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 …
H Cha, J Lee, J Shin - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
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 …
H Shi, H Wang - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
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 …