CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics
This work addresses mode collapse in GANs for image generation, offering an incremental improvement over existing MMD-based methods.
The authors tackled the problem of mode collapse in generative adversarial networks (GANs) by proposing CKGAN, a variant based on characteristic kernel integral probability metrics, which generally outperformed other MMD-based GANs on benchmarks like MNIST and CelebA, with automatically selected kernels delivering performance close to manually fine-tuned ones.
In this paper, we propose CKGAN, a novel generative adversarial network (GAN) variant based on an integral probability metrics framework with characteristic kernel (CKIPM). CKIPM, as a distance between two probability distributions, is designed to optimize the lowerbound of the maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space, and thus can be used to train GANs. CKGAN mitigates the notorious problem of mode collapse by mapping the generated images back to random noise. To save the effort of selecting the kernel function manually, we propose a soft selection method to automatically learn a characteristic kernel function. The experimental evaluation conducted on a set of synthetic and real image benchmarks (MNIST, CelebA, etc.) demonstrates that CKGAN generally outperforms other MMD-based GANs. The results also show that at the cost of moderately more training time, the automatically selected kernel function delivers very close performance to the best of manually fine-tuned one on real image benchmarks and is able to improve the performances of other MMD-based GANs.