能量波动化与再分配用于测试时自适应：一个控制系统的视角
Energy Waveify and Redistribution for Test-Time Adaptation: A Control System Perspective
用复值波函数与概率流守恒替代朗之万/蒙特卡洛迭代采样来更新能量模型，可作为一种免随机采样的测试时自适应模块，直接插入依赖能量模型的视觉分类或分割流程中以降低自适应延迟。
原文依据 achieving adaptive energy redistribution without additional stochastic sampling while preserving the overall normalization of the energy landscape
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本工作针对测试时能量自适应中的一个关键挑战：近期最优的测试时自适应（TTA）方法建立在能量模型之上，这些方法依赖迭代的蒙特卡洛或朗之万动力学采样，对每个测试实例进行多次随机更新以近似能量梯度，因而带来难以承受的时间开销。我们从一种新颖的控制系统视角来解决该问题：i）将能量描述为复值波，其中振幅编码能量不确定性，相位刻画其演化；ii）维护一个含时波动方程，将 TTA 解释为控制系统的演化过程。通过施加控制系统的概率流守恒定律，我们的方法引导概率流从高能量（易出错）区域流向低能量（准确）区域，在无需额外随机采样的情况下实现自适应能量再分配，同时保持能量景观的整体归一化。实验上，所提方法在多个公开基准数据集上显著优于基线方法，其自适应时间仅为所比较的 Top-1 至 Top-3 基线所需时间的 1/3 至 1/7。代码见 https://github.com/wongzbb/APT。
英文原文摘要 1276 字符
This work tackles a key challenge in test-time energy adaptation: prohibitive time overhead arising from recent state-of-the-art test-time adaptation (TTA) methods, which are built on energy models relying on iterative Monte Carlo or Langevin dynamics sampling with multiple stochastic updates per test instance to approximate energy gradients. We tackle the problem from an innovative control system perspective by i) describing the energy as a complex-valued wave, where the amplitude encodes energy uncertainty and the phase characterizes its evolution, and ii) maintaining a time-dependent wave equation that interprets TTA as a control system evolution process. By enforcing the control system law of probability current conservation, our method directs probability current away from high-energy (error-prone) regions toward low-energy (accurate) ones, achieving adaptive energy redistribution without additional stochastic sampling while preserving the overall normalization of the energy landscape. Experimentally, the proposed method significantly outperforms baseline methods across several public benchmark datasets, with adaptive time being only 1/3 1/7 of that required by the compared Top-1 to Top-3 baselines. Code is available at https://github.com/wongzbb/APT.