A survey on continual semantic segmentation: Theory, challenge, method and application

B Yuan, D Zhao - IEEE Transactions on Pattern Analysis and …, 2024 - ieeexplore.ieee.org
Continual learning, also known as incremental learning or life-long learning, stands at the
forefront of deep learning and AI systems. It breaks through the obstacle of one-way training …

Continual Learning and Catastrophic Forgetting

GM van de Ven, N Soures, D Kudithipudi - arXiv preprint arXiv:2403.05175, 2024 - arxiv.org
This book chapter delves into the dynamics of continual learning, which is the process of
incrementally learning from a non-stationary stream of data. Although continual learning is a …

CL3: Generalization of Contrastive Loss for Lifelong Learning

K Roy, C Simon, P Moghadam, M Harandi - Journal of Imaging, 2023 - mdpi.com
Lifelong learning portrays learning gradually in nonstationary environments and emulates
the process of human learning, which is efficient, robust, and able to learn new concepts …

Flashback for Continual Learning

L Mahmoodi, M Harandi… - Proceedings of the …, 2023 - openaccess.thecvf.com
To strike a delicate balance between model stability and plasticity of continual learning,
previous approaches have adopted strategies to guide model updates on new data to …

[HTML][HTML] Multivariate prototype representation for domain-generalized incremental learning

C Peng, P Koniusz, K Guo, BC Lovell… - Computer Vision and …, 2024 - Elsevier
Deep learning models often suffer from catastrophic forgetting when fine-tuned with samples
of new classes. This issue becomes even more challenging when there is a domain shift …

A masking, linkage and guidance framework for online class incremental learning

G Liang, Z Chen, S Su, S Zhang, Y Zhang - Pattern Recognition, 2025 - Elsevier
Due to the powerful ability to acquire new knowledge and preserve previously learned
concepts from a dynamic data stream, continual learning has recently garnered substantial …

Class similarity weighted knowledge distillation for few shot incremental learning

F Akmel, F Meng, Q Wu, S Chen, R Zhang, M Assefa - Neurocomputing, 2024 - Elsevier
Few-shot class incremental learning illustrates the challenges of learning new concepts,
where the learner can access only a small sample per concept. The standard incremental …

Federated Incremental Named Entity Recognition

D Zhang, Y Yu, C Li, J Dong, D Yu - arXiv preprint arXiv:2411.11623, 2024 - arxiv.org
Federated Named Entity Recognition (FNER) boosts model training within each local client
by aggregating the model updates of decentralized local clients, without sharing their private …

Inductive Graph Few-shot Class Incremental Learning

Y Li, P Moghadam, C Peng, N Ye, P Koniusz - arXiv preprint arXiv …, 2024 - arxiv.org
Node classification with Graph Neural Networks (GNN) under a fixed set of labels is well
known in contrast to Graph Few-Shot Class Incremental Learning (GFSCIL), which involves …

M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning

K Roy, A Dissanayake, B Tidd, P Moghadam - arXiv preprint arXiv …, 2024 - arxiv.org
Lifelong imitation learning for manipulation tasks poses significant challenges due to
distribution shifts that occur in incremental learning steps. Existing methods often focus on …