Skip to content
Gopi Krishna Tummala
← Back to Home

Computer Vision

How Machines See

From convolutions to vision foundation models: classification, detection, segmentation, video, 3D and open-vocabulary vision, explained through intuition.

Suggested Learning Path

  1. 1 Start with **Module 1** for the map of vision tasks and how the field evolved
  2. 2 Move through **CNNs** and **Vision Transformers** for the backbones
  3. 3 Then **Detection**, **Segmentation**, **Video** and **3D** for the core tasks
  4. 4 Finish with **Vision Foundation Models** for open-vocabulary vision and VLMs

All Posts in This Track

8 articles covering computer vision