AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

TL;DR

AUGCAL enhances synthetic-to-real domain adaptation by calibrating model confidence through augmented synthetic images and calibration loss, leading to more reliable predictions without sacrificing performance.

Contribution

AUGCAL introduces a training-time calibration method that improves model confidence and reduces miscalibration during SIM2REAL adaptation, applicable across various methods and tasks.

Findings

Reduces model miscalibration and overconfidence.

Improves confidence score reliability for misclassification detection.

Enhances SIM2REAL adaptation performance across multiple settings.

Abstract

Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world applications can be challenging due to appearance disparities. A commonly employed solution to counter this SIM2REAL gap is unsupervised domain adaptation, where models are trained using labeled SIM data and unlabeled REAL data. Mispredictions made by such SIM2REAL adapted models are often associated with miscalibration - stemming from overconfident predictions on real data. In this paper, we introduce AUGCAL, a simple training-time patch for unsupervised adaptation that improves SIM2REAL adapted models by - (1) reducing overall miscalibration, (2) reducing overconfidence in incorrect predictions and (3) improving confidence score reliability by better guiding misclassification detection - all while retaining or improving SIM2REAL performance. Given a base SIM2REAL adaptation algorithm, at training time, AUGCAL involves replacing vanilla SIM images with strongly augmented views (AUG intervention) and additionally optimizing for a training time calibration loss on augmented SIM predictions (CAL intervention). We motivate AUGCAL using a brief analytical justification of how to reduce miscalibration on unlabeled REAL data. Through our experiments, we empirically show the efficacy of AUGCAL across multiple adaptation methods, backbones, tasks and shifts.