Explainable AI for Visual Defect Inspection
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
This repo contains keras implementation of few XAI algorithms on NEU surface defect dataset.
- NEU steel surface defect database
- Original train images
- NEU steel surface defect database - Test Split
- contains 180 test images (with 10% partition)
- Training a MobileNet model on the NEU surface defect dataset using Transfer Learning.
- Visualizing the important features of test images using model agnostic LIME and SHAP algorithms.
Sample images from NEU dataset :
- Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
- Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
- Semantic Input Sampling for Explanation (SISE) - A Technical Description
- Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation
- IDC type Breast Cancer Classification