The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Citations
3,784 citations
1,939 citations
Cites background from "The Mapillary Vistas Dataset for Se..."
...Most datasets provide 2D semantic annotations as boxes or masks (class or instance) [8, 19, 33, 85, 55]....
[...]
...Vistas [33] 2017 n/a - 25k 0 0 25k 0 Yes/Yes 0 152 Global...
[...]
...CamVid [8], Cityscapes [19], Mapillary Vistas [33], D-City [11], BDD100k [85] and Apolloscape [41] released ever growing datasets with segmentation masks....
[...]
1,378 citations
1,163 citations
Cites background from "The Mapillary Vistas Dataset for Se..."
...Existing datasets for autonomous driving [15, 7, 24] are limited in one or more significant aspects, including the scene variation, the richness of annotations, and the geographic distribution....
[...]
...Like Vistas, our data is crowdsourced, however, our dataset is collected solely from drivers, with each annotated image corresponding to a video sequence, which enables interesting applications for modeling temporal dynamics....
[...]
...Mapillary Vistas [24] provides fine-grained annotations for user uploaded data, which is much more diverse with respect to location....
[...]
...Especially with the advent of deep learning methods, large scale visual datasets, such as [8, 36, 40, 24], are essential for learning high-level image representations....
[...]
980 citations
Cites background or methods or result from "The Mapillary Vistas Dataset for Se..."
...This includes the Cityscapes [6], ADE20k [54], and Mapillary Vistas [35] datasets....
[...]
...Both COCO [25] and Mapillary Vistas [35] featured the panoptic segmentation task as one of the tracks in their recognition challenges at ECCV 2018....
[...]
...As expected, humans are not perfect at this task, which is consistent with studies of annotation quality from [6, 54, 35]....
[...]
...Finally we note that the panoptic segmentation task was featured as a challenge track by both the COCO [25] and Mapillary Vistas [35] recognition challenges and that the proposed task has already begun to gain traction in the community (e....
[...]
...Recently the field has seen numerous new segmentation datasets including Cityscapes [6], ADE20k [54], and Mapillary Vistas [35]....
[...]
References
123,388 citations
49,914 citations
[...]
46,982 citations
44,703 citations
"The Mapillary Vistas Dataset for Se..." refers methods in this paper
...A line of successful approaches have been inspired by the Fully Convolutional Network (FCN) [37], which has shown that effective semantic segmentation networks can be obtained from state-of-the-art architectures for image classification such as VGG [52], GoogleNet [53], ResNet [18], Wider ResNet [58], etc., pre-trained on ImageNet [48] and/or Places2 [63], by turning fully-connected layers into convolutional layers....
[...]
...The ResNet 50 models are used due to preference of larger image inputs (max. image size 1900) over deeper feature extractors....
[...]
...The winning team PSPNET [60] built upon [61], extending the basic ResNet 101 (pretrained on ImageNet and Cityscapes, though Cityscapes contribution was negligible) architecture with the following features: i) Modifying the res4b module according to the hybrid dilation convolution (HDC) approach intro- duced in [54]....
[...]
...A line of successful approaches have been inspired by the Fully Convolutional Network (FCN) [37], which has shown that effective semantic segmentation networks can be obtained from state-of-the-art architectures for image classification such as VGG [52], GoogleNet [53], ResNet [18], Wider ResNet [58], etc....
[...]
...2 we present baseline results using a Wider Network (ResNet38) [55] architecture with cross-entropy loss as well as imbalance correction via loss max-pooling and/or alternative minibatch compilation strategies as described in [47]....
[...]
30,811 citations