计算机应用与软件2025，Vol.42Issue(4)：319-325,334,8.DOI:10.3969/j.issn.1000-386x.2025.04.045
融合知识蒸馏与迁移学习的小样本学习方法
FEW-SHOT LEARNING BASED ON KNOWLEDGE DISTILLATION AND TRANSFER LEARNING
摘要
Abstract
Aiming at overfitting training data in deep model caused by too few samples,we propose a few-shot learning method that combines knowledge distillation and transfer learning.In order to improve the feature expression ability of shallow network for small sample images,we designed a multi-generation distillation network structure.A modified transfer learning structure was given to enhance the generalization ability of the network by adjusting few parameters.Multiple classifiers were combined to fuse the networks obtained through distillation and transfer.The experiments on three few-shot standard datasets show that the proposed model can effectively improve the classification ability of the model and make the few-shot prediction results more accurate.关键词
小样本学习/图像分类/知识蒸馏/迁移学习/集成学习Key words
Few-shot learning/Image classification/Knowledge distillation/Transfer learning/Ensemble learning分类
信息技术与安全科学引用本文复制引用
黄友文,胡燕芳,魏国庆..融合知识蒸馏与迁移学习的小样本学习方法[J].计算机应用与软件,2025,42(4):319-325,334,8.基金项目
江西省教育厅科技项目(GJJ180443). （GJJ180443）
