Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model. However, the number of domains encountered during test time can be very large, and the data is usually unlabeled. Thus, adaptation to new domains is challenging; it is also impractical to generate customized tuned modules for each such domain. Toward addressing these challenges, this work introduces PLUTO: a Plug-and-pLay modUlar Test-time domain adaptatiOn strategy. We pre-train a large set of modules, each specialized for different source domains, effectively creating a ``module store''. Given a target domain with few-shot unlabeled data, we introduce an unsupervised test-time adaptation (TTA) method to (1) select a sparse subset of relevant modules from this store and (2) create a weighted combination of selected modules without tuning their weights. This plug-and-play nature enables us to harness multiple most-relevant source domains in a single inference call. Comprehensive evaluations demonstrate that PLUTO uniformly outperforms alternative TTA methods and that selecting $\leq$5 modules suffice to extract most of the benefit. At a high level, our method equips pre-trained transformers with the capability to dynamically adapt to new domains, motivating a new paradigm for efficient and scalable domain adaptation.

翻译：参数高效微调（PET）方法（如LoRA、Adapter和Visual Prompt Tuning（VPT））通过调整Transformer模型中的小型模块，已在适应新领域方面取得成功。然而，测试时遇到的领域数量可能非常庞大，且数据通常无标签。因此，适应新领域极具挑战性；为每个此类领域生成定制化调优模块也不切实际。为应对这些挑战，本文提出PLUTO：一种即插即用的模块化测试时领域自适应策略。我们预训练大量模块，每个模块针对不同源领域专门优化，有效构建了一个“模块库”。给定目标领域少量无标签数据，我们引入一种无监督测试时自适应（TTA）方法，用于（1）从该库中选择一个稀疏的相关模块子集，以及（2）在不调整权重的情况下创建所选模块的加权组合。这种即插即用特性使我们能够在单次推理调用中利用多个最相关的源领域。全面评估表明，PLUTO始终优于其他TTA方法，且选择≤5个模块即可提取大部分性能优势。从宏观来看，我们的方法使预训练Transformer具备动态适应新领域的能力，为高效且可扩展的领域自适应催生了新范式。