Generative Convolution Layer for Image Generation

11/30/2021
by   Seung Park, et al.
0

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.

READ FULL TEXT

page 2

page 9

page 10

research
01/27/2022

Effective Shortcut Technique for GAN

In recent years, generative adversarial network (GAN)-based image genera...
research
01/19/2021

Generative Adversarial Network using Perturbed-Convolutions

Despite growing insights into the GAN training, it still suffers from in...
research
06/03/2019

cGANs with Conditional Convolution Layer

Conditional generative adversarial networks (cGANs) have been widely res...
research
12/30/2021

A Novel Generator with Auxiliary Branch for Improving GAN Performance

The generator in the generative adversarial network (GAN) learns image g...
research
04/20/2023

Adaptive Consensus Optimization Method for GANs

We propose a second order gradient based method with ADAM and RMSprop fo...
research
10/18/2022

IF-GAN: A Novel Generator Architecture with Information Feedback

This paper presents an alternative generator architecture for image gene...
research
01/26/2022

Image Generation with Self Pixel-wise Normalization

Region-adaptive normalization (RAN) methods have been widely used in the...

Please sign up or login with your details

Forgot password? Click here to reset