Hierarchical Neural Architecture Search for Single Image Super-Resolution

03/10/2020
by   Yong Guo, et al.
0

Deep neural networks have exhibited promising performance in image super-resolution (SR). Most SR models follow a hierarchical architecture that contains both the cell-level design of computational blocks and the network-level design of the positions of upsampling blocks. However, designing SR models heavily relies on human expertise and is very labor-intensive. More critically, these SR models often contain a huge number of parameters and may not meet the requirements of computation resources in real-world applications. To address the above issues, we propose a Hierarchical Neural Architecture Search (HNAS) method to automatically design promising architectures with different requirements of computation cost. To this end, we design a hierarchical SR search space and propose a hierarchical controller for architecture search. Such a hierarchical controller is able to simultaneously find promising cell-level blocks and network-level positions of upsampling layers. Moreover, to design compact architectures with promising performance, we build a joint reward by considering both the performance and computation cost to guide the search process. Extensive experiments on five benchmark datasets demonstrate the superiority of our method over existing methods.

READ FULL TEXT

page 1

page 4

research
05/09/2021

Lightweight Image Super-Resolution with Hierarchical and Differentiable Neural Architecture Search

Single Image Super-Resolution (SISR) tasks have achieved significant per...
research
01/17/2021

Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution

This paper proposes a trilevel neural architecture search (NAS) method f...
research
04/19/2021

Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS

The recent progress of deep convolutional neural networks has enabled gr...
research
09/27/2022

Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances

With the advent of Deep Learning (DL), Super-Resolution (SR) has also be...
research
02/02/2019

Transparent Concurrency Control: Decoupling Concurrency Control from DBMS

For performance reasons, conventional DBMSes adopt monolithic architectu...
research
01/22/2019

Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search

Deep convolution neural networks demonstrate impressive results in super...
research
01/04/2019

Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search

Fabricating neural models for a wide range of mobile devices demands for...

Please sign up or login with your details

Forgot password? Click here to reset