Modern machine learning pipelines are limited due to data availability, storage quotas,
privacy regulations, and expensive annotation processes. These constraints make it difficult …

Continual learning (CL) is under-explored in the video domain. The few existing works
contain splits with imbalanced class distributions over the tasks, or study the problem in …

Continual learning aims to learn on non-stationary data streams without catastrophically
forgetting previous knowledge. Prevalent replay-based methods address this challenge by …

Continual learning aims to emulate the human ability to continually accumulate knowledge
over sequential tasks. The main challenge is to maintain performance on previously learned …

Continual learning (CL) aims to develop techniques by which a single model adapts to an
increasing number of tasks encountered sequentially, thereby potentially leveraging …

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

As image-based deep learning becomes pervasive on every device, from cell phones to
smart watches, there is a growing need to develop methods that continually learn from data …

Online class-incremental continual learning aims to learn new classes continually from a
never-ending and single-pass data stream, while not forgetting the learned knowledge of old …

Existing continual learning techniques focus on either task incremental learning (TIL) or
class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …

Continual learning usually assumes the incoming data are fully labeled, which might not be
applicable in real applications. In this work, we consider semi-supervised continual learning …