機械知覚&ロボティクスグループ
中部大学

Deep Learning 国際会議

Multiple Skip Connections and Dilated Convolutions for Semantic Segmentation

Author
Takayoshi Yamashita, Hironori Furukawa, Yuji Yamauchi, Hironobu Fujiyoshi
Publication
Workshop on IEEE Intelligent Vehicle Symposium, 2017

Download: PDF (English)

We propose a scale-aware semantic segmentation method specifically for small objects. The contributions of this method are 1) to feed the features of a small region by using multiple skip connections, and 2) to extract context from multiple receptive fields by using multiple dilated convolution blocks. The proposed method has achieved high accuracy in the Cityscapes dataset. In comparison with state-of-the-art methods, it has achieved a comparative performance in category IoU and iIoU metrics.

前の研究 次の研究