Sensitivity and stability of pretrained CNN filters

Jehan Ghafuri; Hongbo Du; Sabah Jassim

doi:10.1117/12.2589521

12 April 2021 Sensitivity and stability of pretrained CNN filters

Jehan Ghafuri, Hongbo Du, Sabah Jassim

Proceedings Volume 11734, Multimodal Image Exploitation and Learning 2021; 117340B (2021) https://doi.org/10.1117/12.2589521
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Convolutional Neural Network (CNN) is a powerful and successful deep learning technique for a variety of computer vision and image analysis applications. Interpreting and explaining the decisions of CNNs is one of the most challengeable tasks despite its significant success in various image analysis tasks. Topological Data Analysis (TDA) is an approach that exploits algebraic invariants from topology to analyse high dimensional and noisy datasets as well as growing challenges of big data applications. Persistent homology (PH) is an algebraic topology method for measuring topological features of shapes and/or functions at different distance or similarity resolutions. This work is an attempt to investigate the algebraic properties of pretrained CNN convolutional layer filters based on random Gaussian/Uniform distribution. We shall investigate the stability and sensitivity of the condition number of CNN filters during and post the model training with focus on class discriminability of the PH features of the convolved images. We shall demonstrate a strong link between the condition number of the CNN filters and their discriminating power of the PH representation. In particular, we shall establish that if small perturbation added to the original images then feature maps with well-conditioned filters will produce similar topological features to the original image. Our investigation and findings are based on training CNN’s with Digits, MNIST and CIFAR-10 datasets. Our ultimate interest in applying the results of these findings in designing appropriate CNN models for classifications of ultrasound tumor scan images. Preliminary results for these applications are encouraging.

Conference Presentation

Citation Download Citation

Jehan Ghafuri, Hongbo Du, and Sabah Jassim "Sensitivity and stability of pretrained CNN filters", Proc. SPIE 11734, Multimodal Image Exploitation and Learning 2021, 117340B (12 April 2021); https://doi.org/10.1117/12.2589521

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