[3D2-OS-12b] 創作者と人工知能が創る創作の未来(2/3)

[3D2-OS-12b-03] Free Configurational Atrous Convolution for Semantic Segmentation

〇Ryoma Okamoto¹, Akira Terauchi¹, Naoki Mori¹, Makoto Okada¹ (1. Osaka Prefecture University)

Keywords:Deep learning, Semantic segmentation, Image recognition, Atrous convolution, Comic understanding

In recent years, semantic segmentation by DeepLabv3+ has attracted much attention. One of the features of this model is atrous convolution, which adjusts the convolutional range of filter (field-of-view of filter) by dilating its convolutional position (viewpoints of filter). However, previous atrous convolution considers only adjusting field-of-view of filter and does not consider adjusting viewpoints of filter. In this paper, we propose free configurational atrous convolution, which is an extension of the viewpoint placement method in previous atrous convolution, and semantic segmentation based on this method. In the proposed method, we first partition viewpoints in the 3 × 3 convolutional filter into two groups. Next, we applied atrous convolution with different rates to the filters. Then, by adding the outputs, we realized the convolution with the adjustment of field-of-view of filter and viewpoints of filter. The effectiveness of the proposed method is confirmed by computer simulations taking the benchmark dataset of semantic segmentation as an example.