Tian, Y;
Wang, Q;
Huang, Z;
Li, W;
Dai, D;
Yang, M;
Wang, J;
(2020)
Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search.
In:
Computer Vision – ECCV 2020. ECCV 2020.
(pp. pp. 175-192).
Springer: Cham, Switzerland.
![[thumbnail of 123520171.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
123520171.pdf - Accepted Version Download (1MB) |
Abstract
In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is able to discover highly competitive architectures for generally better image generation results with a considerably reduced computational burden: 7 GPU hours. Our code is available at https://github.com/Yuantian013/E2GAN.
| Type: | Proceedings paper |
|---|---|
| Title: | Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search |
| Event: | European Conference on Computer - Vision ECCV 2020: Computer Vision – ECCV 2020 |
| ISBN-13: | 9783030585709 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-030-58571-6_11 |
| Publisher version: | http://dx.doi.org/10.1007/978-3-030-58571-6_11 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Neural architecture search, Generative adversarial networks, Reinforcement learning, Markov decision process, Off-policy |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10118102 |
Archive Staff Only
 |
View Item |
