Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive ...
However, the majority of these works constrain the representation of class prototypes implicitly through complex network structures, such as multi-attention mechanisms, graph neural networks, and contrastive learning, which constrict the model's ability to generalize. In addition, most models with ...
(SWAV这篇paper,个人感觉才是真正意义上在做contrastive learning的事情,个人认为contrastive learning和deep metric learning的最大的区别主要在于前者其实更多focus在对比任务的设计上,即怎么去对比的问题,而不在 已知怎么对比的情况下,去上各种各样的优化手段增强对比的效果,后者个人感觉其实和deep metric learning的rese...
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approache...