The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize large quantities of unlabeled data for learning representations. Contrastive Predictive Coding (CPC) is one such method, learning effective representations by leveraging properties of time-series data to setup a contrastive future timestep prediction task. In this work, we propose enhancements to CPC, by systematically investigating the encoder architecture, the aggregator network, and the future timestep prediction, resulting in a fully convolutional architecture, thereby improving parallelizability. Across sensor positions and activities, our method shows substantial improvements on four of six target datasets, demonstrating its ability to empower a wide range of application scenarios. Further, in the presence of very limited labeled data, our technique significantly outperforms both supervised and self-supervised baselines, positively impacting situations where collecting only a few seconds of labeled data may be possible. This is promising, as CPC does not require specialized data transformations or reconstructions for learning effective representations.
翻译:获得活动说明具有挑战性,而从可磨损的数据收集则比较直接,两者的区别性使得人们非常关注开发利用大量未贴标签数据进行学习演示的技术。 相矛盾的预测编码(CPC)就是这样一种方法,通过利用时间序列数据的特性来利用时间序列数据的特性来制定对比性的未来时间步骤预测任务,来学习有效的表述。在这项工作中,我们建议通过系统调查编码器结构、聚合器网络和未来时间步骤预测来加强CPC,从而形成一个完全革命性的结构,从而改进平行性。在传感器的位置和活动之间,我们的方法显示六套目标数据集中的四套有了重大改进,显示了它有能力增强广泛的应用情景。此外,在存在非常有限的标签数据的情况下,我们的技术大大超越了受监管和自我监督的基线,对仅收集几秒钟标签数据的可能性产生了积极影响。这很有希望,因为CPC不需要专门的数据转换或重建来学习有效演示。