发表机构
Nanyang Technological University; Sungkyunkwan University（南洋理工大学; 成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对持续测试时自适应中修正不可靠的问题，提出增益感知干预（GAIN）框架，通过历史提出、增益决定的原则，以无反向传播方式实现高效自适应，在多个基准上取得良好性能。
AI 中文摘要
持续测试时自适应（CTTA）将源模型适应于分布可能随时间变化的未标注测试流。现有的TTA方法通常使用置信度或熵来评估预测可靠性，这些主要反映模型对当前样本的自我确定性。在CTTA中，累积的目标观测可以为修正源预测提供补充证据，但随着目标分布的变化，这种历史信息可能变得不匹配。因此，关键问题不在于修正与源预测的差异有多大，而在于是否以及以何种强度应用该修正。本文提出增益感知干预（GAIN），一个无反向传播的CTTA框架，遵循简单原则：历史提出，增益决定。GAIN维护紧凑的目标统计量以形成修正提案，并采用考虑估计不确定性的后验预测评估器。由此产生的源相对增益估计提案的益处，并通过高效的一维优化沿连续路径确定样本特定的干预强度。增益控制的预测随后在线更新目标统计量，限制不可靠修正的传播，全程无需反向传播、样本存储或重放。在五个基准上，我们的方法实现了强大的预测性能，在持续自适应中具有有利的准确性-校准-效率权衡。例如，在ImageNet-C上，GAIN实现了61.9%的准确率，且校准接近源模型。在多样且具有挑战性的持续变化下保持稳定，同时运行速度比代表性的基于优化的CTTA基线快15.9倍。
英文摘要
Continual test-time adaptation (CTTA) adapts a source model to an unlabeled test stream whose distribution may change over time. Existing TTA methods often assess prediction reliability using confidence or entropy, which primarily reflect the model's self-certainty for the current sample. In CTTA, accumulated target observations can provide complementary evidence for correcting the source prediction, but this history may become misaligned as the target distribution changes. The key question is therefore not how much the correction differs from the source prediction, but whether and how strongly it should be applied. This paper proposes Gain-Aware INtervention (GAIN), a backpropagation-free CTTA framework guided by a simple principle: history proposes, gain decides. GAIN maintains compact target statistics to form a correction proposal and a posterior-predictive evaluator that accounts for estimation uncertainty. The resulting source-relative gain estimates the proposal's benefit and determines a sample-specific intervention strength along a continuous path through efficient one-dimensional optimization. Gain-controlled predictions then update the target statistics online, limiting the propagation of unreliable corrections, all without backpropagation, sample storage, or replay. Across five benchmarks, our method achieves strong predictive performance, with favorable accuracy--calibration--efficiency trade-offs in continual adaptation. On ImageNet-C, for example, GAIN achieves 61.9% accuracy with near-source calibration. It remains stable under diverse and challenging continual shifts while running 15.9x faster than a representative optimization-based CTTA baseline.
