A comprehensive survey of continual learning: theory, method and application

L Wang, X Zhang, H Su, J Zhu - IEEE Transactions on Pattern …, 2024‏ - ieeexplore.ieee.org
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 …

Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need

DW Zhou, ZW Cai, HJ Ye, DC Zhan, Z Liu - arxiv preprint arxiv …, 2023‏ - arxiv.org
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 …

Three types of incremental learning

GM Van de Ven, T Tuytelaars, AS Tolias - Nature Machine Intelligence, 2022‏ - nature.com
Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Class-incremental learning: A survey

DW Zhou, QW Wang, ZH Qi, HJ Ye… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
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 …

Class-incremental learning: survey and performance evaluation on image classification

M Masana, X Liu, B Twardowski… - … on Pattern Analysis …, 2022‏ - ieeexplore.ieee.org
For future learning systems, incremental learning is desirable because it allows for: efficient
resource usage by eliminating the need to retrain from scratch at the arrival of new data; …

Online continual learning in image classification: An empirical survey

Z Mai, R Li, J Jeong, D Quispe, H Kim, S Sanner - Neurocomputing, 2022‏ - Elsevier
Online continual learning for image classification studies the problem of learning to classify
images from an online stream of data and tasks, where tasks may include new classes …

Continual detection transformer for incremental object detection

Y Liu, B Schiele, A Vedaldi… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Incremental object detection (IOD) aims to train an object detector in phases, each with
annotations for new object categories. As other incremental settings, IOD is subject to …

Open-world machine learning: A review and new outlooks

F Zhu, S Ma, Z Cheng, XY Zhang, Z Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Machine learning has achieved remarkable success in many applications. However,
existing studies are largely based on the closed-world assumption, which assumes that the …

Memory replay with data compression for continual learning

L Wang, X Zhang, K Yang, L Yu, C Li, L Hong… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of
representative old training samples has been shown as an effective solution, and achieves …

Training networks in null space of feature covariance for continual learning

S Wang, X Li, J Sun, Z Xu - … of the IEEE/CVF conference on …, 2021‏ - openaccess.thecvf.com
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …