GP-NAS: Gaussian process based neural architecture search
File(s)
Author(s)
Type
Conference Paper
Abstract
Neural architecture search (NAS) advances beyond the state-of-the-art in various computer vision tasks by automating the designs of deep neural networks. In this paper, we aim to address three important questions in NAS: (1) How to measure the correlation between architectures and their performances? (2) How to evaluate the correlation between different architectures? (3) How to learn these correlations with a small number of samples? To this end, we first model these correlations from a Bayesian perspective. Specifically, by introducing a novel Gaussian Process based NAS (GP-NAS) method, the correlations are modeled by the kernel function and mean function. The kernel function is also learnable to enable adaptive modeling for complex correlations in different search spaces. Furthermore, by incorporating a mutual information based sampling method, we can theoretically ensure the high-performance architecture with only a small set of samples. After addressing these problems, training GP-NAS once enables direct performance prediction of any architecture in different scenarios and may obtain efficient networks for different deployment platforms. Extensive experiments on both image classification and face recognition tasks verify the effectiveness of our algorithm.
Date Issued
2020-08-05
Date Acceptance
2020-06-14
Citation
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp.11930-11939
ISSN
1063-6919
Publisher
IEEE Computer Society
Start Page
11930
End Page
11939
Journal / Book Title
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2020 IEEE. This ICCV workshop paper is the Open Access version, provided by the Computer Vision Foundation. Except for the watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.
Source
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Science & Technology
Technology
Publication Status
Published
Start Date
2020-06-14
Finish Date
2020-06-19
Coverage Spatial
Seattle, WA, USA (virtual)