Computer Vision
Teaching machines to see — from pixels to understanding
Beyond classification: detection, segmentation, vision transformers, and the multimodal models that connect vision to language.
Intermediate3 modules · 10 lessons~84 min825 XPAligned with Hugging Face CV CourseStart with: Deep Learning
Progress0/10
Module
Seeing More Than Labels
The task landscape past classification: boxes, masks, and identities over time
The CV Task Landscape8 min · 75 XPThe CV Task Landscape
Object Detection9 min · 85 XPObject Detection
Segmentation: Pixel-Perfect Masks9 min · 85 XPSegmentation: Pixel-Perfect Masks
Module
Vision Meets Transformers
Attention eats vision too — patches, contrastive learning, and multimodal models
Vision Transformers9 min · 90 XPVision Transformers
CLIP: Vision Learns from Language9 min · 90 XPCLIP: Vision Learns from Language
Multimodal Models8 min · 80 XPMultimodal Models
Module
Vision in Practice
Where vision models earn their keep — and where they break
Face Recognition & Its Ethics8 min · 80 XPFace Recognition & Its Ethics
Medical Imaging Breakthroughs8 min · 80 XPMedical Imaging Breakthroughs
Video: Vision Plus Time8 min · 85 XPVideo: Vision Plus Time
Evaluation Pitfalls8 min · 75 XPEvaluation Pitfalls
Capstone project
See like a machine
Build an image classifier for a domain you pick — plants, sneakers, food, whatever. Then break it deliberately: what inputs fool it, and why?
Deliverable: A notebook or demo app plus a 'failure gallery' showing five inputs it gets wrong.
Milestones
Finish every lesson to earn the Computer Vision Certificate.