cvlab-epfl/iter_unc

Official code for "Enabling Uncertainty Estimation in Iterative Neural Networks" (ICML 2024)

27
/ 100
Experimental

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.

aerospace-engineering geospatial-analysis image-segmentation predictive-modeling quality-assurance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

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.