Evaluating CNN interpretability on sketch classification

Abraham Theodorus; Meike Nauta; Christin Seifert

doi:10.1117/12.2559536

31 January 2020 Evaluating CNN interpretability on sketch classification

Abraham Theodorus, Meike Nauta, Christin Seifert

Proceedings Volume 11433, Twelfth International Conference on Machine Vision (ICMV 2019); 114331Q (2020) https://doi.org/10.1117/12.2559536
Event: Twelfth International Conference on Machine Vision, 2019, Amsterdam, Netherlands

Abstract

While deep neural networks (DNNs) have been shown to outperform humans on many vision tasks, their intransparent decision making process inhibits wide-spread uptake, especially in high-risk scenarios. The BagNet architecture was designed to learn visual features that are easier to explain than the feature representation of other convolutional neural networks (CNNs). Previous experiments with BagNet were focused on natural images providing rich texture and color information. In this paper, we investigate the performance and interpretability of BagNet on a data set of human sketches, i.e., a data set with limited color and no texture information. We also introduce a heatmap interpretability score (HI score) to quantify model interpretability and present a user study to examine BagNet interpretability from user perspective. Our results show that BagNet is by far the most interpretable CNN architecture in our experiment setup based on the HI score.

Citation Download Citation

Abraham Theodorus, Meike Nauta, and Christin Seifert "Evaluating CNN interpretability on sketch classification", Proc. SPIE 11433, Twelfth International Conference on Machine Vision (ICMV 2019), 114331Q (31 January 2020); https://doi.org/10.1117/12.2559536

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