Evolutionary Neural Architecture Search for Image Restoration
This work addresses the time-consuming and limited exploration of manual architecture design for image restoration, though it is incremental as it applies existing NAS concepts to a less explored domain.
The paper tackled the problem of automating neural architecture design for image restoration tasks, proposing an evolutionary neural architecture search method that achieved comparable performance to human-engineered baselines using only 2 GPU-hours of search.
Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture search (NAS) methods automatically search the space of neural network hyperparameters in order to find optimal task-specific architectures. NAS methods have discovered CNN architectures that achieve state-of-the-art performance in image classification among other tasks, however the application of NAS to image-to-image regression problems such as image restoration is sparse. This paper proposes a NAS method that performs computationally efficient evolutionary search of a minimally constrained network architecture search space. The performance of architectures discovered by the proposed method is evaluated on a variety of image restoration tasks applied to the ImageNet64x64 dataset, and compared with human-engineered CNN architectures. The best neural architectures discovered using only 2 GPU-hours of evolutionary search exhibit comparable performance to the human-engineered baseline architecture.