"Learning adaptive receptive fields for deep image parsing networks" by Zhen Wei, Yao Sun et al.

Article Title

Learning adaptive receptive fields for deep image parsing networks

Authors

Zhen Wei, State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China. University of Chinese Academy of Sciences, Beijing 101408, China.
Yao Sun, State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China.
Junyu Lin, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China.
Si Liu, State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China. Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology, Nanjing 210094, China.

Keywords

semantic segmentation, receptive field, data-driven, face parsing

Abstract

In this paper, we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks. Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network’s backbone and operates on feature maps. Feature maps are inflated or shrunk by the new layer, thereby changing the receptive fields in the following layers. By use of end-to-end training, the whole framework is data-driven, without laborious manual intervention. The proposed method is generic across datasets and different tasks. We have conducted extensive experiments on both general image parsing tasks, and face parsing tasks as concrete examples, to demonstrate the method’s superior ability to regulate over manual designs.

DOI

https://doi.org/10.1007/s41095-018-0112-1

Publisher

Tsinghua University Press

Recommended Citation

Zhen Wei, Yao Sun, Junyu Lin et al. Learning adaptive receptive fields for deep image parsing networks. Computational Visual Media 2018, 04(03): 231-244.

Download

Request a Copy

Included in

Computational Engineering Commons, Computer-Aided Engineering and Design Commons, Graphics and Human Computer Interfaces Commons, Software Engineering Commons

COinS