Test Time Adaptation (TTA) is a pivotal concept in machine learning, enabling models to perform well in real-world scenarios, where test data distribution differs from training. In this work, we propose a novel approach called pseudo Source guided Target Clustering (pSTarC) addressing the relatively unexplored area of TTA under real-world domain shifts. This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples. The test samples are strategically aligned with these pseudo-source samples, facilitating their clustering and thereby enhancing TTA performance. pSTarC operates solely within the fully test-time adaptation protocol, removing the need for actual source data. Experimental validation on a variety of domain shift datasets, namely VisDA, Office-Home, DomainNet-126, CIFAR-100C verifies pSTarC's effectiveness. This method exhibits significant improvements in prediction accuracy along with efficient computational requirements. Furthermore, we also demonstrate the universality of the pSTarC framework by showing its effectiveness for the continuous TTA framework. The source code for our method is available at https://manogna-s.github.io/pstarc

翻译：测试时自适应（TTA）是机器学习中的一个关键概念，能够使模型在训练与测试数据分布不一致的现实场景中表现出色。本文提出了一种名为“伪源引导的目标聚类”（pSTarC）的新方法，用于解决实际域偏移场景下相对未被充分探索的TTA问题。该方法受目标聚类技术启发，利用源分类器生成伪源样本，并策略性地将测试样本与这些伪源样本对齐，从而促进样本聚类并提升TTA性能。pSTarC仅在完全测试时自适应协议下运行，无需实际源数据。在VisDA、Office-Home、DomainNet-126和CIFAR-100C等多个域偏移数据集上的实验验证了pSTarC的有效性。该方法在预测精度上取得显著提升，同时保持高效的计算需求。此外，我们还通过展示pSTarC框架在连续TTA框架中的有效性，证明了其通用性。本方法的源代码可在https://manogna-s.github.io/pstarc 获取。