Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or teacher-student pseudo-labeling schemes for knowledge extraction in unlabeled target domains. However, dynamic data distributions cause miscalibrated predictions and noisy pseudo-labels in existing self-supervised learning methods, hindering the effective mitigation of error accumulation and catastrophic forgetting problems during the continual adaptation process. To tackle these issues, we propose a continual self-supervised method, Adaptive Distribution Masked Autoencoders (ADMA), which enhances the extraction of target domain knowledge while mitigating the accumulation of distribution shifts. Specifically, we propose a Distribution-aware Masking (DaM) mechanism to adaptively sample masked positions, followed by establishing consistency constraints between the masked target samples and the original target samples. Additionally, for masked tokens, we utilize an efficient decoder to reconstruct a hand-crafted feature descriptor (e.g., Histograms of Oriented Gradients), leveraging its invariant properties to boost task-relevant representations. Through conducting extensive experiments on four widely recognized benchmarks, our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks. Our project page: https://sites.google.com/view/continual-mae/home.

翻译：持续测试时自适应（CTTA）旨在将源域预训练模型迁移至持续变化的目标分布，以应对真实世界的动态性。现有CTTA方法主要依赖熵最小化或教师-学生伪标签方案，从无标签目标域中提取知识。然而，动态数据分布会导致现有自监督学习方法中的预测校准偏差和伪标签噪声，从而阻碍在持续自适应过程中有效缓解误差累积和灾难性遗忘问题。为解决这些问题，我们提出了一种持续自监督方法——自适应分布掩码自编码器（ADMA），该方法在增强目标域知识提取的同时，抑制分布偏移的累积。具体而言，我们提出了一种分布感知掩码（DaM）机制，自适应采样掩码位置，并在掩码后的目标样本与原始目标样本之间建立一致性约束。此外，对于掩码令牌，我们利用高效解码器重构手工设计的特征描述符（例如方向梯度直方图），借助其不变性特性增强任务相关表征。通过在四个广泛认可的基准数据集上进行大量实验，本文方法在分类和分割CTTA任务中均达到了最先进的性能。项目页面：https://sites.google.com/view/continual-mae/home。