非平稳测试时适应的逐层自动加权
Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
AI总结：
本文提出一种用于非平稳测试时适应的逐层自动加权算法，利用FIM设计学习权重并引入指数极小极大缩放器，在最小化遗忘和误差累积的同时显著降低计算负荷，实现高效适应。
摘要：
鉴于现实应用中推理期间领域偏移的不可避免性，测试时适应（TTA）对于模型部署后的适应至关重要。然而，目标分布不断变化的现实场景带来了灾难性遗忘和误差累积等挑战。针对非平稳领域偏移的现有TTA方法虽然有效，但会产生过高的计算负荷，使其难以应用于设备端环境。本文提出一种用于持续和渐进TTA的逐层自动加权算法，可自主识别需要保留或集中适应的层。通过利用Fisher信息矩阵（FIM），我们首先设计学习权重以选择性地关注与对数似然变化相关的层，同时保留不相关的层。然后，我们进一步提出一种指数极小极大缩放器，使特定层近乎冻结，同时缓解异常值。这能最小化遗忘和误差累积，从而实现对非平稳目标分布的高效适应。在CIFAR-10C、CIFAR-100C和ImageNet-C上的实验表明，我们的方法优于传统的持续和渐进TTA方法，同时显著降低了计算负荷，突显了基于FIM的学习权重在适应持续或逐渐偏移的目标域中的重要性。
英文摘要：
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presents challenges including catastrophic forgetting and error accumulation. Existing TTA methods for non-stationary domain shifts, while effective, incur excessive computational load, making them impractical for on-device settings. In this paper, we introduce a layer-wise auto-weighting algorithm for continual and gradual TTA that autonomously identifies layers for preservation or concentrated adaptation. By leveraging the Fisher Information Matrix (FIM), we first design the learning weight to selectively focus on layers associated with log-likelihood changes while preserving unrelated ones. Then, we further propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. This minimizes forgetting and error accumulation, leading to efficient adaptation to non-stationary target distribution. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches while significantly reducing computational load, highlighting the importance of FIM-based learning weight in adapting to continuously or gradually shifting target domains.
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。
