Results 11 to 20 of about 842,651 (374)
Federated Class-Incremental Learning [PDF]
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Federated learning (FL) has attracted growing attentions via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume object classes of the overall framework are fixed over time.
Jiahua Dong +6 more
semanticscholar +3 more sources
Essentials for Class Incremental Learning [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world applications. In this work, we shed light on the causes of this well-known yet unsolved phenomenon - often referred to as ...
Sudhanshu Mittal +2 more
openaire +2 more sources
Multi-view class incremental learning
Information Fusion, 2023 Multi-view learning (MVL) has gained great success in integrating information from multiple perspectives of a dataset to improve downstream task performance. To make MVL methods more practical in an open-ended environment, this paper investigates a novel paradigm called multi-view class incremental learning (MVCIL), where a single model incrementally ...
Depeng Li +5 more
openalex +3 more sources
FOSTER: Feature Boosting and Compression for Class-Incremental Learning [PDF]
European Conference on Computer Vision, 2022 The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories.
Fu-Yun Wang +3 more
semanticscholar +1 more source
Class-Incremental Learning with Generative Classifiers [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 Incrementally training deep neural networks to recognize new classes is a challenging problem. Most existing class-incremental learning methods store data or use generative replay, both of which have drawbacks, while 'rehearsal-free' alternatives such as parameter regularization or bias-correction methods do not consistently achieve high performance ...
van de Ven, Gido M. +2 more
openaire +3 more sources
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [PDF]
International Conference on Learning Representations, 2023 Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions.
Yibo Yang +5 more
semanticscholar +1 more source
Class-Incremental Exemplar Compression for Class-Incremental Learning
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Accepted to CVPR ...
Zilin Luo +3 more
openaire +3 more sources
Class-Incremental Learning with Repetition
CoRR, 2023 Accepted to the 2nd Conference on Lifelong Learning Agents (CoLLAs), 2023 19 ...
Hamed Hemati +7 more
openaire +6 more sources
Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation [PDF]
Computer Vision and Pattern Recognition, 2022 We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks.
Minsoo Kang, Jaeyoo Park, Bohyung Han
semanticscholar +1 more source
Taxonomic Class Incremental Learning
CoRR, 2023 The problem of continual learning has attracted rising attention in recent years. However, few works have questioned the commonly used learning setup, based on a task curriculum of random class. This differs significantly from human continual learning, which is guided by taxonomic curricula.
Yuzhao Chen +3 more
openaire +2 more sources