JinhaoLee/WCA

[ICML 2024] Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

38
/ 100
Emerging

This project helps improve the accuracy of classifying images based on text descriptions. It takes an image and a set of detailed text descriptions (often generated by AI) and determines how well they match. The output is a refined similarity score that helps identify the image's category more precisely, benefiting researchers and practitioners working with vision-language models for image classification tasks.

No commits in the last 6 months.

Use this if you need to improve the zero-shot classification performance of your vision-language models, especially when using AI-generated text descriptions for images.

Not ideal if you are looking for a general-purpose image classifier without reliance on vision-language models or detailed text prompts.

image-classification computer-vision natural-language-processing ai-model-evaluation zero-shot-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

19

Forks

7

Language

Python

License

MIT

Last pushed

Sep 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JinhaoLee/WCA"

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