A self-adapting super-resolution structures framework for automatic design of GAN
This work addresses hyperparameter tuning for super-resolution image reconstruction, offering an incremental improvement by automating a process previously reliant on expert knowledge or brute-force search.
The paper tackles the problem of designing complex super-resolution GANs by introducing a framework that uses Bayesian optimization to automatically tune hyperparameters like network layers and neurons, reducing manual effort; experiments show it finds optimal solutions faster than other algorithms.
With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the models have a greater impact on model performance. In the existing works, experts have gradually explored a set of optimal model parameters based on empirical values or performing brute-force search. In this paper, we introduce a new super-resolution image reconstruction generative adversarial network framework, and a Bayesian optimization method used to optimizing the hyperparameters of the generator and discriminator. The generator is made by self-calibrated convolution, and discriminator is made by convolution lays. We have defined the hyperparameters such as the number of network layers and the number of neurons. Our method adopts Bayesian optimization as a optimization policy of GAN in our model. Not only can find the optimal hyperparameter solution automatically, but also can construct a super-resolution image reconstruction network, reducing the manual workload. Experiments show that Bayesian optimization can search the optimal solution earlier than the other two optimization algorithms.