ADVISE: ADaptive Feature Relevance and VISual Explanations for Convolutional Neural Networks

Abstract

To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in the classifiers. This paper introduces ADVISE, a new explainability method that quantifies and leverages the relevance of each unit of the feature map to provide better visual explanations. To this end, we propose using adaptive bandwidth kernel density estimation to assign a relevance score to each unit of the feature map with respect to the predicted class. We also propose an evaluation protocol to quantitatively assess the visual explainability of CNN models. We extensively evaluate our idea in the image classification task using AlexNet, VGG16, ResNet50, and Xception pretrained on ImageNet. We compare ADVISE with the state-of-the-art visual explainable methods and show that the proposed method outperforms competing approaches in quantifying feature-relevance and visual explainability while maintaining competitive time complexity. Our experiments further show that ADVISE fulfils the sensitivity and implementation independence axioms while passing the sanity checks. The implementation is accessible for reproducibility purposes on https://github.com/dehshibi/ADVISE.

References in corpus (4)

• A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images
• A deep convolutional neural network for classification of Aedes albopictus mosquitoes
• Pain level and pain-related behaviour classification using GRU-based sparsely-connected RNNs
• On the use of uncertainty in classifying Aedes Albopictus mosquitoes

Cited by in corpus (2)

• L-SFAN: Lightweight Spatially-focused Attention Network for Pain Behavior Detection
• When One Sensor Fails: Tolerating Dysfunction in Multi-Sensor Prototypes