Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the following characteristics required for online adaptation: 1) can work seamlessly with different (preferably small) batch sizes to reduce latency; 2) should continue to work well for the source domain; 3) should have minimal tunable hyper-parameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed SATA framework modifies the batch-norm affine parameters using source anchoring based self-distillation. This ensures that the model incorporates the knowledge of the newly encountered domains, without catastrophically forgetting about the previously seen ones. We also propose a source-prototype driven contrastive alignment to ensure natural grouping of the target samples, while maintaining the already learnt semantic information. Extensive evaluation on three benchmark datasets under challenging settings justify the effectiveness of SATA for real-world applications.

翻译：使已训练模型能够在持续变化的测试域/环境中保持满意性能，是一项重要且具有挑战性的任务。本文提出新型框架SATA，旨在满足在线适应所需的以下特性：1）能够无缝适配不同（最好是小尺寸）批次以降低延迟；2）对源域保持良好性能；3）具有最少的可调超参数与存储需求。给定在源域数据上预训练的网络，所提出的SATA框架通过基于源锚定的自蒸馏方法调整批归一化仿射参数。这确保模型在融合新遇域知识的同时，避免对先前所见域的灾难性遗忘。我们还提出源原型驱动的对比对齐方法，在保持已学习语义信息的前提下实现目标样本的自然聚类。在基准数据集上的广泛评估表明，SATA在现实应用中具有显著有效性。