Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but …

Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides …

Semantic Input Sampling for Explanation (SISE) - A Technical Description

TL;DR * We propose a state-of-the-art post-hoc CNN specific Visual XAI algorithm - SISE. * Input : A test image; The trained model * Output : A visual 2D heatmap * Properties : Noise-free, High resolution, Class discriminative and Correlates to model's prediction.

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class …

Explainable AI for Visual Defect Inspection

NEU_XAI Developed and studied XAI algorithms that generates saliency maps according to the importance of each corresponding pixels of the input test image towards the Machine Learning model’s predictive accuracy, with the aim of decoding complex black-box models.