基于小样本学习融合随机深度和多尺度卷积的SDM-RNET网络
SDM-RNET Network Based on Small-sample Learning Fusing Stochastic Depth and Multi-scale Convolution
刘馨瑶 1梁军 1余嘉琳1
作者信息
- 1. 华南师范大学软件学院,佛山 528225
- 折叠
摘要
针对神经网络难以利用少量标注数据获取足够的信息来正确分类图像的问题,提出了一种融合随机深度网络和多尺度卷积的关系网络——SDM-RNET.首先在模型嵌入模块引入随机深度网络用于加深模型深度,然后在特征提取阶段采用多尺度深度可分离卷积替代普通卷积进行特征融合,经过骨干网络后再采用深浅层特征融合获取更丰富的图像特征,最终学习预测出图像的类别.在mini-ImageNet、RP2K、Omniglot这 3 个数据集上对比该方法与其他小样本图像分类方法,结果表明在5-way 1-shot和5-way 5-shot分类任务上该方法准确率最高.
Abstract
To solve the problem that it is difficult for neural networks to obtain enough information to correctly classify images by using a small amount of labeled data,this study proposes a new relational network,SDM-RNET,which combines random deep network and multi-scale convolution.First,a stochastic deep network is introduced into the model embedding module to deepen the model depth.Then,in the feature extraction stage,multi-scale depth-separable convolution is adopted to replace ordinary convolution for feature fusion.After the backbone network,deep and shallow layer feature fusion is applied to obtain richer image features and finally learn to predict the categories of images.Compared with other small sample image classification methods on mini-ImageNet,RP2K,and Omniglot datasets,the results show that the proposed method has the highest accuracy on 5-way 1-shot and 5-way 5-shot classification tasks.
关键词
深度学习/小样本学习/图像分类Key words
deep learning(DL)/small-sample learning/image classification引用本文复制引用
基金项目
广东省基础与应用基础研究基金(2022A1515140110)
广东省基础与应用基础研究基金(2020B1515120089)
广东省基础与应用基础研究基金(2021A1515110673)
佛山市高等教育高层次人才项目()
出版年
2024
NETL
NSTL
万方数据