Skip to yearly menu bar Skip to main content


Poster

Selective Classification for Deep Neural Networks

Yonatan Geifman · Ran El-Yaniv

Pacific Ballroom #134

Keywords: [ Learning Theory ] [ Deep Learning ] [ Supervised Deep Networks ] [ Classification ]


Abstract:

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% error in top-5 ImageNet classification can be guaranteed with probability 99.9%, with almost 60% test coverage.

Live content is unavailable. Log in and register to view live content