Attention to refine through multi-scales for semantic segmentation

作     者：Yang, Shiqi Peng, Gang 

作者机构：Key Laboratory of Ministry of Education for Image Processing and Intelligence Control School of Automation Huazhong University of Science and Technology Wuhan China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2018年

核心收录：

主　　题：Semantic Segmentation 

摘      要：This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different scales inputs, by which means the CNN can get representations in different scales. The proposed attention model will handle the features from different scale streams respectively and integrate them. Then location attention branch of the model learns to softly weight the multi-scale features at each pixel location. More- over, we add an recalibrating branch, parallel to where location attention comes out, to recalibrate the score map per class. We achieve quite com- petitive results on PASCAL VOC 2012 and ADE20K datasets, which surpass baseline and related works. Copyright © 2018, The Authors. All rights reserved.