Course
Computer Vision
Teaching machines to see, from raw pixels to recognition.
L3 · AdvancedEvolvingKnown~3 h
What you’ll learn
- Explain how images are represented and processed as tensors
- Describe how convolution and CNNs learn spatial features efficiently
- Compare detection, segmentation, vision transformers, and multimodal models
Prerequisites
deep-learning-and-frontier
Module 1. Vision Foundations
Images as tensors, and the convolution that made deep vision work.
Module 2. Modern Vision
Detection, segmentation, vision transformers, and multimodal models.