ADE20k swMATH ID: 36627 Software Authors: Zhou B., Zhao H., Puig X., Fidler S., Barriuso A., Torralba A. Description: Scene parsing through ADE20k dataset. Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the communitys efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. A scene parsing benchmark is built upon the ADE20K with 150 object and stuff classes included. Several segmentation baseline models are evaluated on the benchmark. A novel network design called Cascade Segmentation Module is proposed to parse a scene into stuff, objects, and object parts in a cascade and improve over the baselines. We further show that the trained scene parsing networks can lead to applications such as image content removal and scene synthesis Homepage: https://ieeexplore.ieee.org/document/8100027 Related Software: MS-COCO; DeepLab; Cityscapes; KITTI; U-Net; Mapillary Vistas; ImageNet; PASCAL VOC; CCNet; SemanticKITTI; Python; nuScenes; ApolloScape; H3D; Waymo; BDD100k; ShuffleNet; RefineNet; ParseNet; SegNet Cited in: 6 Publications all top 5 Cited by 27 Authors 1 Chen, Xilin 1 Fan, Jinlong 1 Fuxin, Li 1 Gao, Yongsheng 1 Guo, Jianyuan 1 Huang, Lang 1 Khorram, Saeed 1 Li, Jingyu 1 Li, Zhibin 1 Liu, Sifei 1 Luo, Jiebo 1 Luo, Ping 1 Ma, Huimin 1 Maybank, Stephen John 1 Qi, Zhongang 1 Ren, Jiamin 1 Shao, Wenqi 1 Tao, Dacheng 1 Wang, Jingdong 1 Wang, Xiang 1 Wang, Xiaogang 1 Xu, Min 1 Yang, Ming-Hsuan 1 Yu, Litao 1 Yuan, Yuhui 1 Zhang, Jian 1 Zhang, Ruimao Cited in 2 Serials 5 International Journal of Computer Vision 1 Artificial Intelligence Cited in 1 Field 6 Computer science (68-XX) Citations by Year