Towards a visualization of deep neural networks for rough line images

Narendra Chaudhary; Serap A. Savari

doi:10.1117/12.2535667

29 August 2019 Towards a visualization of deep neural networks for rough line images

Narendra Chaudhary, Serap A. Savari

Proceedings Volume 11177, 35th European Mask and Lithography Conference (EMLC 2019); 111770S (2019) https://doi.org/10.1117/12.2535667
Event: 35th European Mask and Lithography Conference, 2019, Dresden, Germany

Abstract

Low dose scanning electron microscope (SEM) images are an attractive option to estimate the roughness of nanos- tructures. We recently proposed two deep convolutional neural network (CNN) architectures named “LineNet” to simultaneously perform denoising and edge estimation on rough line SEM images. In this paper we consider multiple visualization tools to improve our understanding of LineNet1; one of these techniques is new to the visualization of denoising CNNs. We use the resulting insights from these visualizations to motivate a study of two variations of LineNet1 with fewer neural network layers. Furthermore, although in classification CNNs edge detection is commonly believed to happen early in the network, the visualization techniques suggest that important aspects of edge detection in LineNet1 occur late in the network.

Citation Download Citation

Narendra Chaudhary and Serap A. Savari "Towards a visualization of deep neural networks for rough line images", Proc. SPIE 11177, 35th European Mask and Lithography Conference (EMLC 2019), 111770S (29 August 2019); https://doi.org/10.1117/12.2535667

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