计算机与现代化Issue(9)：27-34,42,9.DOI:10.3969/j.issn.1006-2475.2025.09.004
基于自蒸馏和自注意力增强的低数据细粒度图像分类
Low-data Fine-grained Image Classification Based on Self-distillation and Self-attention Enhancement
摘要
Abstract
Training a fine-grained image classification(FGIC)model with limited data is a great challenge,where subtle differ-ences between categories may not be easily discernible.A common strategy is to utilize pre-trained network models to generate ef-fective feature representations.However,when fine-tuning the pre-trained model using limited fine-grained data,the model of-ten tends to extract less relevant features,which triggers the overfitting problem.To address the above issues,this paper designs an new FGIC method named SDA-Net under low-data conditions,which optimizes the feature learning process by fusing the spa-tial self-attention mechanism and the self-distillation technique,which can effectively mitigate the overfitting problem caused by data scarcity and improve the performance of deep neural networks in low-data environments.Specifically,SDA-Net improves the intra-class representation by introducing spatial self-attention to encode contextual information into local features.Mean-while,a distillation branch is introduced and the distillation loss is used in the augmented input samples,which realizes the deep enhancement and transfer of knowledge within the network.A comprehensive evaluation on three fine-grained benchmark data shows that SDA-Net exhibits significant performance gains compared to both traditional fine-tuning methods and the current SOTA low-data FGIC strategy.In 3 scenarios with 10%low-data volume,relative accuracies are improved by 30%,47%,and 29%,respectively,compared to standard ResNet-50,and by 15%,28%,and 17%,respectively,compared to SOTA.关键词
深度学习/细粒度图像分类/低数据学习/自蒸馏/自注意力/数据增广Key words
deep learning/fine-grained image classification/low-data learning/self-distillation/self-attention/data augmen-tation分类
信息技术与安全科学引用本文复制引用
张婧颖,耿琳,刘宁钟..基于自蒸馏和自注意力增强的低数据细粒度图像分类[J].计算机与现代化,2025,(9):27-34,42,9.基金项目
江苏省前沿引领技术基础研究重大项目(BK20222012) （BK20222012）
