Semantic Segmentation by Improved Generative Adversarial Networks

TL;DR

This paper introduces an improved GAN-based approach for semantic segmentation that integrates convolutional CRFs and a specially designed discriminator to produce more detailed and accurate segmentation results, surpassing existing methods.

Contribution

The paper proposes a novel GAN architecture with convolutional CRFs and a cascaded discriminator for end-to-end semantic segmentation, enhancing detail and accuracy over prior techniques.

Findings

Achieves better segmentation performance than state-of-the-art methods.

Effectively incorporates convolutional CRFs into GAN framework.

Produces more detailed segmentation outputs.

Abstract

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.