Home
Scholarly Works
Finding Representative Interpretations on...
Journal article

Finding Representative Interpretations on Convolutional Neural Networks

Abstract

Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual or a small number of images. To facilitate human understandability and generalization ability, it is important to develop representative interpretations that interpret common decision logics of a CNN on a large group of similar images, which reveal the common semantics data contributes to many closely related predictions. In this paper, we develop a novel unsupervised approach to produce a highly representative interpretation for a large number of similar images. We formulate the problem of finding representative interpretations as a co-clustering problem, and convert it into a submodular cost submodular cover problem based on a sample of the linear decision boundaries of a CNN. We also present a visualization and similarity ranking method. Our extensive experiments demonstrate the excellent performance of our method.

Authors

Lam PC-H; Chu L; Torgonskiy M; Pei J; Zhang Y; Wang L

Journal

, Vol. 00, , pp. 1325–1334

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

October 17, 2021

DOI

10.1109/iccv48922.2021.00138
View published work (Non-McMaster Users)

Contact the Experts team