🧭 Roadmap › 09 · Emerging AI › Vision Transformers (ViT)
09 · Emerging AI

Vision Transformers (ViT)

Applying the Transformer architecture directly to image patches

🟡 GOOD
🧠 Understand👁️ Visualize⚖️ Compare🗣️ Explain
8 subtopics — click to study
Image Patches 🔴 Patch Embeddings 🔴 CLS Token 🔴 Self-Attention on Patches 🔴 Positional Encoding for Patches 🟡 ViT vs CNN 🔴 DINO / DINOv2 🟡 Swin Transformer 🟢
← Back to Roadmap
This page 0:00
This session 0:00
Total (all pages) 0:00
Today 0:00
▶ Running
📊 View all study stats →
0:00 studying