Learning a Discriminative Feature Network for Semantic Segmentation

• DOI: 10.48550/arxiv.1804.09337
• Publication Date: 2018-01-01
• Authors: Changqian Yu; Jingbo Wang; Chao Peng; Changxin Gao; Gang Yu; Nong Sang
• Keywords: Discriminative model; Pooling; Pascal (unit); Feature (linguistics); Backbone network; Semantic feature

Most existing methods of semantic segmentation still suffer from two aspects challenges: intra-class inconsistency and inter-class indistinction. To tackle these problems, we propose a Discriminative Feature Network (DFN), which contains sub-networks: Smooth Border Network. Specifically, to handle the problem, specially design with Channel Attention Block global average pooling select more discriminative features. Furthermore, make bilateral features boundary distinguishable deep supervision. Based on our proposed DFN, achieve state-of-the-art performance 86.2% mean IOU PASCAL VOC 2012 80.3% Cityscapes dataset.