The Cityscapes Dataset for Semantic Urban Scene Understanding
Citations
2,159 citations
Cites methods from "The Cityscapes Dataset for Semantic..."
...We use state-of-the-art segmentation networks for each dataset: DeepLabV2 [6, 32] for COCOStuff, UperNet101 [42] for ADE20K, and DRN-D-105 [44] for Cityscapes....
[...]
...Recent work has achieved photorealistic semantic image synthesis results [35, 39] on the Cityscapes dataset....
[...]
...We note that the SIMS model produces a lower FID score but has poor segmentation performances on the Cityscapes dataset....
[...]
...• Cityscapes dataset [8] contains street scene images in German cities....
[...]
...In Figure 19 and 20, we show additional synthesis results from the proposed method on the ADE20K-outdoor and Cityscapes datasets with comparison to those from the CRN [7], SIMS [35], and pix2pixHD [40] methods....
[...]
1,972 citations
1,939 citations
Cites background or methods from "The Cityscapes Dataset for Semantic..."
...CamVid [8], Cityscapes [19], Mapillary Vistas [33], D(2)-City [11], BDD100k [85] and Apolloscape [41] released ever growing datasets with segmentation masks....
[...]
...CamVid [8], Cityscapes [19], Mapillary Vistas [33], D2-City [11], BDD100k [85] and Apolloscape [41] released ever growing datasets with segmentation masks....
[...]
...mAP with a threshold on IOU is perhaps the most popular metric for object detection [32, 19, 21]....
[...]
...Most datasets provide 2D semantic annotations as boxes or masks (class or instance) [8, 19, 33, 85, 55]....
[...]
...KITTI [32] was the pioneering multimodal dataset providing dense pointclouds from a lidar sensor as well as front-facing stereo images and GPS/IMU data....
[...]
1,874 citations
1,828 citations
Cites background from "The Cityscapes Dataset for Semantic..."
...ck-ends in small / medium scale scenarios [32, 159] X Front-ends and back-ends in synthetic scenarios [109] X Loop-closures [98, 222] X [184] X [220] X Long-term SLAM [13, 64] X [220] X Semantic SLAM [55] X [220, 284] X Multi-robot SLAM [164] X of visual maps created by large fleets of autonomous vehicles is a compelling area for future work. One can identify tasks for which different flavors of SLAM fo...
[...]
References
73,978 citations
55,235 citations
"The Cityscapes Dataset for Semantic..." refers methods in this paper
...We adopted VGG16 [68] and utilize the PASCAL-context setup [41] with a modified learning rate to match our image resolution under an unnormalized loss....
[...]
49,914 citations
[...]
46,982 citations
30,811 citations