Skip to main content
Context Awesome

awesome-visual-representation-learning-with-transformers

github.com/alohays/awesome-visual-representation-learning-with-transformers ↗

Awesome Transformers (self-attention) in Computer Vision

267
GitHub Stars
57
Curated Resources
4
Categories
22 hours ago
Last Refreshed
About transformersCombining CNN with self-attentionStand-alone transformers for Computer VisionUnified text-vision tasks

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me detr family resources from awesome-visual-representation-learning-with-transformers"

Installation instructions →

What's inside

Combining CNN with self-attention

Stand-alone transformers for Computer Vision

  • [paper]Self-attention only in local neighborhood

  • [paper]Self-attention only in local neighborhood

  • [paper]Self-attention only in local neighborhood

  • [paper]Self-attention only in local neighborhood

  • [paper]Scalable approximations to global self-attention

  • [paper]Scalable approximations to global self-attention

Unified text-vision tasks

Showing a sample of 57 resources. View the full list on GitHub →