Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation

By Haitian Zheng, Yebin Liu, Mengqi Ji, Feng Wu, Lu Fang. 2015

10 citations recorded by the source corpus.

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level coding, middle-level segmentation and low-level image to introduce global prior for semantic segmentation. Based on this structure, we proposed a generative model called conditional variational auto-encoder (CVAE) that can build up the links behind these three layers. These important links include an image encoder that extracts high level info from image, a segmentation encoder that extracts high level info from segmentation, and a hybrid decoder that outputs semantic segmentation from the high level prior and input image. We theoretically derive the semantic segmentation as an optimization problem parameterized by these links. Finally, the optimization problem enables us to take advantage of state-of-the-art fully convolutional network structure for the implementation of the above encoders and decoder. Experimental results on several representative datasets demonstrate our supreme performance for semantic segmentation.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Luc Van Gool
3. Liang Lin
4. Ping Luo
5. Yi Yang
6. Dacheng Tao
7. Ming-Hsuan Yang
8. Bernt Schiele

Citations in the corpus

• Convolutional Neural Fabrics (2016, methodology): “Finally, we analyze the number of response maps, parameters, and activations of fabrics in Section 3.3.”
• Deep Dual Learning for Semantic Image Segmentation (2017, methodology): “Network Input Network Output Latent Representation GAN [11] labelmap image coding AE [1] image labelmap coding VAE [29] coding + image labelmap coding DIS (ours) image labelmap + image labelmap + clean tags”