CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization
This addresses the issue of discriminator overfitting and unstable training in data-efficient GANs for image generation, though it is incremental as it builds on existing normalization techniques.
The paper tackles the problem of GANs struggling with limited training data by proposing CHAIN, a normalization method that replaces batch normalization's centering step with zero-mean regularization and adds a Lipschitz constraint, achieving state-of-the-art results on datasets like CIFAR-10/100 and ImageNet in data-limited scenarios.
Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overfitting and unstable training. Batch Normalization (BN), despite being known for enhancing generalization and training stability, has rarely been used in the discriminator of Data-Efficient GANs. Our work addresses this gap by identifying a critical flaw in BN: the tendency for gradient explosion during the centering and scaling steps. To tackle this issue, we present CHAIN (lipsCHitz continuity constrAIned Normalization), which replaces the conventional centering step with zero-mean regularization and integrates a Lipschitz continuity constraint in the scaling step. CHAIN further enhances GAN training by adaptively interpolating the normalized and unnormalized features, effectively avoiding discriminator overfitting. Our theoretical analyses firmly establishes CHAIN's effectiveness in reducing gradients in latent features and weights, improving stability and generalization in GAN training. Empirical evidence supports our theory. CHAIN achieves state-of-the-art results in data-limited scenarios on CIFAR-10/100, ImageNet, five low-shot and seven high-resolution few-shot image datasets. Code: https://github.com/MaxwellYaoNi/CHAIN