融合自注意力和卷积的图像检索技术  

Image Retrieval Technology Combining Self-attention and Convolution

作　　者：曾凡锋[1] 王祺 ZENG Fan-feng;WANG Qi(North China University of Technology,Beijing 100144,China;School of Information Science and Technology,North China University of Technology,Beijing 100144,China)

机构地区：[1]北方工业大学,北京100144 [2]北方工业大学信息学院,北京100144

出　　处：《计算机技术与发展》2023年第7期34-40,共7页Computer Technology and Development

基　　金：北京市教育员会科学研究计划项目资助(110052971921/021)。

摘　　要：针对细粒度图像类别之间差异较小的问题,需要对不同区域进行特征提取,自注意力模型能够有效地获取全局特征,卷积神经网络有利于得到图像的局部细节特征。为了实现高效的图像特征提取,提出一种融合自注意力和卷积的图像检索方法。自注意力和卷积是特征提取的两种强有力的方法,将两者进行有效融合,以提取更鲁棒的特征。该方法先通过卷积层提取图像局部特征,然后再输入到自注意力模型捕获全局信息,生成质量更高的图像特征用于图像检索。为了使自注意力模型与卷积能够有效融合,对自注意力模型进行了改进,更好地将局部特征与全局表示进行融合,实现改善图像检索效果的目的。在CUB-200-2011及CARS196图像检索数据集上的实验结果表明,所提方法可以有效地提高检索精度。In view of the small difference between fine-grained image categories,feature extraction in different regions is needed.The self-attention model is effective in obtaining global features.Convolutional neural networks are beneficial in obtaining local detailed features of images.In order to achieve efficient image feature extraction,an efficient image retrieval method that combines self-attention and convolution is proposed.Self-attention and convolution are two powerful methods for feature extraction,and the two are effectively fused to extract efficient and robust features.The local features of the image are extracted through the convolutional layer,and then the global information is captured by inputting into the self-attention model to generate the image features with higher quality for image retrieval.In order to integrate the self-attention model and convolution effectively,the self-attention model is improved to integrate the local features with the global representation better,so as to improve the image retrieval effect.Experiments on the CUB-200-2011 and CARS196 image retrieval datasets show that the proposed method can effectively improve the retrieval accuracy.

关 键 词：图像检索 自注意力 卷积神经网络 特征提取 深度学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]