The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes

By Gerhard Neuhold, Tobias Ollmann, Samuel Rota Bulò, Peter Kontschieder. 2017

1,529 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ocean Engineering, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Ocean Engineering

In Evaluation & Benchmarks

Citations in the corpus

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “, Mapillary Vistas [65]), our multi-scale Axial-DeepLab-XL attains 68.”
Panoptic Feature Pyramid Networks (2019, methodology): “1For details of not yet published winning entries in the 2018 COCO and Mapillary Recognition Challenge please see: http://cocodataset. org/workshop/coco-mapillary-eccv-2018.html.”
Panoptic Segmentation (2018, methodology): “This includes the Cityscapes [6], ADE20k [54], and Mapillary Vistas [35] datasets.”
LVIS: A Dataset for Large Vocabulary Instance Segmentation (2019, neutral): “LVIS is inspired by these and other related datasets, including those focused on street scenes (Cityscapes [3] and Mapillary [22]) and pedestrians (Caltech Pedestrians [4]).”
Language-driven Semantic Segmentation (2022, background): “…of 7 different datasets (Lambert et al., 2020), including ADE20K (Zhou et al., 2019), BDD (Yu et al., 2020), Cityscapes (Cordts et al., 2016), COCO-Panoptic (Lin et al., 2014; Caesar et al., 2018), IDD (Varma et al., 2019), Mapillary Vistas (Neuhold et al., 2017), and SUN RGBD (Song et al., 2015).”
Masked-attention Mask Transformer for Universal Image Segmentation (2021, methodology): “We study Mask2Former using four widely used image segmentation datasets that support semantic, instance and panoptic segmentation: COCO [35] (80 “things” and 53 “stuff” categories), ADE20K [65] (100 “things” and 50 “stuff” categories), Cityscapes [16] (8 “things” and 11 “stuff” categories) and Mapil”
Per-Pixel Classification is Not All You Need for Semantic Segmentation (2021, methodology): “We evaluate MaskFormer on five semantic segmentation datasets with various numbers of categories: Cityscapes [15] (19 classes), Mapillary Vistas [34] (65 classes), ADE20K [55] (150 classes), COCOStuff-10K [3] (171 classes), and ADE20K-Full [55] (847 classes).”
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, background): “with multiple annotations and tasks, towards learning intermediate representations through downstream and multi-task learning on the same input. This has been recently achieved for autonomous driving [17,18,19,20,21,22,23,24] and scene understanding [25,26]. For example, Taskonomy [25] contains 26 t”
WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving (2019, background): “Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
Path Aggregation Network for Instance Segmentation (2018, methodology): “We also benchmark our system on Cityscapes and MVD, which similarly yields top-ranking results, manifesting that our PANet is a very practical and top-performing framework.”
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming (2019, methodology): “…of available object detection datasets [Everingham et al., 2010, Geiger et al., 2012, Lin et al., 2014, Cordts et al., 2016, Zhou et al., 2017, Neuhold et al., 2017, Krasin et al., 2017], we chose to use PASCAL VOC [Everingham et al., 2010], MS COCO [Lin et al., 2014] and Cityscapes [Cordts…”
A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, background): “Cityscapes [270] X X Vehicle Berkley DeepDrive [271] X X Vehicle X X Mapillary [272] X X Vehicle X X Oxford RobotCar [49] X X Vehicle X X X KITTI [174] X X X X Vehicle H3D [273] X X X Vehicle ApolloScape [274] X X X X Vehicle nuScenes [175] X X X X Vehicle X X Udacity [275] X X X X Vehicle DDD17 [85”
In-place Activated BatchNorm for Memory-Optimized Training of DNNs (2017, methodology): “State-of-the-art segmentations are typically obtained by combining classification models pretrained on ImageNet (typically referred to as body) with segmentation-specific head architectures and jointly fine-tuning them on suitable, (densely) annotated training data like Cityscapes [5], COCO-Stuff [1”
Object-Contextual Representations for Semantic Segmentation (2019, methodology): “For comparison with the approaches based on the advanced baselines, we perform our OCR on the HRNet-W48, and pre-train our model on the Mapillary dataset [50].”
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (2019, methodology): “We perform experiments on Cityscapes [3] and Mapil-lary Vistas [11] datasets.”
PointRend: Image Segmentation As Rendering (2019, methodology): “These methods can produce more detailed output, however, they lag behind region-based approaches on most instance segmentation benchmarks [26, 8, 35].”
nuScenes: A Multimodal Dataset for Autonomous Driving (2019, background): “Most datasets provide 2D semantic annotations as boxes or masks (class or instance) [8, 19, 33, 85, 55].”