LeapLabTHU/Cross-Modal-Adapter

[Pattern Recognition 2025] Cross-Modal Adapter for Vision-Language Retrieval

40
/ 100
Emerging

This project helps researchers and practitioners in AI and machine learning efficiently adapt large pre-trained vision-language models for specific retrieval tasks. By reducing the number of parameters that need fine-tuning, it takes in existing models and datasets to output a more specialized, high-performing model for tasks like image or video search using text queries. It's designed for machine learning engineers, AI researchers, and data scientists working with multimodal data.

140 stars. No commits in the last 6 months.

Use this if you need to fine-tune large pre-trained vision-language models for specific retrieval tasks but want to significantly reduce computational costs and training time.

Not ideal if you are looking for a complete end-user application for image/video retrieval, as this project focuses on the underlying model adaptation methodology.

vision-language modeling information retrieval multimodal AI model adaptation deep learning optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

140

Forks

12

Language

Python

License

Apache-2.0

Last pushed

Aug 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LeapLabTHU/Cross-Modal-Adapter"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.