Self Sparse Generative Adversarial Networks

01/26/2021
by   Wenliang Qian, et al.
0

Generative Adversarial Networks (GANs) are an unsupervised generative model that learns data distribution through adversarial training. However, recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem. In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. In the Self-Sparse GAN, we design a Self-Adaptive Sparse Transform Module (SASTM) comprising the sparsity decomposition and feature-map recombination, which can be applied on multi-channel feature maps to obtain sparse feature maps. The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator, which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps. We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the Batch Normalization layer and driving the weight of deconvolution layers away from being negative. The experimental results show that our method achieves the best FID scores for image generation compared with WGAN-GP on MNIST, Fashion-MNIST, CIFAR-10, STL-10, mini-ImageNet, CELEBA-HQ, and LSUN bedrooms, and the relative decrease of FID is 4.76

READ FULL TEXT

page 10

page 11

research
10/02/2018

On Self Modulation for Generative Adversarial Networks

Training Generative Adversarial Networks (GANs) is notoriously challengi...
research
11/22/2018

TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers

In this paper, we propose a novel method to efficiently train a Generati...
research
12/16/2022

Machine Learning and Polymer Self-Consistent Field Theory in Two Spatial Dimensions

A computational framework that leverages data from self-consistent field...
research
01/20/2019

Inducing Sparse Coding and And-Or Grammar from Generator Network

We introduce an explainable generative model by applying sparse operatio...
research
01/20/2023

Asynchronously Trained Distributed Topographic Maps

Topographic feature maps are low dimensional representations of data, th...
research
05/14/2020

Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs

In the generator of typical Generative Adversarial Networks (GANs), a no...
research
01/25/2018

Generative Adversarial Networks using Adaptive Convolution

Most existing GANs architectures that generate images use transposed con...

Please sign up or login with your details

Forgot password? Click here to reset