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 …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

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 …

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

机器学**技术成功地应用于计算机视觉, 自然语言处理和语音识别等众多领域. 然而,
现有的大多数机器学**模型在部署后类别和参数是固定的, 只能泛化到训练集中出现的类别 …

This paper investigates data-free class-incremental learning (DFCIL) for hand gesture
recognition from 3D skeleton sequences. In this class-incremental learning (CIL) setting …

Recently, prompt-based learning has made impressive progress on image class-
incremental learning, but it still lacks sufficient exploration in the video domain. In this paper …

Recent incremental learning for action recognition usually stores representative videos to
mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the …

Class-incremental learning is one of the most important settings for the study of Continual
Learning, as it closely resembles real-world application scenarios. With constrained memory …