Survey of recent progress in semantic image segmentation with CNNs  

作　　者：Qichuan GENG Zhong ZHOU Xiaochun CAO 

机构地区：[1]State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering, Beihang University [2]State Key Laboratory of Information Security, Institute of Information Engineering,Chinese Academy of Sciences

出　　处：《Science China(Information Sciences)》2018年第5期103-120,共18页中国科学（信息科学）（英文版）

基　　金：supported by National High-tech R&D Program of China (863 Program) (Grant No. 2015AA016403);National Natural Science Foundation of China (Grant Nos. 61572061, 61472020)

摘　　要：In recent years, convolutional neural networks （CNNs） are leading the way in many computer vision tasks, such as image classification, object detection, and face recognition. In order to produce more refined semantic image segmentation, we survey the powerful CNNs and novel elaborate layers, structures and strategies, especially including those that have achieved the state-of-the-art results on the Pascal VOC 2012 semantic segmentation challenge. Moreover, we discuss their different working stages and various mechanisms to utilize the structural and contextual information in the image and feature spaces. Finally, combining some popular underlying referential methods in homologous problems, we propose several possible directions and approaches to incorporate existing effective methods as components to enhance CNNs for the segmentation of specific semantic objects.In recent years, convolutional neural networks （CNNs） are leading the way in many computer vision tasks, such as image classification, object detection, and face recognition. In order to produce more refined semantic image segmentation, we survey the powerful CNNs and novel elaborate layers, structures and strategies, especially including those that have achieved the state-of-the-art results on the Pascal VOC 2012 semantic segmentation challenge. Moreover, we discuss their different working stages and various mechanisms to utilize the structural and contextual information in the image and feature spaces. Finally, combining some popular underlying referential methods in homologous problems, we propose several possible directions and approaches to incorporate existing effective methods as components to enhance CNNs for the segmentation of specific semantic objects.

关 键 词：semantic image segmentation CNN Pascal VOC 2012 challenge multi-granularity features construction of contextual relationships 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]