Generative Convolution Layer for Image Generation

TL;DR

This paper proposes a new generative convolution method (GConv) that enhances GAN performance by creating latent-specific kernels, leading to higher quality image generation with minimal additional hardware cost.

Contribution

The paper introduces GConv, a simple yet effective convolution technique that improves GANs without altering existing architectures.

Findings

GConv significantly improves Inception scores and FID across multiple datasets.

GConv enhances both unconditional and conditional GANs.

Experimental results demonstrate superior image quality with minimal hardware overhead.

Abstract

This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) performance. Unlike the standard convolution, GConv first selects useful kernels compatible with the given latent vector, and then linearly combines the selected kernels to make latent-specific kernels. Using the latent-specific kernels, the proposed method produces the latent-specific features which encourage the generator to produce high-quality images. This approach is simple but surprisingly effective. First, the GAN performance is significantly improved with a little additional hardware cost. Second, GConv can be employed to the existing state-of-the-art generators without modifying the network architecture. To reveal the superiority of GConv, this paper provides extensive experiments using various standard datasets including CIFAR-10, CIFAR-100, LSUN-Church, CelebA, and tiny-ImageNet. Quantitative evaluations prove that GConv significantly boosts the performances of the unconditional and conditional GANs in terms of Inception score (IS) and Frechet inception distance (FID). For example, the proposed method improves both FID and IS scores on the tiny-ImageNet dataset from 35.13 to 29.76 and 20.23 to 22.64, respectively.