To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

Abstract The field of Continual Learning investigates the ability to learn consecutive tasks
without losing performance on those previously learned. The efforts of researchers have …

Recent breakthroughs in self-supervised learning show that such algorithms learn visual
representations that can be transferred better to unseen tasks than cross-entropy based …

Online continual learning (CL) studies the problem of learning continuously from a single-
pass data stream while adapting to new data and mitigating catastrophic forgetting …

Pre-training is prevalent in nowadays deep learning to improve the learned model's
performance. However, in the literature on federated learning (FL), neural networks are …

Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which
prevents them from leveraging abundant unlabeled data. From an information-theoretic …

In this paper we describe the design and the ideas motivating a new Continual Learning
benchmark for Autonomous Driving (CLAD), that focuses on the problems of object …

Real-time on-device continual learning is needed for new applications such as home robots,
user personalization on smartphones, and augmented/virtual reality headsets. However, this …

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

Abstract Domain incremental learning aims to adapt to a sequence of domains with access
to only a small subset of data (ie, memory) from previous domains. Various methods have …