CNet: Context-Aware Network for Semantic Segmentation

Semantic segmentation is one of the great challenges in computer vision. Recently, deep convolutional neural networks (DCNNs) have achieved great success in most of the computer vision tasks. However, in terms of semantic segmentation, it is still difficult for the DCNN methods to take full advantage of context information and determine the fine boundaries of objects. In this paper, we propose a Context-aware Network (CNet), which utilizes robust context information to improve segmentation results. CNet has two significant components: 1) a feature collection module (FCM), which is constructed to extract low-level contextual features including texture, layout, boundary, local and global relationships by different receptive fields to complement high-level feature learning, and 2) a novel layer named ResGate, which is developed to select robust contextual features from the FCM. The two combined components can thoroughly explore context information to improve boundary segmentation accuracy. We evaluate the proposed method on the popular PASCAL VOC2012 dataset, and obtain promising performance compared with related methods, especially in the situation of similar objects or objects in complex scene.