fregu856/ebms_regression

Official implementation of "Energy-Based Models for Deep Probabilistic Regression" (ECCV 2020) and "How to Train Your Energy-Based Model for Regression" (BMVC 2020).

43
/ 100
Emerging

This project offers an advanced method for deep probabilistic regression, helping computer vision engineers get more precise and robust predictions from their models. It takes in raw image data and outputs predicted bounding box coordinates for object detection, or other continuous values like age or head-pose, along with a measure of uncertainty. This allows practitioners to understand not just 'what' but 'how sure' the model is, which is crucial for high-stakes applications.

106 stars. No commits in the last 6 months.

Use this if you need to perform precise object detection or other continuous value predictions from images and require a clear understanding of the model's confidence in its predictions.

Not ideal if you are looking for a simple, off-the-shelf image classification tool or a solution for non-image-based regression tasks.

object-detection computer-vision probabilistic-modeling image-analysis deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

106

Forks

19

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 14, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fregu856/ebms_regression"

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