"Multi-SelfGAN: A Self-Guiding Neural Architecture Search Method for Ge" by Jiachen Shi, Guoqiang Zhou et al.
In recent years, Reinforcement Learning and Gradient optimization were applied with Neural Architecture Search algorithms in Generative Adversarial Network to achieve their state-of-the-art (SOTA) performance. However, the existing RL-based methods utilised the calculation of Inception Score or Fréchet Inception Distance as the reward value to guide the controller, which actually wasted much of searching time. In order to improve the search efficiency without degradation of performance, this paper proposes recycling the discriminator to evaluate the performance of architectures, in other word...
Source: uow.edu.au