cvlab-epfl/zigzag

Official code for "ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference" (TMLR 2024)

37
/ 100
Emerging

This project provides a method to quickly and reliably estimate how confident an AI model is about its predictions without slowing it down. You input your data into an AI model, and it outputs both a prediction and a measure of how uncertain that prediction is. This is useful for anyone working with AI models in critical applications who needs to understand the reliability of a model's output, such as data scientists, machine learning engineers, and researchers.

No commits in the last 6 months.

Use this if you need to understand the trustworthiness of your AI model's predictions on various types of data, including image classification, regression, and identifying unusual data points, without sacrificing inference speed.

Not ideal if you are looking for a complete, production-ready library with extensive model integration, as this focuses on the core method rather than broad platform support.

AI model reliability Uncertainty quantification Out-of-distribution detection Machine learning explainability Deep learning validation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

4

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cvlab-epfl/zigzag"

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