mesnico/ALADIN

Official implementation of the paper "ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval"

39
/ 100
Emerging

This tool helps researchers and engineers improve how computers match images with descriptive text. It takes a collection of images and corresponding text descriptions and trains a model to understand their relationships more efficiently. The end-user is typically a computer vision researcher or machine learning engineer working on content-based retrieval systems.

No commits in the last 6 months.

Use this if you need to build or evaluate systems that accurately find images based on text queries or vice-versa, with a focus on improving model efficiency.

Not ideal if you are looking for an out-of-the-box application for general image search or a solution that doesn't require deep machine learning expertise to implement.

image-text-matching cross-modal-retrieval deep-learning-research computer-vision natural-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

28

Forks

7

Language

Python

License

MIT

Last pushed

Dec 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/mesnico/ALADIN"

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