SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation
This work tackles the problem of robust unsupervised domain adaptation, particularly under label distribution shift, which is a common challenge for practitioners deploying models in new environments.
This paper addresses unsupervised domain adaptation (UDA) under both data and label distribution shifts, where unreliable pseudo-labels can lead to error accumulation. The authors propose SENTRY, which selectively optimizes predictive entropy based on the consistency of predictions across a committee of random image transformations, achieving significant improvements over state-of-the-art on 27/31 domain shifts.
Many existing approaches for unsupervised domain adaptation (UDA) focus on adapting under only data distribution shift and offer limited success under additional cross-domain label distribution shift. Recent work based on self-training using target pseudo-labels has shown promise, but on challenging shifts pseudo-labels may be highly unreliable, and using them for self-training may cause error accumulation and domain misalignment. We propose Selective Entropy Optimization via Committee Consistency (SENTRY), a UDA algorithm that judges the reliability of a target instance based on its predictive consistency under a committee of random image transformations. Our algorithm then selectively minimizes predictive entropy to increase confidence on highly consistent target instances, while maximizing predictive entropy to reduce confidence on highly inconsistent ones. In combination with pseudo-label based approximate target class balancing, our approach leads to significant improvements over the state-of-the-art on 27/31 domain shifts from standard UDA benchmarks as well as benchmarks designed to stress-test adaptation under label distribution shift.