CDE-GAN: Cooperative Dual Evolution-Based Generative Adversarial Network (2020-08-21T00:00:00.000000Z)

TL;DR

Extensive experiments demonstrate that the proposed CDE-GAN achieves the competitive and superior performance in generating good quality and diverse samples over baselines, and to improve generative performance.

Abstract

Generative adversarial networks (GANs) have been a popular deep generative model for real-world applications. Despite many recent efforts on GANs that have been contributed, mode collapse and instability of GANs are still open problems caused by their adversarial optimization difficulties. In this article, motivated by the cooperative co-evolutionary algorithm, we propose a cooperative dual evolution-based GAN (CDE-GAN) to circumvent these drawbacks. In essence, CDE-GAN incorporates dual evolution with respect to the generator(s) and discriminators into a unified evolutionary adversarial framework to conduct effective adversarial multiobjective optimization. Thus, it exploits the complementary properties and injects dual mutation diversity into the training, to steadily diversify the estimated density in capturing multimodes and improve generative performance. Specifically, CDE-GAN decomposes the complex adversarial optimization problem into two subproblems (generation and discrimination), and each subproblem is solved with a separated subpopulation (E-Generators and E-Discriminators), evolved by its own evolutionary algorithm. Additionally, we further propose a Soft Mechanism to balance the tradeoff between E-Generators and E-Discriminators to conduct steady training for CDE-GAN. Extensive experiments on one synthetic dataset and three real-world benchmark image datasets demonstrate that the proposed CDE-GAN achieves a competitive and superior performance in generating good quality and diverse samples over baselines. The code and more generated results are available at our project homepage https://shiming-chen.github.io/CDE-GAN-website/CDE-GAN.html.

Authors

References58 items

Generative Adversarial Networks

Completely Automated CNN Architecture Design Based on Blocks

Novel Prediction Strategies for Dynamic Multiobjective Optimization

Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor

Re-purposing heterogeneous generative ensembles with evolutionary computation

microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination

CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation

COEGAN: evaluating the coevolution effect in generative adversarial networks

Deep Neuro-Cognitive Co-Evolution for Fuzzy Attribute Reduction by Quantum Leaping PSO With Nearest-Neighbor Memeplexes

Spatial evolutionary generative adversarial networks

A dynamic multiobjective evolutionary algorithm based on a dynamic evolutionary environment model

Dynamic Cooperative Coevolution for Large Scale Optimization

Multi-objective training of Generative Adversarial Networks with multiple discriminators

Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification

Online Adaptative Curriculum Learning for GANs

Towards Distributed Coevolutionary GANs

Cooperative Co-Evolution-Based Design Optimization: A Concurrent Engineering Perspective

Evolutionary Generative Adversarial Networks

MGAN: Training Generative Adversarial Nets with Multiple Generators

Spectral Normalization for Generative Adversarial Networks

On the Effectiveness of Least Squares Generative Adversarial Networks

A Particle Swarm Optimization-Based Flexible Convolutional Autoencoder for Image Classification

Evolving Unsupervised Deep Neural Networks for Learning Meaningful Representations

Evolving Deep Convolutional Neural Networks for Image Classification

Dual Discriminator Generative Adversarial Nets

MoCoGAN: Decomposing Motion and Content for Video Generation

Wasserstein Generative Adversarial Networks

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

Gradient descent GAN optimization is locally stable

Stabilizing GAN Training with Multiple Random Projections

Multi-agent Diverse Generative Adversarial Networks

Improved Training of Wasserstein GANs

BEGAN: Boundary Equilibrium Generative Adversarial Networks

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

Towards Principled Methods for Training Generative Adversarial Networks

AdaGAN: Boosting Generative Models

NIPS 2016 Tutorial: Generative Adversarial Networks

Least Squares Generative Adversarial Networks

Improving Generative Adversarial Networks with Denoising Feature Matching

Unrolled Generative Adversarial Networks

Generative Multi-Adversarial Networks

Cooperative Training of Descriptor and Generator Networks

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Improved Techniques for Training GANs

Machine Learning for Evolution Strategies

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

Deep Learning Face Attributes in the Wild

Cooperative Co-Evolution With Differential Grouping for Large Scale Optimization

A Competitive-Cooperative Coevolutionary Paradigm for Dynamic Multiobjective Optimization

Automatically Designing CNN Architectures Using Genetic Algorithm for Image Classification

Huazhong University of Sciences and Technology(HUST), China. He received the B.E. degree in College of

University of Birmingham Cooperative co-evolutionary module identification with application to cancer disease module discovery

Learning Multiple Layers of Features from Tiny Images

Multi-objective optimization using evolutionary algorithms

His research results have expounded in 20+ publications at prestigious journals and prominent conferences, such as IEEE

His current research interests span computer vision and machine learning with a series of topics, such as generative modeling and learning