MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning | IEEE Journals & Magazine | IEEE Xplore

MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning


Abstract:

As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowl...Show More

Abstract:

As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this paper, we concentrate on this “slow versus fast” (SvF) dilemma to determine which knowledge components to be updated in a slow fashion or a fast fashion, and thereby balance old-knowledge preservation and new-knowledge adaptation. We propose a multi-grained SvF learning strategy to cope with the SvF dilemma from two different grains: intra-space (within the same feature space) and inter-space (between two different feature spaces). The proposed strategy designs a novel frequency-aware regularization to boost the intra-space SvF capability, and meanwhile develops a new feature space composition operation to enhance the inter-space SvF learning performance. With the multi-grained SvF learning strategy, our method outperforms the state-of-the-art approaches by a large margin.
Page(s): 1576 - 1588
Date of Publication: 09 December 2021

ISSN Information:

PubMed ID: 34882547

Funding Agency:

Citations are not available for this document.

Cites in Papers - |

Cites in Papers - IEEE (42)

Select All
1.
Bo Cui, JiaHui Yao, "CBL-ISL: A CNN and Bi-LSTM-Based Incremental Few-Shot Learning Approach for Real-Time Intrusion Detection in Industrial Internet of Things (IIoT) Systems", 2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp.1770-1775, 2025.
2.
Zicheng Pan, Xiaohan Yu, Yongsheng Gao, "Session-Guided Attention in Continuous Learning With Few Samples", IEEE Transactions on Image Processing, vol.34, pp.2654-2666, 2025.
3.
Kirill Paramonov, Mete Ozay, Eunju Yang, Jijoong Moon, Umberto Michieli, "Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning", ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.1-5, 2025.
4.
Jialu Wu, Shaofan Wang, Yanfeng Sun, Baocai Yin, Qingming Huang, "Dual-Domain Division Multiplexer for General Continual Learning: A Pseudo Causal Intervention Strategy", IEEE Transactions on Image Processing, vol.34, pp.1966-1979, 2025.
5.
Parinita Nema, Vinod K Kurmi, "Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning", 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp.6394-6403, 2025.
6.
Jinghua Zhang, Li Liu, Olli Silvén, Matti Pietikäinen, Dewen Hu, "Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.47, no.4, pp.2924-2945, 2025.
7.
Shuo Li, Fang Liu, Licheng Jiao, Lingling Li, Puhua Chen, Xu Liu, Wenping Ma, "Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning", IEEE Transactions on Circuits and Systems for Video Technology, vol.35, no.5, pp.4991-5005, 2025.
8.
Yifan Zhao, Jia Li, Zeyin Song, Yonghong Tian, "Language-Inspired Relation Transfer for Few-Shot Class-Incremental Learning", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.47, no.2, pp.1089-1102, 2025.
9.
Tao Chen, Yanrong Guo, Shijie Hao, Richang Hong, "Leaving None Behind: Data-Free Domain Incremental Learning for Major Depressive Disorder Detection", IEEE Transactions on Affective Computing, vol.16, no.2, pp.758-770, 2025.
10.
Lingzhe Kong, Fei Gao, Xiaoyu He, Jun Wang, Jinping Sun, Huiyu Zhou, Amir Hussain, "Few-Shot Class-Incremental SAR Target Recognition via Orthogonal Distributed Features", IEEE Transactions on Aerospace and Electronic Systems, vol.61, no.1, pp.325-341, 2025.
11.
Zicheng Pan, Xiaohan Yu, Miaohua Zhang, Weichuan Zhang, Yongsheng Gao, "DyCR: A Dynamic Clustering and Recovering Network for Few-Shot Class-Incremental Learning", IEEE Transactions on Neural Networks and Learning Systems, vol.36, no.4, pp.7116-7129, 2025.
12.
Xuewei Li, Guangcong Zheng, Yunlong Yu, Naye Ji, Xi Li, "Relationship-Incremental Scene Graph Generation by a Divide-and-Conquer Pipeline With Feature Adapter", IEEE Transactions on Image Processing, vol.34, pp.678-688, 2025.
13.
