Version 1
: Received: 26 January 2021 / Approved: 28 January 2021 / Online: 28 January 2021 (12:29:20 CET)
Version 2
: Received: 20 November 2021 / Approved: 22 November 2021 / Online: 22 November 2021 (14:06:52 CET)
How to cite:
Islam, M.M.; Tushar, Z.H. Interpreting and Comparing Convolutional Neural Networks: A Quantitative Approach. Preprints2021, 2021010579. https://doi.org/10.20944/preprints202101.0579.v1
Islam, M.M.; Tushar, Z.H. Interpreting and Comparing Convolutional Neural Networks: A Quantitative Approach. Preprints 2021, 2021010579. https://doi.org/10.20944/preprints202101.0579.v1
Islam, M.M.; Tushar, Z.H. Interpreting and Comparing Convolutional Neural Networks: A Quantitative Approach. Preprints2021, 2021010579. https://doi.org/10.20944/preprints202101.0579.v1
APA Style
Islam, M.M., & Tushar, Z.H. (2021). Interpreting and Comparing Convolutional Neural Networks: A Quantitative Approach. Preprints. https://doi.org/10.20944/preprints202101.0579.v1
Chicago/Turabian Style
Islam, M.M. and Zahid Hassan Tushar. 2021 "Interpreting and Comparing Convolutional Neural Networks: A Quantitative Approach" Preprints. https://doi.org/10.20944/preprints202101.0579.v1
Abstract
A convolutional neural network (CNN) is sometimes understood as a black box in the sense that while it can approximate any function, studying its structure will not give us any insights into the nature of the function being approximated. In other terms, the discriminative ability does not reveal much about the latent representation of a network. This research aims to establish a framework for interpreting the CNNs by profiling them in terms of interpretable visual concepts and verifying them by means of Integrated Gradient. We also ask the question, "Do different input classes have a relationship or are they unrelated?" For instance, could there be an overlapping set of highly active neurons to identify different classes? Could there be a set of neurons that are useful for one input class whereas misleading for a different one? Intuition answers these questions positively, implying the existence of a structured set of neurons inclined to a particular class. Knowing this structure has significant values; it provides a principled way for identifying redundancies across the classes. Here the interpretability profiling has been done by evaluating the correspondence between individual hidden neurons and a set of human-understandable visual semantic concepts. We also propose an integrated gradient-based class-specific relevance mapping approach that takes the spatial position of the region of interest in the input image. Our relevance score verifies the interpretability scores in terms of neurons tuned to a particular concept/class. Further, we perform network ablation and measure the performance of the network based on our approach.
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
