RAPNet: Residual Atrous Pyramid Network for Importance-Aware Street Scene Parsing

• Published in: IEEE transactions on image processing 2020-01, Vol.29, p.1-1
• Main Authors: Zhang, Pingping, Liu, Wei, Lei, Yinjie, Wang, Hongyu, Lu, Huchuan
• Format: Article
• Language: English
• Subjects: Driving; fully convolutional network; importance-aware feature selection; Labeling; Labels; Machine learning; residual atrous spatial pyramid; Scene analysis; Semantics; Street scene parsing; Walkways
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2020.2978339

Street Scene Parsing (SSP) is a fundamental and important step for autonomous driving and traffic scene understanding. Recently, Fully Convolutional Network (FCN) based methods have delivered expressive performances with the help of large-scale dense-labeling datasets. However, in urban traffic environments, not all the labels contribute equally for making the control decision. Certain labels such as pedestrian, car, bicyclist, road lane or sidewalk would be more important in comparison with labels for vegetation, sky or building. Based on this fact, in this paper we propose a novel deep learning framework, named Residual Atrous Pyramid Network (RAPNet), for importance-aware SSP. More specifically, to incorporate the importance of various object classes, we propose an Importance-Aware Feature Selection (IAFS) mechanism which automatically selects the important features for label predictions. The IAFS can operate in each convolutional block, and the semantic features with different importance are captured in different channels so that they are automatically assigned with corresponding weights. To enhance the labeling coherence, we also propose a Residual Atrous Spatial Pyramid (RASP) module to sequentially aggregate global-to-local context information in a residual refinement manner. Extensive experiments on two public benchmarks have shown that our approach achieves new state-of-the-art performances, and can consistently obtain more accurate results on the semantic classes with high importance levels.