AcTTA：通过动态激活重新审视测试时自适应
AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
把激活函数（ReLU/GELU）重参数化为可学习的阈值偏移与梯度敏感度调制，在测试时只更新这组极少量参数即可应对域偏移，为视觉模型部署时提供了一种比调归一化层更轻量、无需源数据的 TTA 手段。
原文依据 reformulates conventional activation functions (e.g., ReLU, GELU) into parameterized forms that shift their response threshold and modulate gradient sensitivity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论测试时自适应（TTA）旨在通过在推理阶段更新模型参数来缓解分布偏移下的性能退化。现有方法主要围绕仿射调制展开，聚焦于对归一化层进行重新校准。这一视角虽然有效，却忽略了表征动态中的另一个重要组成部分：激活函数。我们重新审视这一被忽视的空间，提出 AcTTA，一个激活感知的框架，它从可学习的角度重新解释传统激活函数，并在测试时对其进行自适应更新。AcTTA 将传统激活函数（如 ReLU、GELU）重构为参数化形式，通过平移其响应阈值并调制梯度敏感度，使网络能够在域偏移下调整激活行为。这种函数级重参数化使得激活行为可以被连续调节，而无需修改网络权重，也无需源数据。尽管方法简单，AcTTA 在多种损坏下均实现了稳健且稳定的自适应。在 CIFAR10-C、CIFAR100-C 和 ImageNet-C 上，AcTTA 一致优于基于归一化的 TTA 方法。我们的发现表明，激活自适应是一条通往域偏移鲁棒测试时学习的紧凑而有效的路径，拓宽了当前以仿射为中心的适应视角。
英文原文摘要 1378 字符
Test-time adaptation (TTA) aims to mitigate performance degradation under distribution shifts by updating model parameters during inference. Existing approaches have primarily framed adaptation around affine modulation, focusing on recalibrating normalization layers. This perspective, while effective, overlooks another influential component in representation dynamics: the activation function. We revisit this overlooked space and propose AcTTA, an activation-aware framework that reinterprets conventional activation functions from a learnable perspective and updates them adaptively at test time. AcTTA reformulates conventional activation functions (e.g., ReLU, GELU) into parameterized forms that shift their response threshold and modulate gradient sensitivity, enabling the network to adjust activation behavior under domain shifts. This functional reparameterization enables continuous adjustment of activation behavior without modifying network weights or requiring source data. Despite its simplicity, AcTTA achieves robust and stable adaptation across diverse corruptions. Across CIFAR10-C, CIFAR100-C, and ImageNet-C, AcTTA consistently surpasses normalization-based TTA methods. Our findings highlight activation adaptation as a compact and effective route toward domain-shift-robust test-time learning, broadening the prevailing affine-centric view of adaptation.