Authors:Yuki Hiramatsu andKazuhiro Hotta

Affiliation:Meijo University, Japan

Keyword(s):Semantic Segmentation, Attention Mechanism, Encoder-decoder Structure.

Abstract:Semantic segmentation using convolutional neural networks (CNN) can be applied to various fields such as automatic driving. Semantic segmentation is pixel-wise class classification, and various methods using CNN have been proposed. We introduce a light attention mechanism to the encoder-decoder network. The network that introduced a light attention mechanism pays attention to features extracted during training, emphasizes the features judged to be effective for training and suppresses the features judged to be irrelevant for each pixel. As a result, training can be performed by focusing on only necessary features. We evaluated the proposed method using the CamVid dataset and obtained higher accuracy than conventional segmentation methods.