Generation of rule-based explanations of CNN classifiers using regional features

Author:

Philipp William1,R Yashwanthika2,K Sikha O1,Benitez Raul1

Affiliation:

1. Universitat Politècnica de Catalunya (UPC-BarcelonaTECH)

2. Amrita Vishwa Vidyapeetham University

Abstract

Abstract

Although Deep Learning networks generally outperform traditional machine learning approaches based on tailored features, they often lack explainability. To address this issue, numerous methods have been proposed, particularly for image-related tasks such as image classification or object segmentation. These methods generate a heatmap that visually explains the classification problem by identifying the most important regions for the classifier. However, these explanations remain purely visual. To overcome this limitation, we introduce a novel CNN explainability method that identifies the most relevant regions in an image and generates a decision tree based on meaningful regional features, providing a rule-based explanation of the classification model. We evaluated the proposed method on a synthetic blob's dataset and subsequently applied it to two cell image classification datasets with healthy and pathological patterns.

Publisher

Springer Science and Business Media LLC

Reference32 articles.

1. Selvaraju, Ramprasaath R. and Cogswell, Michael and Das, Abhishek and Vedantam, Ramakrishna and Parikh, Devi and Batra, Dhruv (2017) Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. 10.1109/ICCV.2017.74, 618-626, 2017 IEEE International Conference on Computer Vision (ICCV)

2. Aditya Chattopadhay and Anirban Sarkar and Prantik Howlader and Vineeth N Balasubramanian (2018) Grad-CAM + +: Improved Visual Explanations for Deep Convolutional Networks. {IEEE}, https://doi.org/10.1109%2Fwacv.2018.00097, 10.1109/wacv.2018.00097, mar, 2018 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})

3. Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. https://arxiv.org/abs/1312.6034, arXiv, Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences, 10.48550/ARXIV.1312.6034, arXiv.org perpetual, non-exclusive license, 2013

4. Ruth C. Fong and Andrea Vedaldi (2017) Interpretable Explanations of Black Boxes by Meaningful Perturbation. {IEEE}, https://doi.org/10.1109%2Ficcv.2017.371, 10.1109/iccv.2017.371, oct, 2017 {IEEE} International Conference on Computer Vision ({ICCV})

5. Zhou, Bolei and Khosla, Aditya and Lapedriza, Agata and Oliva, Aude and Torralba, Antonio. Learning Deep Features for Discriminative Localization. https://arxiv.org/abs/1512.04150, arXiv, Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences, 10.48550/ARXIV.1512.04150, arXiv.org perpetual, non-exclusive license, 2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3