Cityscapes swMATH ID: 36624 Software Authors: Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele Description: The Cityscapes Dataset for Semantic Urban Scene Understanding. Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations; 20000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark. Homepage: https://www.cityscapes-dataset.com Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Visual understanding; urban street scenes; Cityscapes Dataset Related Software: MS-COCO; DeepLab; KITTI; U-Net; ImageNet; ParseNet; PASCAL VOC; SYNTHIA Dataset; SegNet; ADE20k; TensorFlow; Mapillary Vistas; BDD100k; Faster R-CNN; RefineNet; ScanNet; Adam; PyTorch; ApolloScape; GitHub Cited in: 15 Publications Standard Articles 1 Publication describing the Software Year The Cityscapes Dataset for Semantic Urban Scene Understanding Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele 2016 all top 5 Cited by 58 Authors 1 Barrowclough, Oliver J. D. 1 Benaim, Sagie 1 Bhatt, Mehul 1 Burgard, Wolfram 1 Chen, Xilin 1 Galanti, Tomer 1 Gao, Yongsheng 1 Gneushev, A. N. 1 Guo, Jianyuan 1 Ha, Namkoo 1 Hamprecht, Fred A. 1 Hehn, Thomas M. 1 Huang, Lang 1 Jang, Hyunsung 1 Ji, Shuiwang 1 Kim, Youngjung 1 Kooij, Julian F. P. 1 Kot, Alex Chichung 1 Li, Haoliang 1 Li, Jingyu 1 Li, Ke 1 Li, Zhibin 1 Luo, Jiebo 1 Luo, Ping 1 Malik, Jitendra Kumar 1 Matveev, Ivan A. 1 Mauch, Lukas 1 Mohan, Rohit 1 Muntingh, Georg 1 Nainamalai, Varatharajan 1 Navab, Nassir 1 Oh, Changjae 1 Peng, Shichong 1 Ren, Jiamin 1 Samsonov, N. A. 1 Shao, Wenqi 1 Sohn, Kwanghoon 1 Song, Taeyong 1 Stangeby, Ivar 1 Suchan, Jakob 1 Tombari, Federico 1 Valada, Abhinav 1 Varadarajan, Srikrishna 1 Wald, Johanna 1 Wan, Renjie 1 Wang, Chunlai 1 Wang, Jingdong 1 Wang, Shiqi 1 Wang, Xiaogang 1 Wang, Zhengyang 1 Wolf, Lior 1 Xu, Min 1 Yang, Bin 1 Yu, Litao 1 Yuan, Yuhui 1 Zhang, Jian 1 Zhang, Ruimao 1 Zhang, Tianhao all top 5 Cited in 7 Serials 9 International Journal of Computer Vision 1 Artificial Intelligence 1 Journal of the Franklin Institute 1 Computer Aided Geometric Design 1 Journal of Computer and Systems Sciences International 1 Data Mining and Knowledge Discovery 1 Journal of Machine Learning Research (JMLR) Cited in 4 Fields 14 Computer science (68-XX) 1 Statistics (62-XX) 1 Numerical analysis (65-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year