Graph-FCN for image semantic segmentation
This work addresses semantic segmentation for computer vision applications, but it is incremental as it builds on existing FCN and graph convolutional network methods.
The paper tackles the problem of semantic segmentation by addressing the loss of local location information in high-level features, proposing Graph-FCN which transforms image data into a graph structure and uses graph convolutional networks for node classification. It achieves a 1.34% improvement in mIOU on the VOC dataset compared to the original FCN model.
Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is important for image semantic segmentation. To avoid this problem, we propose a graph model initialized by a fully convolutional network (FCN) named Graph-FCN for image semantic segmentation. Firstly, the image grid data is extended to graph structure data by a convolutional network, which transforms the semantic segmentation problem into a graph node classification problem. Then we apply graph convolutional network to solve this graph node classification problem. As far as we know, it is the first time that we apply the graph convolutional network in image semantic segmentation. Our method achieves competitive performance in mean intersection over union (mIOU) on the VOC dataset(about 1.34% improvement), compared to the original FCN model.