https://github.com/pasteurlabs/unreasonable_effective_der

Supplementary material to reproduce "The Unreasonable Effectiveness of Deep Evidential Regression"
https://github.com/pasteurlabs/unreasonable_effective_der

confidence deep-learning evidence neural-network pytorch uncertainty

Last synced: about 1 month ago
JSON representation

Supplementary material to reproduce "The Unreasonable Effectiveness of Deep Evidential Regression"

• Host: GitHub
• URL: https://github.com/pasteurlabs/unreasonable_effective_der
• Owner: pasteurlabs
• License: mit
• Created: 2022-05-19T09:29:48.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-11-28T18:38:00.000Z (almost 3 years ago)
• Last Synced: 2024-01-25T12:10:02.473Z (over 1 year ago)
• Topics: confidence, deep-learning, evidence, neural-network, pytorch, uncertainty
• Language: Jupyter Notebook
• Homepage:
• Size: 28.5 MB
• Stars: 19
• Watchers: 2
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
[![arXiv](https://img.shields.io/badge/arXiv-2205.10060-b31b1b.svg)](https://arxiv.org/abs/2205.10060)

[![Python 3.8](https://img.shields.io/badge/python-3.8-blue.svg)](https://www.python.org/downloads/release/python-380/)

# The Unreasonable Effectiveness of Deep Evidential Regression

This repository contains the paper and the supplementary material to reproduce _The Unreasonable Effectiveness of Deep Evidential Regression_:

 - [unreasonable_effective_der.pdf](unreasonable_effective_der.pdf): The paper and the Appendix.

 - [understanding_sota.ipynb](understanding_sota.ipynb): Introduction and high-level overview.

 - [x3_indepth.ipynb](x3_indepth.ipynb): Analysis of one-dimensional cubic regression data set.

 - [binpulse.ipynb](binpulse.ipynb): Analysis of binary pulse experiment.

 - [depth_estimation.ipynb](depth_estimation.ipynb): Notebook that was used to generate the figures of the Monocular Depth Estimation experiment.