智能科学与技术学报2026，Vol.8Issue(1)：72-82,11.DOI:10.11959/j.issn.2096-6652.202606
小样本细粒度图像分类的Mamba-小波多尺度建模方法
Mamba-wavelet-based multi-scale modeling method for few-shot fine-grained image classification
摘要
Abstract
Fine-grained few-shot image classification aims to recognize subtle inter-class differences under limited anno-tated samples and has been widely applied in intelligent recognition,ecological monitoring,and autonomous driving.However,existing convolutional architectures are constrained by fixed receptive fields and local modeling schemes,re-sulting in insufficient characterization of multi-scale feature relationships.Although attention-based or frequency-domain methods have improved the discriminability of fine-grained features,limitations still exist in modeling cross-scale depen-dencies and feature fusion.To address these issues,a Mamba-wavelet-based multi-scale modeling method for few-shot fine-grained image classification was proposed.Specifically,a multi-scale feature relation network(MSFRNet)based on Mamba state space modeling was constructed.The proposed network consisted of two core modules,namely a wavelet-guided dynamic Mamba multi-scale feature extraction(WDMFE)module and a cross-scale attention fusion(CAF)mod-ule.In the WDMFE module,a wavelet-guided dynamic adaptive Mamba structure was introduced to enhance frequency perception and contextual modeling across different scales.In the CAF module,multi-scale features were integrated through channel and spatial attention mechanisms to achieve cross-scale feature complementation.Experimental results on benchmark datasets,including CUB-200-2011,Stanford Dogs,and Stanford Cars,demonstrated that higher classifica-tion accuracy was achieved and stable performance improvements were obtained.It is concluded that the proposed net-work effectively enhances fine-grained feature representation and cross-task generalization ability,and provides a scalable framework for multi-scale modeling in few-shot fine-grained classification.关键词
小样本细粒度图像分类/Mamba状态空间模型/多尺度特征建模/小波引导特征提取/注意力机制/特征融合Key words
fine-grained few-shot classification/Mamba state space model/multi-scale feature modeling/wavelet-guided feature extraction/attention mechanism/feature fusion分类
信息技术与安全科学引用本文复制引用
仝傲,任劼,孟宗阳,鲁磊..小样本细粒度图像分类的Mamba-小波多尺度建模方法[J].智能科学与技术学报,2026,8(1):72-82,11.基金项目
陕西省自然科学基础研究计划(No.2025JC-YBMS-765) （No.2025JC-YBMS-765）
陕西省教育厅重点项目(No.23JY029)The Shaanxi Province Basic Research Program in Natural Sciences(No.2025JC-YBMS-765),The Key Project of Shaanxi Provincial Department of Education(No.23JY029) （No.23JY029）
