湖北民族大学学报（自然科学版）2025，Vol.43Issue(2)：231-236,279,7.DOI:10.13501/j.cnki.42-1908/n.2025.06.013
基于两阶段特征空间增强的小样本图像分类模型
A Few-shot Image Classification Model Based on Two-stage Feature Space Enhancement
摘要
Abstract
In few-shot learning tasks,a few-shot image classification model based on two-stage feature enhancement was proposed to address the issue that traditional backbone convolutional networks,due to the loss of feature information caused by the neglect of detailed features in multi-layer convolutions,resulted in low image classification accuracy.Firstly,this model was introduced with a median-enhanced spatial and channel attention block(MESC)in the lower layers of the residual network(ResNet)12.Secondly,this model was introduced with a spatial group-wise enhance(SGE)module in the middle and upper layers of the ResNet12 to improve the ability of semantic feature learning in convolutional neural networks and enable the model to effectively extract key information from feature maps.The model enhanced the feature representation of limited training samples to improve classification performance and enhance the model's robustness to noise.The results showed that,on the California Institute of Technology-University of California at San Diego birds(CUB)-200-2011 dataset,the classification accuracy of this model were respectively improved by about 5.15%and 1.92%compared with the distribution propagation graph network(DPGN)model under the two parameter settings of 5-way 1-shot and 5-way 5-shot.On the tiered ImageNet(tieredImageNet)dataset,the classification accuracy was respectively increased by about 1.04%and 0.55%compared with the DPGN model under these two parameter settings.The performance of the few-shot image classification task was significantly improved by this model.关键词
卷积神经网络/小样本学习/图像分类/特征空间增强/注意力机制/通道注意力/空间组增强Key words
convolutional neural network/few-shot learning/image classification/feature space enhancement/attention mechanism/channel attention/spatial group enhancement分类
信息技术与安全科学引用本文复制引用
黎格献,章晓爽,贺永姣,杜阳,张艳莎,王林..基于两阶段特征空间增强的小样本图像分类模型[J].湖北民族大学学报（自然科学版）,2025,43(2):231-236,279,7.基金项目
贵州省科技计划项目(黔科合基础-ZK[2022]一般195,黔科合平台人才-ZCKJ[2021]007) （黔科合基础-ZK[2022]一般195,黔科合平台人才-ZCKJ[2021]007）
贵州省青年科技人才成长项目(黔教合KY字[2021]104,黔教技[2024]063号) （黔教合KY字[2021]104,黔教技[2024]063号）
贵州省模式识别与智能系统重点实验室开放课题(GZMUKL[2022]KF01,GZMUKL[2022]KF05) （GZMUKL[2022]KF01,GZMUKL[2022]KF05）
贵州民族大学基金科研项目(GZMUZK[2023]YB14). （GZMUZK[2023]YB14）
