# Effortless Active Labeling for Long-Term Test-Time Adaptation

arXiv: https://arxiv.org/abs/2503.14564 · HTML: https://mlsanity.com/paper/2503.14564/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2025.

## Built on by (most cited first, 7 of 7)

- [Active Test-time Vision-Language Navigation](https://mlsanity.com/paper/2506.06630/) (2025)
- [CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation](https://mlsanity.com/paper/2509.25692/) (2025)
- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)
- [ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2602.23653/) (2026)
- [EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Models](https://mlsanity.com/paper/2603.14666/) (2026)
- [Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2608.12279/) (2026)
- [WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation](https://mlsanity.com/paper/2609.37687/) (2026)

## Abstract (arXiv)

Long-term test-time adaptation (TTA) is a challenging task due to error accumulation. Recent approaches tackle this issue by actively labeling a small proportion of samples in each batch, yet the annotation burden quickly grows as the batch number increases. In this paper, we investigate how to achieve effortless active labeling so that a maximum of one sample is selected for annotation in each batch. First, we annotate the most valuable sample in each batch based on the single-step optimization perspective in the TTA context. In this scenario, the samples that border between the source- and target-domain data distributions are considered the most feasible for the model to learn in one iteration. Then, we introduce an efficient strategy to identify these samples using feature perturbation. Second, we discover that the gradient magnitudes produced by the annotated and unannotated samples have significant variations. Therefore, we propose balancing their impact on model optimization using two dynamic weights. Extensive experiments on the popular ImageNet-C, -R, -K, -A and PACS databases demonstrate that our approach consistently outperforms state-of-the-art methods with significantly lower annotation costs.