Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory
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 natural image quality evaluator (NIQE) and a 60% reduction in root mean squared error (RMSE), which is better than many models trained on large-scale datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ManipulationImage Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
ASAT: Adaptively Scaled Adversarial Training in Time Series
Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improv…
Adversarial RobustnessTime SeriesTime Series AnalysisRevisiting the Robust Generalization of Adversarial Prompt Tuning
Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art d…
Adversarial RobustnessPrompt LearningZero-shot GeneralizationBetter Generalization with Adaptive Adversarial Training
An effective method to obtain an adversarial robust network is to train the network with adversarially perturbed samples. Perturbing all the samples adversarially has shown to increase the robustness of the networks sign…
Adversarial RobustnessEfficient Adversarial Training via Criticality-Aware Fine-Tuning
Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalability enables ViT models to exhibit stro…
parameter-efficient fine-tuningAdversarial RobustnessTwo-flow Feedback Multi-scale Progressive Generative Adversarial Network
Although diffusion model has made good progress in the field of image generation, GAN\cite{huang2023adaptive} still has a large development space due to its unique advantages, such as WGAN\cite{liu2021comparing}, SSGAN\c…
Image Generation