Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Events

Events

Selective Classification for Deep Neural Networks
event speaker icon
Yonatan Geifman, M.Sc. Thesis Seminar
event date icon
Sunday, 7.1.2018, 13:30
event location icon
Taub 601
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. 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%, and almost 60% test coverage.
[Back to the index of events]