Searching Efficient Model-guided Deep Network for Image Denoising

TL;DR

This paper introduces MoD-NAS, a model-guided neural architecture search method for image denoising that automatically designs efficient networks with superior performance and fewer resources, addressing the optimization gap in NAS.

Contribution

It proposes a novel model-guided search space and stable differential search strategies for NAS in image denoising, improving efficiency and performance.

Findings

Achieves better PSNR than state-of-the-art methods.

Uses fewer parameters and less computation.

Demonstrates faster testing times.

Abstract

Neural architecture search (NAS) has recently reshaped our understanding on various vision tasks. Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance. However, the optimization gap between the super-network and the sub-architectures has remained an open issue in both low-level and high-level vision. In this paper, we present a novel approach to filling in this gap by connecting model-guided design with NAS (MoD-NAS) and demonstrate its application into image denoising. Specifically, we propose to construct a new search space under model-guided framework and develop more stable and efficient differential search strategies. MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer as well as network width and depth via gradient descent. During the search process, the proposed MoG-NAS is capable of avoiding mode collapse due to the smoother search space designed under the model-guided framework. Experimental results on several popular datasets show that our MoD-NAS has achieved even better PSNR performance than current state-of-the-art methods with fewer parameters, lower number of flops, and less amount of testing time.