SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

TL;DR

SENTRY is a novel unsupervised domain adaptation method that uses committee consistency to selectively optimize entropy, improving adaptation under complex domain shifts.

Contribution

It introduces a new approach that assesses target instance reliability via committee consistency and selectively optimizes entropy for better domain adaptation.

Findings

Significant improvements over state-of-the-art on 27/31 domain shifts.

Effective under both distribution and label distribution shifts.

Robustness demonstrated on standard and stress-test benchmarks.

Abstract

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.