Selective Classification for Deep Neural Networks

05/23/2017
by   Yonatan Geifman, et al.
0

Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage. In this paper we propose a method to construct a selective classifier given a trained neural network. Our method allows a user to set a desired risk level. At test time, the classifier rejects instances as needed, to grant the desired risk (with high probability). Empirical results over CIFAR and ImageNet convincingly demonstrate the viability of our method, which opens up possibilities to operate DNNs in mission-critical applications. For example, using our method an unprecedented 2 classification can be guaranteed with probability 99.9 coverage.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2019

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

We consider the problem of selective prediction (also known as reject op...
research
10/19/2022

Distribution Shift Detection for Deep Neural Networks

To deploy and operate deep neural models in production, the quality of t...
research
10/19/2022

AUC-based Selective Classification

Selective classification (or classification with a reject option) pairs ...
research
11/19/2022

Gumbel-Softmax Selective Networks

ML models often operate within the context of a larger system that can a...
research
10/15/2020

Selective Classification via One-Sided Prediction

We propose a novel method for selective classification (SC), a problem w...
research
10/28/2021

Trading via Selective Classification

A binary classifier that tries to predict if the price of an asset will ...
research
10/02/2019

Accelerating Deep Learning by Focusing on the Biggest Losers

This paper introduces Selective-Backprop, a technique that accelerates t...

Please sign up or login with your details

Forgot password? Click here to reset