Bag of Tricks for Fully Test-Time Adaptation

TL;DR

This paper systematically analyzes various techniques for fully test-time adaptation, clarifying their individual impacts, trade-offs, and synergies to advance robust model adaptation to data drifts.

Contribution

It provides a comprehensive categorization and detailed analysis of orthogonal TTA techniques, highlighting their effects and combined benefits.

Findings

Identified key techniques that improve TTA robustness

Analyzed trade-offs between accuracy and computational complexity

Achieved new state-of-the-art results through technique combinations

Abstract

Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure robust learning on arbitrary streams of unlabeled data. However, assessing the true impact of each individual technique and obtaining a fair comparison still constitutes a significant challenge. To help consolidate the community's knowledge, we present a categorization of selected orthogonal TTA techniques, including small batch normalization, stream rebalancing, reliable sample selection, and network confidence calibration. We meticulously dissect the effect of each approach on different scenarios of interest. Through our analysis, we shed light on trade-offs induced by those techniques between accuracy, the computational power required, and model complexity. We also uncover the synergy that arises when combining techniques and are able to establish new state-of-the-art results.