Evolutionary Neural Architecture Search for Image Restoration

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-03
Main Authors: Gerard Jacques van Wyk, Bosman, Anna Sergeevna
Format: Article
Language:English
Subjects:
Artificial neural networks
Evolution
Human performance
Image classification
Image restoration
Neural networks
Search process
State of the art
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422