BRIDGING ADVERSARIAL SAMPLES AND ADVERSARIAL NETWORKS
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from sensitivity to hyper-parameters, training instability, and mode collapse. We find that this is partly due to gradient given by non-robust discriminator containing non-informative adversarial noise, which can hinder generator from catching the pattern of real samples. Inspired by defense against adversarial samples, we introduce adversarial training of discriminator on real samples that does not exist in classic GANs framework to make adversarial training symmetric, which can balance min-max game and make discriminator more robust. Robust discriminator can give more informative gradient with less adversarial noise, which can stabilize training and accelerate convergence. We validate the proposed method on image generation tasks with varied network architectures quantitatively. Experiments show that training stability, perceptual quality, and diversity of generated samples are consistently improved with small additional training computation cost.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityImage GenerationSimilar Papers 제목 키워드 기반
Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve training stability, this issue remains as a…
Image GenerationBridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense
Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of the recent advancements in the …
Adversarial AttackAdversarial DefenseAdversarial RobustnessAdversarial-based neural networks for affect estimations in the wild
There is a growing interest in affective computing research nowadays given its crucial role in bridging humans with computers. This progress has been recently accelerated due to the emergence of bigger data. One recent a…
Your Classifier Can Do More: Towards Bridging the Gaps in Classification, Robustness, and Generation
Joint Energy-based Models (JEMs), a class of hybrid generative-discriminative models, are well known for their ability to achieve both high classification accuracy and generative capability within a single model. However…
Adversarial RobustnessQuantum Adversarial Machine Learning
Adversarial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings and developing techniques accordingly to make learning robust to adversari…
BIG-bench Machine LearningQuantum Machine Learning