论文标题
域对齐符合完全测试时间适应
Domain Alignment Meets Fully Test-Time Adaptation
论文作者
论文摘要
部署的ML模型的基本要求是从与培训不同的测试分布中得出的数据概括。解决此问题的一个流行解决方案是仅使用未标记的数据将预训练的模型调整为新的域。在本文中，我们专注于此问题的挑战性变体，其中访问原始源数据受到限制。虽然完全测试时间适应（FTTA）和无监督的域适应性（UDA）密切相关，但UDA的进步不容易适用于TTA，因为大多数UDA方法都需要访问源数据。因此，我们提出了一种新方法，即Cattan，通过放松新颖的深层子空间对准策略来放松访问整个源数据，从而桥接UDA和FTTA。通过为源数据存储的子空间基础设置的最小开销，Cattan可以在适应过程中启用源和目标数据之间的无监督对齐。通过对多个2D和3D视觉基准（Imagenet-C，Office-31，OfficeHome，Domainnet，PointDa-10）和模型体系结构进行广泛的实验评估，我们在FTTA性能方面表现出显着提高。此外，即使使用固有健壮的模型，预训练的VIT表示以及目标域中的样本可用性低，我们也会对对齐目标的实用性做出许多关键发现。
A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. While fully test-time adaptation (FTTA) and unsupervised domain adaptation (UDA) are closely related, the advances in UDA are not readily applicable to TTA, since most UDA methods require access to the source data. Hence, we propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data, through a novel deep subspace alignment strategy. With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation. Through extensive experimental evaluation on multiple 2D and 3D vision benchmarks (ImageNet-C, Office-31, OfficeHome, DomainNet, PointDA-10) and model architectures, we demonstrate significant gains in FTTA performance. Furthermore, we make a number of crucial findings on the utility of the alignment objective even with inherently robust models, pre-trained ViT representations and under low sample availability in the target domain.
