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.
Yonatan Geifman (Technion)
Ran El-Yaniv (Technion)
Related Events (a corresponding poster, oral, or spotlight)
2019 Oral: SelectiveNet: A Deep Neural Network with an Integrated Reject Option »
Tue Jun 11th 11:00 -- 11:20 AM Room Hall A