cvlab-epfl/iter_unc
Official code for "Enabling Uncertainty Estimation in Iterative Neural Networks" (ICML 2024)
This project helps anyone using iterative neural networks to understand how confident the network is about its predictions. It takes the outputs from an iterative model (like those used for image analysis or predicting properties of shapes) and provides an estimate of its certainty. This is useful for scientists, engineers, or analysts who need to trust their model's predictions, especially in critical applications like road detection in aerial images or aerodynamic property estimation.
No commits in the last 6 months.
Use this if you need a reliable, computationally efficient way to quantify the uncertainty of predictions made by your iterative neural networks without altering the original model.
Not ideal if your models are not iterative or if you primarily need uncertainty for simple regression or classification tasks that don't involve complex iterative processing.
Stars
19
Forks
1
Language
Jupyter Notebook
License
MIT
Last pushed
Jul 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cvlab-epfl/iter_unc"
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!