发表机构
Anhui University; University of Nottingham (Malaysia Campus); University of Sassari; University of Warwick（安徽大学; 诺丁汉大学（马来西亚校区）; 萨萨里大学; 华威大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对测试时自适应中的错误累积与灾难性遗忘，提出蒸馏图像原型框架DIPTTA，通过动态特征回放和源校准不确定性估计，在多个基准上显著优于现有方法。
AI 中文摘要
测试时自适应（TTA）增强了模型对分布偏移的鲁棒性，但面临两个关键挑战：噪声伪标签导致的错误累积以及源知识的灾难性遗忘。为缓解错误累积而设计的基于不确定性的方法往往产生过度自信或计算成本高昂的估计，而旨在通过原型回放防止遗忘的策略则依赖静态表示，随着模型自适应，这些表示容易变得错位。为解决这些问题，本文提出了一种新颖框架——蒸馏图像原型用于引导式测试时自适应（DIPTTA）。所提方法的核心是引入蒸馏图像原型（DIP），这是一组紧凑的合成图像，作为源知识的动态且可再生的锚点。该原型实现了动态特征回放机制，持续生成与模型当前状态对齐的特征原型，从而有效防止灾难性遗忘。此外，DIP锚定了一种源校准的不确定性估计方法，通过利用稳定的源知识提供偏差更小的样本可靠性度量，从而稳健地抑制错误累积。在多个基准上的大量实验表明，DIPTTA显著优于最先进的方法，尤其是在严重域偏移下。源代码可在以下网址获取：此https URL。
英文摘要
Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from noisy pseudo-labels and catastrophic forgetting of source knowledge. Uncertainty-based approaches designed to mitigate error accumulation often yield overconfident or computationally expensive estimates, while strategies intended to prevent forgetting via prototype replay rely on static representations that easily become misaligned as the model adapts. To address these issues, this paper proposes a novel framework, Distilling Image Prototype for Guided Test-Time Adaptation (DIPTTA). The core of the proposed approach is the introduction of a Distill Image Prototype (DIP), a compact set of synthetic images that serves as a dynamic and regenerative anchor of source knowledge. This prototype enables a dynamic feature replay mechanism that continuously generates feature prototypes aligned with the current state of the model, thus effectively preventing catastrophic forgetting. Furthermore, the DIP anchors a source-calibrated uncertainty estimation method, which provides a less biased measure of sample reliability by leveraging stable source knowledge, thereby robustly suppressing error accumulation. Extensive experiments on multiple benchmarks demonstrate that DIPTTA significantly outperforms state-of-the-art methods, particularly under severe domain shifts. The source code is available at https://github.com/LiwenWang919/DIPTTA.
