LGCVOct 3, 2023

Bag of Tricks for Fully Test-Time Adaptation

arXiv:2310.02416v211 citationsh-index: 51
AI Analysis

This work consolidates knowledge for researchers in TTA, though it is incremental as it builds on existing techniques rather than introducing new methods.

The paper tackles the challenge of fairly comparing individual techniques in Fully Test-Time Adaptation (TTA) for adapting models to data drifts, and by categorizing and analyzing orthogonal TTA techniques, it establishes new state-of-the-art results through synergistic combinations.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes