Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory

11/30/2022
by   Jing Tang, et al.
0

In recent years, multi-scale generative adversarial networks (GANs) have been proposed to build generalized image processing models based on single sample. Constraining on the sample size, multi-scale GANs have much difficulty converging to the global optimum, which ultimately leads to limitations in their capabilities. In this paper, we pioneered the introduction of PAC-Bayes generalized bound theory into the training analysis of specific models under different adversarial training methods, which can obtain a non-vacuous upper bound on the generalization error for the specified multi-scale GAN structure. Based on the drastic changes we found of the generalization error bound under different adversarial attacks and different training states, we proposed an adaptive training method which can greatly improve the image manipulation ability of multi-scale GANs. The final experimental results show that our adaptive training method in this paper has greatly contributed to the improvement of the quality of the images generated by multi-scale GANs on several image manipulation tasks. In particular, for the image super-resolution restoration task, the multi-scale GAN model trained by the proposed method achieves a 100 reduction in root mean squared error (RMSE), which is better than many models trained on large-scale datasets.

READ FULL TEXT

page 5

page 7

page 8

page 9

page 11

research
03/14/2019

MSG-GAN: Multi-Scale Gradient GAN for Stable Image Synthesis

While Generative Adversarial Networks (GANs) have seen huge successes in...
research
03/31/2021

Generating Multi-scale Maps from Remote Sensing Images via Series Generative Adversarial Networks

Considering the success of generative adversarial networks (GANs) for im...
research
10/09/2022

A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis

Imbalanced image datasets are commonly available in the domain of biomed...
research
11/01/2018

Bi-GANs-ST for Perceptual Image Super-resolution

Image quality measurement is a critical problem for image super-resoluti...
research
09/08/2023

On the Efficacy of Multi-scale Data Samplers for Vision Applications

Multi-scale resolution training has seen an increased adoption across mu...
research
03/22/2018

Branched Generative Adversarial Networks for Multi-Scale Image Manifold Learning

We introduce BranchGAN, a novel training method that enables uncondition...
research
06/02/2020

Asymptotically Scale-invariant Multi-resolution Quantization

A multi-resolution quantizer is a sequence of quantizers where the outpu...

Please sign up or login with your details

Forgot password? Click here to reset