English

Learning When to Say "I Don't Know"

Computer Vision and Pattern Recognition 2023-02-16 v2 Machine Learning

Abstract

We propose a new Reject Option Classification technique to identify and remove regions of uncertainty in the decision space for a given neural classifier and dataset. Such existing formulations employ a learned rejection (remove)/selection (keep) function and require either a known cost for rejecting examples or strong constraints on the accuracy or coverage of the selected examples. We consider an alternative formulation by instead analyzing the complementary reject region and employing a validation set to learn per-class softmax thresholds. The goal is to maximize the accuracy of the selected examples subject to a natural randomness allowance on the rejected examples (rejecting more incorrect than correct predictions). We provide results showing the benefits of the proposed method over na\"ively thresholding calibrated/uncalibrated softmax scores with 2-D points, imagery, and text classification datasets using state-of-the-art pretrained models. Source code is available at https://github.com/osu-cvl/learning-idk.

Keywords

Cite

@article{arxiv.2209.04944,
  title  = {Learning When to Say "I Don't Know"},
  author = {Nicholas Kashani Motlagh and Jim Davis and Tim Anderson and Jeremy Gwinnup},
  journal= {arXiv preprint arXiv:2209.04944},
  year   = {2023}
}

Comments

International Symposium on Visual Computing, October 2022

R2 v1 2026-06-28T01:05:41.206Z