Login | Register

Seeing Through Models’ Eyes: Decomposing Latent Representations of Convolutional Networks

Title:

Seeing Through Models’ Eyes: Decomposing Latent Representations of Convolutional Networks

Miselis, Bartosz (2020) Seeing Through Models’ Eyes: Decomposing Latent Representations of Convolutional Networks. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
Miselis_MCompSc_F2020.pdf - Accepted Version
Available under License Spectrum Terms of Access.
28MB

Abstract

“To comprehend inner data representations constructed by convolutional networks” is an ambitious task attracting a constantly growing number of researchers across the globe. The joint effort has led to the broad space of interpretability techniques that roughly fall into two groups: attribution and feature visualization. The former shines the light on “where” the algorithm looks, while the latter reveals “what” the network sees. Combining them into rich interfaces provides new ways to understand convolutional networks and develop deeper intuitions about their complex behavior.
In this thesis, two novel techniques are proposed to advance the analyses in the field of interpretability: Latent Factor Attribution (LFA) and Distilled Class Factors Atlas. LFA identifies distinct concepts in the activation tensor using matrix decomposition and estimates their influence on the classification result. Distilled Class Factors Atlas then aggregates these concepts and presents them in an interactive, exploratory interface that makes it possible to see the entire class of images through the model’s eyes by leveraging feature visualization. Both techniques introduced in this thesis extend the holistic view on latent representations of convolutional networks by enabling the collective perspective on the patterns that recur in the activation tensors.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Miselis, Bartosz
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science
Date:4 September 2020
Thesis Supervisor(s):Fevens, Thomas and Krzyżak, Adam
ID Code:987381
Deposited By: Bartosz Miselis
Deposited On:25 Nov 2020 16:13
Last Modified:25 Nov 2020 16:13
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top