Deep Dual-Stream Network with Scale Context Selection Attention Module for Semantic Segmentation

摘要

The fusion of multi-scale features has been an effective method to get state-of-the-art performance in semantic segmentation. In this work, we concentrate on two tricky problems—the intra-class inconsistency and the blur on the localization of object boundaries and tackle them by combining two separate multi-scale context features respectively. Specifically, we propose a dual-stream structure with the scale context selection attention module to enhance the capabilities for multi-scale processing, where one stream collects global-scale context and the other captures local-scale information. Meanwhile, the embedded scale context selection attention module in each stream can adaptively focus on different scale context information to get optimal scale features. Based on our dual-stream structure with attention modules, our network can efficiently make use of multi-scale context to generate more comprehensive and powerful features. Our experiments show that our dual-stream network with scale context selection attention module achieves promising performance on the PASCAL VOC 2012 and PASCAL-Person-Part datasets.