Share Email Print

Proceedings Paper

Towards a visualization of deep neural networks for rough line images
Author(s): Narendra Chaudhary; Serap A. Savari
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 29 August 2019
PDF: 12 pages
Proc. SPIE 11177, 35th European Mask and Lithography Conference (EMLC 2019), 111770S (29 August 2019); doi: 10.1117/12.2535667
Show Author Affiliations
Narendra Chaudhary, Texas A&M Univ. (United States)
Serap A. Savari, Texas A&M Univ. (United States)

Published in SPIE Proceedings Vol. 11177:
35th European Mask and Lithography Conference (EMLC 2019)
Uwe F.W. Behringer; Jo Finders, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?