子空间优化用于无反向传播的持续测试时间适应
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
AI总结：
本文提出PACE系统，通过子空间优化正常化层的仿射参数，提升持续分布偏移下的适应性能，减少运行时间超过50%。
摘要：
我们介绍了PACE，一种无需反向传播的持续测试时间适应系统，直接优化归一化层的仿射参数。现有无导数方法难以平衡运行时效率与学习能力，因为它们要么限制更新到输入提示，要么要求持续且资源密集的适应，无论领域稳定性如何。为解决这些限制，PACE利用协方差矩阵适应进化策略与Fastfood投影，在低维子空间中优化高维仿射参数，从而获得更优的适应性能。此外，我们通过引入适应停止准则和领域专用向量库来提高运行时效率，消除冗余计算。我们的框架在多个基准上实现了最先进的准确性，在持续分布偏移下，相比现有无反向传播方法，运行时间减少了超过50%。
英文摘要：
We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers. Existing derivative-free approaches struggle to balance runtime efficiency with learning capacity, as they either restrict updates to input prompts or require continuous, resource-intensive adaptation regardless of domain stability. To address these limitations, PACE leverages the Covariance Matrix Adaptation Evolution Strategy with the Fastfood projection to optimize high-dimensional affine parameters within a low-dimensional subspace, leading to superior adaptive performance. Furthermore, we enhance the runtime efficiency by incorporating an adaptation stopping criterion and a domain-specialized vector bank to eliminate redundant computation. Our framework achieves state-of-the-art accuracy across multiple benchmarks under continual distribution shifts, reducing runtime by over 50% compared to existing backpropagation-free methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
