Occlusion-Based Saliency Maps | Explainable AI for Computer Vision

🚀 Course 🚀
Free: https://adataodyssey.com/xai-for-cv/
Paid: https://adataodyssey.com/courses/xai-for-cv/

Occlusion is one of the simplest and most intuitive techniques used to interpret deep learning models in computer vision. By systematically masking out parts of an image and observing how the model's predictions change, occlusion allows us to build saliency maps that highlight the most important pixels driving a model's decision.

We introduce occlusion-based saliency maps, a foundational method in explainable AI (XAI) and machine learning interpretability. We will:
- Explain the theory behind occlusion and how it is used to interpret computer vision models
- Discuss the key limitations of the method and when it may not be the best choice

This video is ideal for those looking to deepen their understanding of XAI techniques in computer vision, especially those working with deep learning models that require transparent and interpretable predictions.

🚀 Useful playlists 🚀
XAI for CV: https://www.youtube.com/playlist?list=PLqDyyww9y-1QA4-o4tTAF_iD5cKCC1qEA
XAI: https://www.youtube.com/playlist?list=PLqDyyww9y-1SwNZ-6CmvfXDAOdLS7yUQ4
SHAP: https://www.youtube.com/playlist?list=PLqDyyww9y-1SJgMw92x90qPYpHgahDLIK
Algorithm fairness: https://www.youtube.com/playlist?list=PLqDyyww9y-1Q0zWbng6vUOG1p3oReE2xS

🚀 Get in touch 🚀
Medium: https://conorosullyds.medium.com/
Bluesky: https://bsky.app/profile/conorosullyds.bsky.social
Threads: https://www.threads.net/@conorosullyds
Website: https://adataodyssey.com/

🚀 Chapters 🚀
00:00 Introduction
01:19 What is Occlusion
02:31 Occlusion for Saliency Maps
04:56 The limitations of Occlusion

Видео Occlusion-Based Saliency Maps | Explainable AI for Computer Vision канала A Data Odyssey