AutoGAN: Neural Architecture Search for Generative Adversarial Networks

2019-08-11 · ICCV 2019 10 · Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang

Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the first preliminary study on introducing the NAS algorithm to generative adversarial networks (GANs), dubbed AutoGAN. The marriage of NAS and GANs faces its unique challenges. We define the search space for the generator architectural variations and use an RNN controller to guide the search, with parameter sharing and dynamic-resetting to accelerate the process. Inception score is adopted as the reward, and a multi-level search strategy is introduced to perform NAS in a progressive way. Experiments validate the effectiveness of AutoGAN on the task of unconditional image generation. Specifically, our discovered architectures achieve highly competitive performance compared to current state-of-the-art hand-crafted GANs, e.g., setting new state-of-the-art FID scores of 12.42 on CIFAR-10, and 31.01 on STL-10, respectively. We also conclude with a discussion of the current limitations and future potential of AutoGAN. The code is available at https://github.com/TAMU-VITA/AutoGAN

📄 PDF Abstract BibTeX arXiv:1908.03835

Code (2)

TAMU-VITA/AutoGAN 공식 구현 pytorch

VITA-Group/AutoGAN pytorch

Tasks

image-classification Image Classification Image Generation Neural Architecture SearchUnconditional Image Generation

Methods 이 논문이 사용한 방법론

AutoGAN 설명 없음

AutoGAN: Robust Classifier Against Adversarial Attacks

2018-12-08 · Blerta Lindqvist, Shridatt Sugrim, Rauf Izmailov

Classifiers fail to classify correctly input images that have been purposefully and imperceptibly perturbed to cause misclassification. This susceptability has been shown to be consistent across classifiers, regardless o…

Generative Adversarial Network

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks

2020-06-15 · ICML 2020 1 · Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li 외

The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement a…

AutoML Knowledge Distillation Super-Resolution Translation

Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration

2023-01-01 · CVPR 2023 1 · Divya Saxena, Jiannong Cao, Jiahao Xu, Tarun Kulshrestha

Training Generative Adversarial Networks (GANs) on high-fidelity images usually requires a vast number of training images. Recent research on GAN tickets reveals that dense GANs models contain sparse sub-networks or …

Image Generation

AdversarialNAS: Adversarial Neural Architecture Search for GANs

2019-12-04 · CVPR 2020 6 · Chen Gao, Yunpeng Chen, Si Liu, Zhenxiong Tan 외

Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tail…

GPU Image Generation Neural Architecture Search Unconditional Image Generation

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