SelectiveNet: A Deep Neural Network with an Integrated Reject Option

Code

• github.com/geifmany/SelectiveNet
  OfficialIn papernone★ 0
• github.com/BorealisAI/towards-better-sel-cls
  pytorch★ 8
• github.com/ssatsuki/label-selection-layer
  pytorch★ 2
• github.com/gatheluck/pytorch-selectivenet
  pytorch★ 0
• github.com/ravi0912/selectiveNetNLP
  none★ 0

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.

Tasks

Reproductions