Improving Confidence Estimates for Unfamiliar Examples

By Zhizhong Li, Derek Hoiem. 2018

43 citations recorded by the source corpus.

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to recognize gender is 12 times more likely to be wrong with a 99% confident prediction if presented with a subject from a different age group than those seen during training. In this paper, we compare and evaluate several methods to improve confidence estimates for unfamiliar and familiar samples. We propose a testing methodology of splitting unfamiliar and familiar samples by attribute (age, breed, subcategory) or sampling (similar datasets collected by different people at different times). We evaluate methods including confidence calibration, ensembles, distillation, and a Bayesian model and use several metrics to analyze label, likelihood, and calibration error. While all methods reduce over-confident errors, the ensemble of calibrated models performs best overall, and T-scaling performs best among the approaches with fastest inference.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Distilling Causal Effect of Data in Class-Incremental Learning (2021, background): “For example, if the new data are outof-distribution compared to the old one, the features of the new data extracted from the old network will be elusive, and thus the corresponding distillation loss will mislead the new training [23, 20].”
A survey of uncertainty in deep neural networks (2021, background): “In practice, several works pointed out that deeper networks tend to be more overconfident than shallower ones [15], [266], [267].”