cvlab-epfl/zigzag
Official code for "ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference" (TMLR 2024)
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.
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.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!