Results 331 to 340 of about 842,651 (374)

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

European Conference on Computer Vision
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time.
Linlan Huang, Xusheng Cao, Haori Lu, Xialei Liu   +3 more
semanticscholar   +1 more source

Class-Aware Prompting for Federated Few-Shot Class-Incremental Learning

IEEE transactions on circuits and systems for video technology (Print)
Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from limited samples while preventing catastrophic forgetting. With the increasing distribution of learning data across different clients and privacy concerns, FSCIL faces
Fang liang, Yu-Wei Zhan, Jiale Liu, Chong-Yu Zhang, Zhen-Duo Chen, Xin Luo, Xinshun Xu   +6 more
semanticscholar   +1 more source

A Few-Shot Class-Incremental Learning Method for Network Intrusion Detection

IEEE Transactions on Network and Service Management
With the rapid development of information technologies, the security of cyberspace has become increasingly serious. Network intrusion detection is a practical scheme to protect network systems from cyber attacks.
Lei Du, Zhaoquan Gu, Yechen Wang, Le Wang, Yan Jia   +4 more
semanticscholar   +1 more source

Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt

European Conference on Computer Vision
Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading to overfitting and hindering the ...
Chenxi Liu, Zhenyi Wang, Tianyi Xiong, Ruibo Chen, Yihan Wu, Junfeng Guo, Heng Huang   +6 more
semanticscholar   +1 more source

Retrospective Class Incremental Learning

2021 IEEE International Conference on Multimedia and Expo (ICME), 2021
Qingyi Tao, Chen Change Loy, Jianfei Cai 0001, ZongYuan Ge, Simon See   +4 more
openaire   +1 more source

MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

AAAI Conference on Artificial Intelligence
Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as the model ...
Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye   +5 more
semanticscholar   +1 more source

Pseudo-Labeling for Class Incremental Learning [PDF]

Proceedings of the British Machine Vision Conference 2021, 2021
Alexis Lechat, Stéphane Herbin, Frédéric Jurie   +2 more
openaire   +1 more source

DiffClass: Diffusion-Based Class Incremental Learning

European Conference on Computer Vision
Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data.
Zichong Meng, Jie Zhang, Changdi Yang, Zheng Zhan, Pu Zhao, Yanzhi Wang   +5 more
semanticscholar   +1 more source

CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning

European Conference on Computer Vision
Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.
Junghun Oh, Sungyong Baik, Kyoung Mu Lee
semanticscholar   +1 more source

FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning

Computer Vision and Pattern Recognition
Non-Exemplar Class Incremental Learning (NECIL) involves learning a classification model on a sequence of data without access to exemplars from previously encountered old classes. Such a stringent constraint always leads to catastrophic forgetting of the
Qiwei Li, Yuxin Peng, Jiahuan Zhou
semanticscholar   +1 more source