Explainable AI for Computer Vision: Free Python Course

Welcome to Explainable AI for Computer Vision — a free course that covers the theory and Python code for XAI methods applied to computer vision machine learning models. See the course outline video below. Scroll down to see all the available course sections.

Course Outline

• Code and Requirements

Part 1: Introduction

1. Importance
2. Taxonomy
3. Evaluation
4. Axioms
5. Limitations

Part 2: Permutation-based methods

1. Permutation Channel Importance
2. Occlusion
3. LIME
4. SHAP (Coming Soon)

Part 3: Gradient-based methods

1. Vanilla Gradients
2. Input X Gradients
3. Guided Backprop
4. Grad-CAM
5. Guided Grad-CAM
6. SmoothGrad
7. DeepLift
8. Integrated Gradients

Part 4: Interpretability by Design

1. Class Activation Maps (CAMs)
2. Prototype Layers (Coming Soon)

---

See the course page for more XAI courses. You can also find me on Bluesky  | YouTube | Medium 

---

Datasets

Conor O’Sullivan, & Soumyabrata Dev. (2024). The Landsat Irish Coastal Segmentation (LICS) Dataset. (CC BY 4.0) https://doi.org/10.5281/zenodo.13742222

Conor O’Sullivan (2024). Pot Plant Dataset. (CC BY 4.0) https://www.kaggle.com/datasets/conorsully1/pot-plants

Conor O’Sullivan (2024). Road Following Car. (CC BY 4.0). https://www.kaggle.com/datasets/conorsully1/road-following-car

---