Skip to content
Code for ICLR 2019 SafeML workshop paper: Analysis of Confident-Classifiers for Out-of-distribution Detection
Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
gan_ood_proof_exp
README.md
classifier_3class_boundary.ipynb
classifier_3class_boundary_ndim.ipynb
classifier_3class_boundary_ndim_boundary.ipynb
classifier_3class_rectangle.ipynb
classifier_3class_rectangle_ndim.ipynb
classifier_3class_rectangle_ndim_gaussian.ipynb
classifier_confidence_boundary.ipynb
classifier_confidence_boundary_ndim.ipynb
classifier_confidence_boundary_ndim_gaussian.ipynb
classifier_confidence_rectangle.ipynb
classifier_confidence_rectangle_ndim.ipynb
classifier_confidence_rectangle_ndim_gaussian.ipynb
exp1_a.png
exp1_b.png
exp1_c.png
exp2_a.png
exp2_b.png
exp2_c.png
exp3_a.png
exp3_b.png
exp3_c.png

README.md

This is the code for ICLR 2019 SafeML workshop paper titled "Analysis of Confident-Classifiers for Out-of-distribution Detection"

https://arxiv.org/abs/1904.12220

Each ipython notebook corresponds to each experiment mentioned in the paper.

You can’t perform that action at this time.