SelectiveNet: A Deep Neural Network with an Integrated Reject Option
Abstract
We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly on a threshold over the prediction confidence of a pre-trained network. In contrast, SelectiveNet is trained to optimize both classification (or regression) and rejection simultaneously, end-to-end. The result is a deep neural network that is optimized over the covered domain. In our experiments, we show a consistently improved risk-coverage trade-off over several well-known classification and regression datasets, thus reaching new state-of-the-art results for deep selective classification.
Cite
Text
Geifman and El-Yaniv. "SelectiveNet: A Deep Neural Network with an Integrated Reject Option." International Conference on Machine Learning, 2019.Markdown
[Geifman and El-Yaniv. "SelectiveNet: A Deep Neural Network with an Integrated Reject Option." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/geifman2019icml-selectivenet/)BibTeX
@inproceedings{geifman2019icml-selectivenet,
title = {{SelectiveNet: A Deep Neural Network with an Integrated Reject Option}},
author = {Geifman, Yonatan and El-Yaniv, Ran},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {2151-2159},
volume = {97},
url = {https://mlanthology.org/icml/2019/geifman2019icml-selectivenet/}
}