Frustratingly Easy Uncertainty Estimation for Distribution Shift

TL;DR

This paper presents a surprisingly simple method for uncertainty estimation under distribution shift in image classification, using corrupted images and statistical calibration, outperforming more complex prior approaches.

Contribution

The authors demonstrate that uncertainty estimation can be effectively achieved through a straightforward approach without modifying the original model or training process.

Findings

Superior uncertainty estimation performance across various distribution shifts

Effective on unsupervised domain adaptation tasks

Simple calibration method outperforms complex prior techniques

Abstract

Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domain adaptation. While the primary goal is to improve accuracy under distribution shift, an important secondary goal is uncertainty estimation: evaluating the probability that the prediction of a model is correct. While improving accuracy is hard, uncertainty estimation turns out to be frustratingly easy. Prior works have appended uncertainty estimation into the model and training paradigm in various ways. Instead, we show that we can estimate uncertainty by simply exposing the original model to corrupted images, and performing simple statistical calibration on the image outputs. Our frustratingly easy methods demonstrate superior performance on a wide range of distribution shifts as well as on unsupervised domain adaptation tasks, measured through extensive experimentation.