针对持续域偏移的分割任务，提出自适应伪标签机制提升鲁棒性。
Instance-Aware Test-Time Segmentation for Continual Domain Shifts
- 按图像内置信度分布动态调整伪标签，实现细粒度适应
- 在8个场景中超越现有方法，显著降低错误累积
- 适合长期演化环境下的语义分割应用
持续测试时适应（CTTA）使预训练模型能够适应持续演化的数据分布。现有方法虽提升了鲁棒性，但通常依赖固定或批量级阈值，无法反映不同类别和实例间的难度差异。这一缺陷在语义分割中尤为严重，因需对每张图像进行密集的多类别预测。本文提出一种自适应调整伪标签的方法，根据图像内部置信度分布动态生成监督信号，并动态平衡受域偏移影响较大的类别学习。该细粒度、类别与实例感知的适应策略产生更可靠的监督，有效缓解持续适应过程中的误差累积。在八个CTTA与TTA场景（包括合成到真实及长期域偏移）上的大量实验表明，本方法始终优于当前最优技术，为演化条件下语义分割设立了新标准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。