论文标题
ACTMAD：激活与测试时间训练的对齐分布的匹配
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
论文作者
论文摘要
测试时间训练（TTT）是一种通过调整训练有素的模型来应对测试时间发生的分配变化来应对分布（OOD）数据的方法。我们建议通过激活匹配（ACTMAD）执行此适应：我们分析了模型的激活，并将OOD测试数据的对齐激活统计数据与培训数据的激活统计数据进行分析。与现有方法相比，在特征提取器的最终层中对整个通道的分布进行了建模，我们在整个网络中多个层中的每个特征的分布建模。这导致了更细粒度的监督，并使ACTMAD在CIFAR-100C和Imagenet-C上达到了最先进的性能。 ACTMAD也是体系结构和任务无关，它使我们超越了图像分类，在评估Kitti-Fog上的Kitti-Trained对象检测器时，比以前的方法得分15.4％。我们的实验强调，ACTMAD可以在现实的情况下应用于在线适应，几乎没有数据才能达到其全部性能。
Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time. We propose to perform this adaptation via Activation Matching (ActMAD): We analyze activations of the model and align activation statistics of the OOD test data to those of the training data. In contrast to existing methods, which model the distribution of entire channels in the ultimate layer of the feature extractor, we model the distribution of each feature in multiple layers across the network. This results in a more fine-grained supervision and makes ActMAD attain state of the art performance on CIFAR-100C and Imagenet-C. ActMAD is also architecture- and task-agnostic, which lets us go beyond image classification, and score 15.4% improvement over previous approaches when evaluating a KITTI-trained object detector on KITTI-Fog. Our experiments highlight that ActMAD can be applied to online adaptation in realistic scenarios, requiring little data to attain its full performance.