Cheng Feng, Chaoliang Zhong, Jie Wang, Jun Sun, Yasuto Yokota, "Conditional Past Experience Generation for Dark Continual Learning", 2024 IEEE International Conference on Image Processing (ICIP), pp.284-290, 2024.
14.
Kang Sun, Yao Liu, Genzhong Zhang, "Few-shot Incremental Event Detection Based on Auxiliary Cluster and Feature Transfer", 2024 International Seminar on Artificial Intelligence, Computer Technology and Control Engineering (ACTCE), pp.220-225, 2024.
15.
Xuan Wang, Zhong Ji, Yunlong Yu, Yanwei Pang, Jungong Han, "Model Attention Expansion for Few-Shot Class-Incremental Learning", IEEE Transactions on Image Processing, vol.33, pp.4419-4431, 2024.
16.
Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu, "Class-Incremental Learning: A Survey", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.46, no.12, pp.9851-9873, 2024.
17.
De Cheng, Yuxin Zhao, Nannan Wang, Guozhang Li, Dingwen Zhang, Xinbo Gao, "Efficient Statistical Sampling Adaptation for Exemplar-Free Class Incremental Learning", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.11, pp.11451-11463, 2024.
18.
Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan, "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning", 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.23554-23564, 2024.
19.
R. O. Malashin, M. A. Mikhalkova, "Avoiding Catastrophic Forgetting Via Neuronal Decay", 2024 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF), pp.1-6, 2024.
20.
Yiming Wu, Hangfei Li, Fangfang Wang, Yilong Zhang, Ronghua Liang, "Self-Distilled Dynamic Fusion Network for Language-Based Fashion Retrieval", ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.3260-3264, 2024.
21.
Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche, Leo Zhao, Abbas Rahimi, Luca Benini, "12 mJ Per Class On-Device Online Few-Shot Class-Incremental Learning", 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp.1-6, 2024.
22.
Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche, Leo Zhao, Abbas Rahimi, Luca Benini, "12 mJ Per Class On-Device Online Few-Shot Class-Incremental Learning", 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp.1-6, 2024.
23.
Sichao Fu, Qinmu Peng, Xiaorui Wang, Yang He, Wenhao Qiu, Bin Zou, Duanquan Xu, Xiao-Yuan Jing, Xinge You, "Jointly Optimized Classifiers for Few-Shot Class-Incremental Learning", IEEE Transactions on Emerging Topics in Computational Intelligence, vol.8, no.5, pp.3316-3326, 2024.
24.
Shuai Chen, Mingyi Zhang, Junge Zhang, Kaiqi Huang, "Exemplar-Based Continual Learning via Contrastive Learning", IEEE Transactions on Artificial Intelligence, vol.5, no.7, pp.3313-3324, 2024.
25.
Ruru Zhang, E Haihong, Meina Song, "FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification", Chinese Journal of Electronics, vol.33, no.1, pp.139-152, 2024.
26.
Yan Zhao, Lingjun Zhao, Siqian Zhang, Kefeng Ji, Gangyao Kuang, Li Liu, "Azimuth-Aware Subspace Classifier for Few-Shot Class-Incremental SAR ATR", IEEE Transactions on Geoscience and Remote Sensing, vol.62, pp.1-20, 2024.
27.
Solang Kim, Yuho Jeong, Joon Sung Park, Sung Whan Yoon, "MICS: Midpoint Interpolation to Learn Compact and Separated Representations for Few-Shot Class-Incremental Learning", 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp.2225-2234, 2024.
28.
Jiashuo Li, Songlin Dong, Yihong Gong, Yuhang He, Xing Wei, "Analogical Learning-Based Few-Shot Class-Incremental Learning", IEEE Transactions on Circuits and Systems for Video Technology, vol.34, no.7, pp.5493-5504, 2024.
29.
Lei Du, Zhaoquan Gu, Ye Wang, Le Wang, Yan Jia, "A Few-Shot Class-Incremental Learning Method for Network Intrusion Detection", IEEE Transactions on Network and Service Management, vol.21, no.2, pp.2389-2401, 2024.
30.
Jie Du, Peng Liu, Chi-Man Vong, Chuangquan Chen, Tianfu Wang, C. L. Philip Chen, "Class-Incremental Learning Method With Fast Update and High Retainability Based on Broad Learning System", IEEE Transactions on Neural Networks and Learning Systems, vol.35, no.8, pp.11332-11345, 2024.

