ExplainableML/WaffleCLIP

Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts"

35
/ 100
Emerging

This project helps researchers and machine learning engineers improve how well AI models can identify objects in images, especially when they haven't been specifically trained on those objects. You input a set of images and a list of object categories, and the system outputs an improved classification of what's in each image. It's designed for those who work with computer vision models like CLIP and need to boost their 'zero-shot' performance.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer working with Vision-Language Models (VLMs) like CLIP and need to improve their classification accuracy on new, unseen categories without additional training data.

Not ideal if you are looking for a plug-and-play image classification tool for a production environment without delving into research-focused model enhancements.

computer-vision zero-shot-learning image-classification deep-learning-research multimodal-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

61

Forks

6

Language

Python

License

MIT

Last pushed

Jul 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ExplainableML/WaffleCLIP"

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