Generalized Loss-Sensitive Adversarial Learning with Manifold Margins
The classic Generative Adversarial Net and its variants can be roughly categorized into two large families: the unregularized ver- sus regularized GANs. By relaxing the non-parametric assumption on the discriminator in the classic GAN, the regularized GANs have better generalization ability to produce new samples drawn from the real dis- tribution. It is well known that the real data like natural images are not uniformly distributed over the whole data space. Instead, they are often restricted to a low-dimensional manifold of the ambient space. Such a manifold assumption suggests the distance over the manifold should be a better measure to characterize the distinct between real and fake sam- ples. Thus, we define a pullback operator to map samples back to their data manifold, and a manifold margin is defined as the distance between the pullback representations to distinguish between real and fake sam- ples and learn the optimal generators. We justify the effectiveness of the proposed model both theoretically and empirically.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
In this paper, we present the Lipschitz regularization theory and algorithms for a novel Loss-Sensitive Generative Adversarial Network (LS-GAN). Specifically, it trains a loss function to distinguish between real and fak…
Generative Adversarial Networkimage-classificationImage ClassificationImage GenerationLEARNING ADVERSARIAL EXAMPLES WITH RIEMANNIAN GEOMETRY
Adversarial examples, referred to as augmented data points generated by imperceptible perturbation of input samples, have recently drawn much attention. Well-crafted adversarial examples may even mislead state-of-the-art…
Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose Manifold-…
Adversarial RobustnessSpatially Decomposed Hinge Adversarial Loss by Local Gradient Amplifier
Generative Adversarial Networks (GANs) have achieved large attention and great success in various research areas, but it still suffers from training instability. Recently hinge adversarial loss for GAN is proposed that i…
One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
This paper proposes a new loss function for adversarial training. Since adversarial training has difficulties, e.g., necessity of high model capacity, focusing on important data points by weighting cross-entropy loss has…
Adversarial Robustness