EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

2021-11-30 · Guohao Ying, Xin He, Bin Gao, Bo Han, Xiaowen Chu

Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying GAN architecture, it requires much expertise. Neural architecture search (NAS) has become an attractive solution to search GANs automatically. The early NAS-GANs search only generators to reduce search complexity but lead to a sub-optimal GAN. Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training. To alleviate the instability, we propose an efficient two-stage evolutionary algorithm-based NAS framework to search GANs, namely EAGAN. We decouple the search of G and D into two stages, where stage-1 searches G with a fixed D and adopts the many-to-one training strategy, and stage-2 searches D with the optimal G found in stage-1 and adopts the one-to-one training and weight-resetting strategies to enhance the stability of GAN training. Both stages use the non-dominated sorting method to produce Pareto-front architectures under multiple objectives (e.g., model size, Inception Score (IS), and Fr\'echet Inception Distance (FID)). EAGAN is applied to the unconditional image generation task and can efficiently finish the search on the CIFAR-10 dataset in 1.2 GPU days. Our searched GANs achieve competitive results (IS=8.81$\pm$0.10, FID=9.91) on the CIFAR-10 dataset and surpass prior NAS-GANs on the STL-10 dataset (IS=10.44$\pm$0.087, FID=22.18). Source code: https://github.com/marsggbo/EAGAN.

📄 PDF Abstract BibTeX arXiv:2111.15097

Code (1)

marsggbo/EAGAN 공식 구현 pytorch

Tasks

GPUImage Generation Neural Architecture SearchUnconditional Image GenerationVocal Bursts Valence Prediction

EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning

2023-08-19 · Shiming Chen, Shihuang Chen, Wenjin Hou, Weiping Ding 외

Zero-shot learning (ZSL) aims to recognize the novel classes which cannot be collected for training a prediction model. Accordingly, generative models (e.g., generative adversarial network (GAN)) are typically used to sy…

Generative Adversarial Network Neural Architecture Search Zero-Shot Learning

Personalized Early Stage Alzheimer's Disease Detection: A Case Study of President Reagan's Speeches

2020-05-08 · WS 2020 7 · Ning Wang, Fan Luo, Vishal Peddagangireddy, K. P. Subbalakshmi 외

Alzheimer`s disease (AD)-related global healthcare cost is estimated to be $1 trillion by 2050. Currently, there is no cure for this disease; however, clinical studies show that early diagnosis and intervention helps to …

Alzheimer's Disease Detection Anomaly Detection Clustering

On the Effectiveness of Adversarial Samples against Ensemble Learning-based Windows PE Malware Detectors

2023-09-25 · Trong-Nghia To, Danh Le Kim, Do Thi Thu Hien, Nghi Hoang Khoa 외

Recently, there has been a growing focus and interest in applying machine learning (ML) to the field of cybersecurity, particularly in malware detection and prevention. Several research works on malware analysis have bee…

Ensemble Learning Malware Analysis Malware Detection Reinforcement Learning (RL)

Graph Topological Features via GAN

2018-01-01 · ICLR 2018 1 · Weiyi Liu, Hal Cooper, Min-hwan Oh

Inspired by the success of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via …

Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis

2026-06-24 · Abrar Alotaibi, Moataz Ahmed arxiv

Neural Architecture Search (NAS) has emerged as a pivotal technique in optimizing the design of Generative Adversarial Networks (GANs), automating the search for effective architectures while addressing the challenges in…

Neural Architecture Search