Alert button
Picture for ZengShun Zhaoa

ZengShun Zhaoa

Alert button

Shandong University of Science and Technology

Semantic Segmentation by Improved Generative Adversarial Networks

Apr 20, 2021
ZengShun Zhaoa, Yulong Wang, Ke Liu, Haoran Yang, Qian Sun, Heng Qiao

Figure 1 for Semantic Segmentation by Improved Generative Adversarial Networks
Figure 2 for Semantic Segmentation by Improved Generative Adversarial Networks
Figure 3 for Semantic Segmentation by Improved Generative Adversarial Networks
Figure 4 for Semantic Segmentation by Improved Generative Adversarial Networks

While most existing segmentation methods usually combined the powerful feature extraction capabilities of CNNs with Conditional Random Fields (CRFs) post-processing, the result always limited by the fault of CRFs . Due to the notoriously slow calculation speeds and poor efficiency of CRFs, in recent years, CRFs post-processing has been gradually eliminated. In this paper, an improved Generative Adversarial Networks (GANs) for image semantic segmentation task (semantic segmentation by GANs, Seg-GAN) is proposed to facilitate further segmentation research. In addition, we introduce Convolutional CRFs (ConvCRFs) as an effective improvement solution for the image semantic segmentation task. Towards the goal of differentiating the segmentation results from the ground truth distribution and improving the details of the output images, the proposed discriminator network is specially designed in a full convolutional manner combined with cascaded ConvCRFs. Besides, the adversarial loss aggressively encourages the output image to be close to the distribution of the ground truth. Our method not only learns an end-to-end mapping from input image to corresponding output image, but also learns a loss function to train this mapping. The experiments show that our method achieves better performance than state-of-the-art methods.

* arXiv admin note: text overlap with arXiv:1802.07934 by other authors 
Viaarxiv icon