PQ":"46.7","PQst":"54.9","PQth":"40.5","mIoU":"61.7"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-mapillary-val","task":"Semantic Segmentation","dataset_variant":"Mapillary val","rows":8,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"AO-SegNet","paper":"/paper/interactive-learning-of-intrinsic-and","metrics":{"mIoU":"76.0"},"code_links":[{"title":"BiQiWHU/All-day-CityScapes-segmentation","url":"https://github.com/BiQiWHU/All-day-CityScapes-segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/query-based-adaptive-aggregation-for-multi","title":"Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition","date":"2025-07-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/focus-on-local-finding-reliable-1","title":"Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition","date":"2025-04-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pair-vpr-place-aware-pre-training-and","title":"Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers","date":"2024-10-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/effovpr-effective-foundation-model","title":"EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition","date":"2024-05-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boq-a-place-is-worth-a-bag-of-learnable","title":"BoQ: A Place is Worth a Bag of Learnable Queries","date":"2024-05-12","rows_on_this_dataset":2,"code_links":1,"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/towards-seamless-adaptation-of-pre-trained","title":"Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition","date":"2024-02-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mrfp-learning-generalizable-semantic","title":"MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation","date":"2023-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/optimal-transport-aggregation-for-visual","title":"Optimal Transport Aggregation for Visual Place Recognition","date":"2023-11-27","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":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/interactive-learning-of-intrinsic-and","title":"Interactive Learning of Intrinsic and Extrinsic Properties for All-day Semantic Segmentation","date":"2023-07-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/intra-batch-supervision-for-panoptic-1","title":"Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images","date":"2023-04-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mixvpr-feature-mixing-for-visual-place","title":"MixVPR: Feature Mixing for Visual Place Recognition","date":"2023-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/global-proxy-based-hard-mining-for-visual","title":"Global Proxy-based Hard Mining for Visual Place Recognition","date":"2023-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gsv-cities-toward-appropriate-supervised","title":"GSV-Cities: Toward Appropriate Supervised Visual Place Recognition","date":"2022-10-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-visual-geo-localization-for-large","title":"Rethinking Visual Geo-localization for Large-Scale Applications","date":"2022-04-05","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/per-pixel-classification-is-not-all-you-need","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","date":"2021-07-13","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/generalized-contrastive-optimization-of","title":"Generalized Contrastive Optimization of Siamese Networks for Place Recognition","date":"2021-03-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/patch-netvlad-multi-scale-fusion-of-locally","title":"Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition","date":"2021-03-02","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-convolutional-networks-for-panoptic","title":"Fully Convolutional Networks for Panoptic Segmentation","date":"2020-12-01","rows_on_this_dataset":3,"code_links":6,"syntology":null},{"paper":"/paper/segblocks-block-based-dynamic-resolution","title":"SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation","date":"2020-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scaling-wide-residual-networks-for-panoptic","title":"Scaling Wide Residual Networks for Panoptic Segmentation","date":"2020-11-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-multi-scale-attention-for","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","date":"2020-05-21","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientps-efficient-panoptic-segmentation","title":"EfficientPS: Efficient Panoptic Segmentation","date":"2020-04-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/axial-deeplab-stand-alone-axial-attention-for","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","date":"2020-03-17","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/panoptic-deeplab-a-simple-strong-and-fast","title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","date":"2019-11-22","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/what-s-there-in-the-dark","title":"What's There in the Dark","date":"2019-09-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptis-adaptive-instance-selection-network","title":"AdaptIS: Adaptive Instance Selection Network","date":"2019-09-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/panoptic-segmentation-with-a-joint-semantic","title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","date":"2018-09-06","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":10,"samples_harvested":69,"samples_ran":26,"samples_unverified":43,"pointer_only_for_licence":11,"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."}