ABCAS: Adaptive Bound Control of spectral norm as Automatic Stabilizer
This work addresses training stability issues in GANs for image generation, offering an incremental improvement over existing spectral normalization methods.
The paper tackles the instability in training Generative Adversarial Networks (GANs) by proposing ABCAS, an adaptive stabilizer that adjusts the discriminator's Lipschitz constant based on dataset characteristics, resulting in improved stability and better Fréchet Inception Distance scores for generated images.
Spectral Normalization is one of the best methods for stabilizing the training of Generative Adversarial Network. Spectral Normalization limits the gradient of discriminator between the distribution between real data and fake data. However, even with this normalization, GAN's training sometimes fails. In this paper, we reveal that more severe restriction is sometimes needed depending on the training dataset, then we propose a novel stabilizer which offers an adaptive normalization method, called ABCAS. Our method decides discriminator's Lipschitz constant adaptively, by checking the distance of distributions of real and fake data. Our method improves the stability of the training of Generative Adversarial Network and achieved better Fréchet Inception Distance score of generated images. We also investigated suitable spectral norm for three datasets. We show the result as an ablation study.