SSD Net: toward deep network models based on dissimilarity metrics

Satoshi Arai; Tomoharu Nagao

doi:10.1117/12.2523764

22 March 2019 SSD Net: toward deep network models based on dissimilarity metrics

Satoshi Arai, Tomoharu Nagao

Proceedings Volume 11049, International Workshop on Advanced Image Technology (IWAIT) 2019; 110492A (2019) https://doi.org/10.1117/12.2523764
Event: 2019 Joint International Workshop on Advanced Image Technology (IWAIT) and International Forum on Medical Imaging in Asia (IFMIA), 2019, Singapore, Singapore

Abstract

Most artificial neural networks that originate from the perceptron use the inner product as the basic operation to calculate pattern similarities. Unlike them, we propose a novel hierarchical network model based on a pattern dissimilarity operation using a popular dissimilarity metric: sum of squared differences. Our model is differentiable and end-to-end trainable. We provide a description of the basic formulation and network architecture of the proposed method. Then we apply our method to image classification tasks using public datasets for performance comparison. Although our method does not outperform the same size of convolutional neural network in terms of classification accuracy, it demonstrates that comparable performance can be obtained.

Citation Download Citation

Satoshi Arai and Tomoharu Nagao "SSD Net: toward deep network models based on dissimilarity metrics", Proc. SPIE 11049, International Workshop on Advanced Image Technology (IWAIT) 2019, 110492A (22 March 2019); https://doi.org/10.1117/12.2523764

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