Abstract
Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying difficulty across classes and instances. This limitation is especially problematic in semantic segmentation, where each image requires dense, multi-class predictions. We propose an approach that adaptively adjusts pseudo labels to reflect the confidence distribution within each image and dynamically balances learning toward classes most affected by domain shifts. This fine-grained, class- and instance-aware adaptation produces more reliable supervision and mitigates error accumulation throughout continual adaptation. Extensive experiments across eight CTTA and TTA scenarios, including synthetic-to-real and long-term shifts, show that our method consistently outperforms state-of-the-art techniques, setting a new standard for semantic segmentation under evolving conditions.
Abstract (translated)
持续测试时间适应（CTTA）使预训练模型能够适应不断变化的领域。现有的方法虽然提高了鲁棒性，但通常依赖于固定的或批处理级别的阈值，这无法考虑不同类别和实例之间的难度差异。这种限制在语义分割任务中尤为突出，因为每个图像都需要密集且多类别的预测。我们提出了一种自适应调整伪标签的方法，以反映每张图片内部的置信度分布，并动态平衡针对受领域变化影响最大的类别的学习过程。这种方法通过提供更可靠的监督信号并减轻连续适应过程中误差积累的问题，实现了细粒度、类别和实例感知的适应性。在八个CTTA和TTA场景下的广泛实验中（包括合成到真实以及长期的变化），我们的方法始终优于最先进的技术，在不断变化条件下进行语义分割方面设立了新标准。
URL
https://arxiv.org/abs/2512.08569