Cites in Papers - Other Publishers (15)

1.
Ning Zhu, Shaofan Wang, Yanfeng Sun, Baocai Yin, "Uncertainty-guided recurrent prototype distillation for graph few-shot class-incremental learning", Multimedia Systems, vol.31, no.3, 2025.
2.
Meilan Hao, Yiren Cai, Xiaoqing Lv, Yizhan Gu, Kai Zhou, Jianing Wang, Xin Ning, , 2025.
3.
Li Jiao, Wenlong Fu, Xiaolu Chen, "Image–Text (IT)-Prompt: Prompt-Based Learning Framework Empowered by the Cluster-Based Nearest Class Mean (C-NCM) for Rehearsal-Free Contrastive Language–Image Pretraining (CLIP)-Based Continual Learning", Applied Sciences, vol.15, no.6, pp.2966, 2025.
4.
Qiuyue Ruan, Shanxiong Chen, Hailing Xiong, Yuqi Ma, Mingyue Yang, Wenjun Zhen, Jiang Yuan, Xiaoliang Li, Xun Pu, Jian Qin, "DFS: Dual-branch forward-looking simulation network for incremental learning of ancient Chinese characters", npj Heritage Science, vol.13, no.1, 2025.
5.
Yang Chu, Yuntao Qian, "Incremental classification of remote sensing images using feature pyramid and class hierarchy enhanced by label relationship graphs", Applied Intelligence, vol.55, no.3, 2025.
6.
Seongbeom Park, Haeji Jung, Daewon Chae, Hyunju Yun, Sungyoon Kim, Suhong Moon, Jinkyu Kim, Seunghyun Park, "Text-Driven Prototype Learning for Few-Shot Class-Incremental Learning", Pattern Recognition, vol.15309, pp.16, 2025.
7.
Longrong Yang, Hanbin Zhao, Yunlong Yu, Xiaodong Zeng, Xi Li, "RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-Based Continual Learning", Computer Vision – ECCV 2024, vol.15105, pp.1, 2025.
8.
Li Jiao, Lihong Cao, Tian Wang, "Prompt-based Continual Learning for Extending Pretrained CLIP Models’ Knowledge", Proceedings of the 6th ACM International Conference on Multimedia in Asia, pp.1, 2024.
9.
Yanfei Qin, Renxin Chu, Baolin Liu, "Advancing Incremental Few-Shot Video Action Recognition with Cluster Compression and Generative Separation", International Journal of Pattern Recognition and Artificial Intelligence, 2024.
10.
Runhang Chen, Xiao-Yuan Jing, Fei Wu, Haowen Chen, "Sharpness-aware gradient guidance for few-shot class-incremental learning", Knowledge-Based Systems, pp.112030, 2024.
11.
Clifford Choe Wei Chang, Tan Jian Ding, Chloe Choe Wei Ee, Wang Han, Johnny Koh Siaw Paw, Iftekhar Salam, Mohammad Arif Sobhan Bhuiyan, Goh Sim Kuan, "Nature-Inspired Heuristic Frameworks Trends in Solving Multi-objective Engineering Optimization Problems", Archives of Computational Methods in Engineering, 2024.
12.
Shengjin Ma, Wang Yuan, Yiting Wang, Xin Tan, Zhizhong Zhang, Lizhuang Ma, "Self-supervised Contrastive Feature Refinement for Few-Shot Class-Incremental Learning", Computer-Aided Design and Computer Graphics, vol.14250, pp.281, 2024.
13.
Xuan Wang, Zhong Ji, Yanwei Pang, Yunlong Yu, , 2024.
14.
Magdiel Jimenez-Guarneros, Roberto Alejo-Eleuterio, "A Class-Incremental Learning Method Based on Preserving the Learned Feature Space for EEG-Based Emotion Recognition", Mathematics, vol.10, no.4, pp.598, 2022.
15.
Can Peng, Kun Zhao, Tianren Wang, Meng Li, Brian C. Lovell, "Few-Shot Class-Incremental Learning from an Open-Set Perspective", Computer Vision ? ECCV 2022, vol.13685, pp.382, 2022.

Contact IEEE to Subscribe

References

References is not available for this document.