[HTML][HTML] A survey on few-shot class-incremental learning

S Tian, L Li, W Li, H Ran, X Ning, P Tiwari - Neural Networks, 2024 - Elsevier
Large deep learning models are impressive, but they struggle when real-time data is not
available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …

Uncertainty-aware distillation for semi-supervised few-shot class-incremental learning

Y Cui, W Deng, H Chen, L Liu - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Given a model well-trained with a large-scale base dataset, few-shot class-incremental
learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples …

Uncertainty-guided semi-supervised few-shot class-incremental learning with knowledge distillation

Y Cui, W Deng, X Xu, Z Liu, Z Liu… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Class-Incremental Learning (CIL) aims at incrementally learning novel classes without
forgetting old ones. This capability becomes more challenging when novel tasks contain one …

Few-shot class incremental learning leveraging self-supervised features

T Ahmad, AR Dhamija, S Cruz… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Few-Shot Class Incremental Learning (FSCIL) is a recently introduced Class
Incremental Learning (CIL) setting that operates under more constrained assumptions: only …

Few-shot learning for structural health diagnosis of civil infrastructure

XU Yang, FAN Yunlei, BAO Yuequan, LI Hui - Advanced Engineering …, 2024 - Elsevier
The successful development of deep learning and computer vision techniques has recently
revolutionized structural health diagnosis (SHD) during life-cycle construction, inspection …

Few-shot class-incremental learning: A survey

J Zhang, L Liu, O Silven, M Pietikäinen… - arXiv preprint arXiv …, 2023 - arxiv.org
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in machine
learning, as it necessitates the continuous learning of new classes from sparse labeled …

Gradient guided multi-scale feature collaboration networks for few-shot class-incremental remote sensing scene classification

W Wang, L Zhang, S Fu, P Ren, G Ren… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
Few-shot class-incremental learning has recently received significant research focus in
remote sensing scene classification (FSCIL-RSSC). The success of FSCIL-RSSC relies on …

Semantic-visual guided transformer for few-shot class-incremental learning

W Qiu, S Fu, J Zhang, C Lei… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in
various areas. Existing FSCIL methods highly depend on the robustness of the feature …

Variable few shot class incremental and open world learning

T Ahmad, AR Dhamija, M Jafarzadeh… - Proceedings of the …, 2022 - openaccess.thecvf.com
Prior work on few-shot class incremental learning has operated with an unnatural
assumption: the number of ways and number of shots are assumed to be known and fixed …

Rethinking Few-shot Class-incremental Learning: Learning from Yourself

YM Tang, YX Peng, J Meng, WS Zheng - European Conference on …, 2025 - Springer
Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited
samples in a few-shot fashion. Inherited from the classical class-incremental learning …