H Liu, L Gu, Z Chi, Y Wang, Y Yu, J Chen… - European Conference on …, 2022 - Springer
Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer …
A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network's recognition performance on old classes degrades …
Z Hu, Y Li, J Lyu, D Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is …
Recent years have witnessed growing interests in developing deep models for incremental learning. However, existing approaches often utilize the fixed structure and online …
Incremental learning with deep neural networks often suffers from catastrophic forgetting, where newly learned patterns may completely erase the previous knowledge. A remedy is to …
Q Jodelet, X Liu, YJ Phua… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional …
Y Liu, Y Li, B Schiele, Q Sun - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity …
X Tao, X Hong, X Chang, S Dong… - Proceedings of the …, 2020 - openaccess.thecvf.com
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot …
L Zhao, J Lu, Y Xu, Z Cheng, D Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Few-Shot Class-Incremental Learning (FSCIL) aims to continually learn novel classes based on only few training samples, which poses a more challenging task than the …