Learning adaptive receptive fields for deep image parsing networks

• Main Authors: Zhen Wei, Yao Sun, Junyu Lin, Si Liu
• Format: Article
• Language: English
• Published: SpringerOpen 2018-04-01
• Series: Computational Visual Media
• Subjects: semantic segmentation; receptive field; data-driven; face parsing
• Online Access: http://link.springer.com/article/10.1007/s41095-018-0112-1
• ISSN: 2096-0433; 2096-0662

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.