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.
[ Outline video coming soon]
Course Outline
Part 1: Introduction
- The importance of XAI in CV
- A Taxonomy of XAI Methods
- The Limitations of XAI
Part 2: Permutation-based methods
- Permutation Channel Importance
- Occlusion for Localization
- SHAP
Part 3: Gradient-based methods
- Gradient-weighted Class Activation Mapping (Grad-CAM)
- DeepLift
- Integrated Gradients
- Deconvolution
Part 4: Interpretability by Design
- Class Activation Maps
- Prototype Layers
See the course page for more XAI courses. You can also find me on Bluesky | Threads | 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
Get the paid version of the course. This will give you access to the course eBook, certificate and all the videos ad free.
If you are interested in XAI, then you will also find these courses useful:
