loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Harry Rogers 1 ; Beatriz De La Iglesia 1 and Tahmina Zebin 2

Affiliations: 1 School of Computing Science, University of East Anglia, U.K. ; 2 School of Computer Science, Brunel University London, U.K.

Keyword(s): Class Activation Maps, Deep Learning, Quantization, XAI.

Abstract: The deployment of Neural Networks on resource-constrained devices for object classification and detection has led to the adoption of network compression methods, such as Quantization. However, the interpretation and comparison of Quantized Neural Networks with their Non-Quantized counterparts remains inadequately explored. To bridge this gap, we propose a novel Quantization Aware eXplainable Artificial Intelligence (XAI) pipeline to effectively compare Quantized and Non-Quantized Convolutional Neural Networks (CNNs). Our pipeline leverages Class Activation Maps (CAMs) to identify differences in activation patterns between Quantized and Non-Quantized. Through the application of Root Mean Squared Error, a subset from the top 5% scoring Quantized and Non-Quantized CAMs is generated, highlighting regions of dissimilarity for further analysis. We conduct a comprehensive comparison of activations from both Quantized and Non-Quantized CNNs, using Entropy, Standard Deviation, Sparsity metric s, and activation histograms. The ImageNet dataset is utilized for network evaluation, with CAM effectiveness assessed through Deletion, Insertion, and Weakly Supervised Object Localization (WSOL). Our findings demonstrate that Quantized CNNs exhibit higher performance in WSOL and show promising potential for real-time deployment on resource-constrained devices. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.137.222.9

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Rogers, H. ; De La Iglesia, B. and Zebin, T. (2023). Evaluating the Use of Interpretable Quantized Convolutional Neural Networks for Resource-Constrained Deployment. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR; ISBN 978-989-758-671-2; ISSN 2184-3228, SciTePress, pages 109-120. DOI: 10.5220/0012231900003598

@conference{kdir23,
author={Harry Rogers and Beatriz {De La Iglesia} and Tahmina Zebin},
title={Evaluating the Use of Interpretable Quantized Convolutional Neural Networks for Resource-Constrained Deployment},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR},
year={2023},
pages={109-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012231900003598},
isbn={978-989-758-671-2},
issn={2184-3228},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR
TI - Evaluating the Use of Interpretable Quantized Convolutional Neural Networks for Resource-Constrained Deployment
SN - 978-989-758-671-2
IS - 2184-3228
AU - Rogers, H.
AU - De La Iglesia, B.
AU - Zebin, T.
PY - 2023
SP - 109
EP - 120
DO - 10.5220/0012231900003598
PB - SciTePress