AdversarialNAS: Adversarial Neural Architecture Search for GANs

By Chen Gao, Yunpeng Chen, Si Liu, Zhenxiong Tan, Shuicheng Yan. 2019

95 citations recorded by the source corpus.

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 tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation. The AdversarialNAS is the first method that can search the architectures of generator and discriminator simultaneously in a differentiable manner. During searching, the designed adversarial search algorithm does not need to comput any extra metric to evaluate the performance of the searched architecture, and the search paradigm considers the relevance between the two network architectures and improves their mutual balance. Therefore, AdversarialNAS is very efficient and only takes 1 GPU day to search for a superior generative model in the proposed large search space. Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of 10.87 and highly competitive Inception Score of 8.74 on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of 26.98 and Inception score of 9.63 on STL-10. Code is at: https://github.com/chengaopro/AdversarialNAS.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhangyang Wang
2. Shiyu Chang
3. Chen Gao
4. Qi Wu
5. Jinyu Chen
6. Qiong Zhang
7. Luting Wang
8. Si Liu

In Computer Vision and Pattern Recognition

1. Zhangyang Wang
2. Shiyu Chang
3. Chen Gao
4. Qi Wu
5. Si Liu
6. Jinyu Chen
7. Qiong Zhang
8. Luting Wang

Citations in the corpus

• TransGAN: Two Transformers Can Make One Strong GAN (2021, background): “Those works are consistently able to discover stronger GAN architectures beyond the standard ResNet topology (Gong et al., 2019; Gao et al., 2020; Tian et al., 2020).”
• Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression (2021, background): “There has been growing interest in combining computer vision [31, 13, 9, 23, 15, 14, 29, 3, 4] and natural language processing [8, 45] techniques to perform vision-language cross-modal tasks [30, 38, 21, 22].”
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up (2021, background): “As shown in Table 1, TransGAN surpasses the strong model of Progressive GAN [16], and many other latest competitors such as SN-GAN [48], AutoGAN [18], and AdversarialNAS-GAN [19], in terms of inception score (IS).”