Semantic segmentation with multi-path refinement and pyramid pooling dilated-resnet

Zhipeng Cui, Qiao Zhang, Shijie Geng, Xiaoguang Niu, Jie Yang, Yu Qiao

Abstract

Recently, fully convolutional network (FCN) and dilated convolution have shown significantly improvment in semantic segmentation task. Deep residual network (ResNet) has shown strong ability in object recognition. However, FCN-based methods utilize intermediate layers and spatial context information ineffectively. Repeated 2-step striding in ResNet is harmful for segmentation tasks. In this paper, we propose a new semantic segmentation method based on FCN and ResNet. Here, we combine the dilated convolution designed for semantic segmentation with residual unit to enlarge receptive field of ResNet. Meanwhile, “pre-activation” method is used in dilated residual unit. We propose a new segmentation architecture which intergrate multiple intermediate layers and global context information. We extract low-level features of intermediate layers with multi-path refinement which consists of relu-conv unit and chained residual pooling. Global context is gathered by a pyramid pooling method which is connected to the final output of ResNet. Outputs of these 2 modules are then fused to reach high-resolution prediction. In this way, global and local information from pyramid pooling can be enhanced by multi-path refinement. Fully-connected conditional random field is added as a “post-processing” after fusion to receive accurate boundary performance. Our proposed approach achieves 74.7% IoU on Cityscapes benchmark.
BibTeX
@inproceedings{cui2017semantic,
  author = {Zhipeng Cui and Qiao Zhang and Shijie Geng and Xiaoguang Niu and Jie Yang and Yu Qiao},
  title = {{Semantic segmentation with multi-path refinement and pyramid pooling dilated-resnet}},
  booktitle = {ICIP},
  year = {2017},
  doi = {10.1109/icip.2017.8296853},
}

Loading related content...

Figure