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 …

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously
acquired knowledge. However, recent CL advances are restricted to supervised continual …

Rehearsal is a critical component for class-incremental continual learning, yet it requires a
substantial memory budget. Our work investigates whether we can significantly reduce this …

Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks
without incurring forgetting. CL settings proposed in literature assume that every incoming …

Continuous unsupervised representation learning (CURL) research has greatly benefited
from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL …

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 …

Abstract Current evaluations of Continual Learning (CL) methods typically assume that there
is no constraint on training time and computation. This is an unrealistic assumption for any …

Learning under a continuously changing data distribution with incorrect labels is a desirable
real-world problem yet challenging. Large body of continual learning (CL) methods …

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

The goal of continual learning is to improve the performance of recognition models in
learning sequentially arrived data. Although most existing works are established on the …