A comprehensive survey of continual learning: theory, method and application
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 …
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
Replay in deep learning: Current approaches and missing biological elements
Replay is the reactivation of one or more neural patterns that are similar to the activation
patterns experienced during past waking experiences. Replay was first observed in …
patterns experienced during past waking experiences. Replay was first observed in …
Deep class-incremental learning: A survey
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 …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Deep long-tailed learning: A survey
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …
to train well-performing deep models from a large number of images that follow a long-tailed …
Online continual learning in image classification: An empirical survey
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 …
images from an online stream of data and tasks, where tasks may include new classes …
Representation compensation networks for continual semantic segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural
networks are required to incorporate new classes continually without catastrophic forgetting …
networks are required to incorporate new classes continually without catastrophic forgetting …
Supervised contrastive replay: Revisiting the nearest class mean classifier in online class-incremental continual learning
Online class-incremental continual learning (CL) studies the problem of learning new
classes continually from an online non-stationary data stream, intending to adapt to new …
classes continually from an online non-stationary data stream, intending to adapt to new …
Continual prototype evolution: Learning online from non-stationary data streams
M De Lange, T Tuytelaars - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Attaining prototypical features to represent class distributions is well established in
representation learning. However, learning prototypes online from streaming data proves a …
representation learning. However, learning prototypes online from streaming data proves a …
A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework
Class imbalance poses new challenges when it comes to classifying data streams. Many
algorithms recently proposed in the literature tackle this problem using a variety of data …
algorithms recently proposed in the literature tackle this problem using a variety of data …
The clear benchmark: Continual learning on real-world imagery
Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However,
existing CL benchmarks, eg Permuted-MNIST and Split-CIFAR, make use of artificial …
existing CL benchmarks, eg Permuted-MNIST and Split-CIFAR, make use of artificial …