Authors:Hyunwoo Kim¹;Huaiyu Li² andSeok-Cheol Kee³

Affiliations:¹Beijing Advanced Innovation Center for Intelligent Robotics and Systems, Beijing Institute of Technology, Beijing and China;²National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing and China;³Smart Car Research Center, Chungbuk National University, Cheongju and South Korea

Keyword(s):Convolutional Network, Joint Training, Global Context, Semantic Scene Segmentation.

Abstract:The state-of-the-art semantic segmentation tasks can be achieved by the variants of the fully convolutional neural networks (FCNs), which consist of the feature encoding and the deconvolution. However, they struggle with missing or inconsistent labels. To alleviate these problems, we utilize the image-level multi-class encoding as the global contextual information. By incorporating object classification into the objective function, we can reduce incorrect pixel-level segmentation. Experimental results show that our algorithm can achieve better performance than other methods on the same level training data volume.