Self-supervised learning has emerged as a method for utilizing massive
unlabeled data for pre-training models, providing an effective feature
extractor for various mobile sensing applications. However, when deployed to
end-users, these models encounter significant domain shifts attributed to user
diversity. We investigate the performance degradation that occurs when
self-supervised models are fine-tuned in heterogeneous domains. To address the
issue, we propose ADAPT^2, a few-shot domain adaptation framework for
personalizing self-supervised models. ADAPT2 proposes self-supervised
meta-learning for initial model pre-training, followed by a user-side model
adaptation by replaying the self-supervision with user-specific data. This
allows models to adjust their pre-trained representations to the user with only
a few samples. Evaluation with four benchmarks demonstrates that ADAPT^2
outperforms existing baselines by an average F1-score of 8.8%p. Our on-device
computational overhead analysis on a commodity off-the-shelf (COTS) smartphone
shows that ADAPT2 completes adaptation within an unobtrusive latency (in three
minutes) with only a 9.54% memory consumption, demonstrating the computational
efficiency of the proposed method.

提出了 ADAPT^2，一种用于个性化自我监督模型的少样本域适应框架，通过重新播放自我监督任务与用户特定数据进行用户端模型适应，以在少样本情况下将模型的预训练表示调整到用户。通过使用四个基准测试，ADAPT^2 的平均 F1 分数超过现有基准测试 8.8% p。在普通的手机上，ADAPT^2 内的装置计算开销分析表明，在不引人注目的延迟（三分钟内）内，ADAPT^2 完成了适应，并且仅占用 9.54% 的内存，从而证明了该方法的计算效率。