Results 321 to 330 of about 842,651 (374)

Class Incremental Learning With Task-Selection

2020 IEEE International Conference on Image Processing (ICIP), 2020
Despite the success of the deep neural networks (DNNs), in case of incremental learning, DNNs are known to suffer from catastrophic forgetting problems which are the phenomenon of entirely forgetting previously learned task information upon learning current task information.
Eun Sung Kim, Jung Uk Kim, Sangmin Lee 0001, Sang-Keun Moon, Yong Man Ro   +4 more
openaire   +1 more source

Task-Agnostic Guided Feature Expansion for Class-Incremental Learning

Computer Vision and Pattern Recognition
The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the model become a prevalent solution for CIL, where the old features are fixed ...
Bowen Zheng, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan   +3 more
semanticscholar   +1 more source

CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning

Computer Vision and Pattern Recognition
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown remarkable ...
Jiangpeng He, Zhihao Duan, F. Zhu
semanticscholar   +1 more source

Distilled Meta-learning for Multi-Class Incremental Learning

ACM Transactions on Multimedia Computing, Communications, and Applications, 2023
Meta-learning approaches have recently achieved promising performance in multi-class incremental learning. However, meta-learners still suffer from catastrophic forgetting, i.e., they tend to forget the learned knowledge from the old tasks when they focus on rapidly adapting to the new classes of the current task.
Hao Liu 0065, Zhaoyu Yan, Bing Liu 0016, Jiaqi Zhao 0001, Yong Zhou 0003, Abdulmotaleb El-Saddik   +5 more
openaire   +1 more source

Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation

Computer Vision and Pattern Recognition, 2023
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 well-studied Class-Incremental Learning (CIL) due to data scarcity.
Linglan Zhao, Jing Lu, Yunlu Xu, Zhanzhan Cheng, Dashan Guo, Yi Niu, Xi Fang   +6 more
semanticscholar   +1 more source

Topology-Preserving Class-Incremental Learning

2020
A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network’s recognition performance on old classes degrades severely when incrementally learning new classes. To alleviate forgetting, we put forward to preserve the old class knowledge by maintaining the topology of the network’s feature space. On this
Xiaoyu Tao, Xinyuan Chang, Xiaopeng Hong, Xing Wei 0001, Yihong Gong   +4 more
openaire   +1 more source

MalFSCIL: A Few-Shot Class-Incremental Learning Approach for Malware Detection

IEEE Transactions on Information Forensics and Security
The continuous evolution of malware is posing a serious threat to personal privacy, enterprise data security, and global network infrastructure. For example, attackers can use phishing emails, botnets, etc.
Yuhan Chai, Ximing Chen, Jing Qiu, Lei Du, Yanjun Xiao, Qiying Feng, Shoulin Ji, Z. Tian   +7 more
semanticscholar   +1 more source

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

arXiv.org
Class Incremental Learning (CIL) aims to continuously learn new categories while retaining the knowledge of old ones. Pre-trained models (PTMs) show promising capabilities in CIL.
Kai Jiang, Zhengyan Shi, Dell Zhang, Hongyuan Zhang, Xuelong Li   +4 more
semanticscholar   +1 more source

Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning

IEEE transactions on circuits and systems for video technology (Print)
Few-Shot Class-Incremental Learning (FSCIL) faces a huge stability-plasticity challenge due to continuously learning knowledge from new classes with a small number of training samples without forgetting the knowledge of previously seen old classes.
Shuo Li, Fang Liu, Licheng Jiao, Lingling Li, Puhua Chen, Xu Liu, Wenping Ma   +6 more
semanticscholar   +1 more source

External Knowledge Injection for CLIP-Based Class-Incremental Learning

IEEE International Conference on Computer Vision
Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-language models (e.g., CLIP) offers a promising starting point for CIL. However,
Da-Wei Zhou, Kai Li, Jingyi Ning, Han-Jia Ye, Lijun Zhang, De-Chuan Zhan   +5 more
semanticscholar   +1 more source