Label Delay in Online Continual Learning

arXiv:2312.00923v2 Announce Type: replace
Abstract: Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and costly annotation processes. We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps. In each step, the framework reveals both unlabeled data from the …

abstract annotation arxiv attention continual cs.cv cs.lg data delay framework however process processes streaming streaming data training training models type