/selective_deep_learning

Code for the paper "Selective Classification for Deep Neural Networks"

Primary LanguagePython

Selective Classification for Deep Neural Networks

By Yonatan Geifman and Ran El-Yaniv

Introduction:

This repository contains the implementation of VGG-16 models for CIFAR-10 and CIFAR-100 and the risk bound proposed in the paper "Selective Classification for Deep Neural Networks".

Citation

If you use these models in your research, please cite:

@ARTICLE{2017arXiv170508500G,
    author = {{Geifman}, Y. and {El-Yaniv}, R.},
    title = "{Selective Classification for Deep Neural Networks}",
    journal = {ArXiv e-prints},
    archivePrefix = "arXiv",
    eprint = {1705.08500},
    year = 2017
}

Weights files:

cifar-100 weights

cifar-10 weights