Operational Calibration: Debugging Confidence Errors for DNNs in the Field

TL;DR

This paper introduces a Bayesian method for operational calibration of DNN confidence scores, effectively reducing high-confidence errors in real-world applications with minimal labeled data.

Contribution

It proposes a Gaussian Process Regression-based Bayesian approach for calibrating DNN confidence in the field, addressing data scarcity and interpretability challenges.

Findings

Significantly outperforms alternative calibration methods.

Reduces 71% to 97% high-confidence errors with minimal labeled data.

Effective across various datasets and DNN models.

Abstract

Trained DNN models are increasingly adopted as integral parts of software systems, but they often perform deficiently in the field. A particularly damaging problem is that DNN models often give false predictions with high confidence, due to the unavoidable slight divergences between operation data and training data. To minimize the loss caused by inaccurate confidence, operational calibration, i.e., calibrating the confidence function of a DNN classifier against its operation domain, becomes a necessary debugging step in the engineering of the whole system. Operational calibration is difficult considering the limited budget of labeling operation data and the weak interpretability of DNN models. We propose a Bayesian approach to operational calibration that gradually corrects the confidence given by the model under calibration with a small number of labeled operation data deliberately selected from a larger set of unlabeled operation data. The approach is made effective and efficient by leveraging the locality of the learned representation of the DNN model and modeling the calibration as Gaussian Process Regression. Comprehensive experiments with various practical datasets and DNN models show that it significantly outperformed alternative methods, and in some difficult tasks it eliminated about 71% to 97% high-confidence (>0.9) errors with only about 10\% of the minimal amount of labeled operation data needed for practical learning techniques to barely work.