Frustratingly Easy Uncertainty Estimation for Distribution Shift

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.

17 pages, 4 Tables, 9 Figures

References in corpus (5)

• Learning Transferable Features with Deep Adaptation Networks
• VisDA: The Visual Domain Adaptation Challenge
• Deep Anomaly Detection with Outlier Exposure
• Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
• Improving model calibration with accuracy versus uncertainty optimization