Continual learning (CL) is under-explored in the video domain. The few existing works contain splits with imbalanced class distributions over the tasks, or study the problem in …
Z Sun, Y Mu, G Hua - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by …
Y Ge, Y Li, S Ni, J Zhao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned …
Continual learning (CL) aims to develop techniques by which a single model adapts to an increasing number of tasks encountered sequentially, thereby potentially leveraging …
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central …
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data …
Y Gu, X Yang, K Wei, C Deng - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Online class-incremental continual learning aims to learn new classes continually from a never-ending and single-pass data stream, while not forgetting the learned knowledge of old …
Existing continual learning techniques focus on either task incremental learning (TIL) or class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …
L Wang, K Yang, C Li, L Hong… - Proceedings of the …, 2021 - openaccess.thecvf.com
Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual learning …