PCA compression of image deblurring neural networks

Greig Richmond; Arlene Cole-Rhodes

doi:10.1117/12.2600055

12 September 2021 PCA compression of image deblurring neural networks

Greig Richmond, Arlene Cole-Rhodes

Proceedings Volume 11870, Artificial Intelligence and Machine Learning in Defense Applications III; 118700P (2021) https://doi.org/10.1117/12.2600055
Event: SPIE Security + Defence, 2021, Online Only

Conference Poster

Abstract

In this work, we describe the compression of an image restoration neural network using principal component analysis (PCA). We compress the SRN-Deblur network that was developed by Tao et al.1 and we evaluate the deblurring performance at various levels of compression quantitatively and qualitatively. A baseline network is obtained by training the network using the GOPRO training dataset9. The performance of the compressed network is then evaluated when deblurring images from the Kohler8, Kernel Fusion13 and GOPRO datasets, as well as from a customized evaluation dataset. We note that after a short retraining step, the compressed network behaves as expected, i.e. deblurring performance slowly decreases as the level of compression increases. We show that the SRN-Deblur network can be compressed by up to 40% without significant reduction in deblurring capabilities and without significant reduction of quality in the recovered image.

Conference Presentation

Citation Download Citation

Greig Richmond and Arlene Cole-Rhodes "PCA compression of image deblurring neural networks", Proc. SPIE 11870, Artificial Intelligence and Machine Learning in Defense Applications III, 118700P (12 September 2021); https://doi.org/10.1117/12.2600055

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available