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 …
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
Recent advances of continual learning in computer vision: An overview
H Qu, H Rahmani, L Xu, B Williams, J Liu - arXiv preprint arXiv …, 2021 - arxiv.org
In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …
represents a family of methods that accumulate knowledge and learn continuously with data …
Deep class-incremental learning: A survey
DW Zhou, QW Wang, ZH Qi, HJ Ye, DC Zhan… - arXiv preprint arXiv …, 2023 - arxiv.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 …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Learn from others and be yourself in heterogeneous federated learning
W Huang, M Ye, B Du - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Federated learning has emerged as an important distributed learning paradigm, which
normally involves collaborative updating with others and local updating on private data …
normally involves collaborative updating with others and local updating on private data …
Dataset condensation via efficient synthetic-data parameterization
JH Kim, J Kim, SJ Oh, S Yun, H Song… - International …, 2022 - proceedings.mlr.press
The great success of machine learning with massive amounts of data comes at a price of
huge computation costs and storage for training and tuning. Recent studies on dataset …
huge computation costs and storage for training and tuning. Recent studies on dataset …
Constrained few-shot class-incremental learning
M Hersche, G Karunaratne… - Proceedings of the …, 2022 - openaccess.thecvf.com
Continually learning new classes from fresh data without forgetting previous knowledge of
old classes is a very challenging research problem. Moreover, it is imperative that such …
old classes is a very challenging research problem. Moreover, it is imperative that such …
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 …
annotations for new object categories. As other incremental settings, IOD is subject to …
Computationally budgeted continual learning: What does matter?
A Prabhu, HA Al Kader Hammoud… - Proceedings of the …, 2023 - openaccess.thecvf.com
Continual Learning (CL) aims to sequentially train models on streams of incoming data that
vary in distribution by preserving previous knowledge while adapting to new data. Current …
vary in distribution by preserving previous knowledge while adapting to new data. Current …
Coda-prompt: Continual decomposed attention-based prompting for rehearsal-free continual learning
JS Smith, L Karlinsky, V Gutta… - Proceedings of the …, 2023 - openaccess.thecvf.com
Computer vision models suffer from a phenomenon known as catastrophic forgetting when
learning novel concepts from continuously shifting training data. Typical solutions for this …
learning novel concepts from continuously shifting training data. Typical solutions for this …
A theoretical study on solving continual learning
G Kim, C Xiao, T Konishi, Z Ke… - Advances in neural …, 2022 - proceedings.neurips.cc
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL
settings, class incremental learning (CIL) and task incremental learning (TIL). A major …
settings, class incremental learning (CIL) and task incremental learning (TIL). A major …