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

Prithvijit Chattopadhyay, Bharat Goyal, Boglarka Ecsedi, Viraj Uday Prabhu, Judy Hoffman

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Unsupervised Domain Adaptation, Sim2Real

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A method to reduce miscalibration for unsupervised Sim2Real adaptation by optimizing for calibrated predictions on augmented synthetic data.

Abstract: Synthetic data (Sim) drawn from simulators have emerged as a popular alternativefor training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world applicationscan 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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 6015