Large-Scale Image Retrieval with Deep Attentive Global Features

Author:

Zhu Yingying1,Wang Yinghao1,Chen Haonan1,Guo Zemian1,Huang Qiang1

Affiliation:

1. College of Computer Science and Software Engineering, Shenzhen University, Nanhai Ave 3688, Shenzhen, Guangdong 518060, P. R. China

Abstract

How to obtain discriminative features has proved to be a core problem for image retrieval. Many recent works use convolutional neural networks to extract features. However, clutter and occlusion will interfere with the distinguishability of features when using convolutional neural network (CNN) for feature extraction. To address this problem, we intend to obtain high-response activations in the feature map based on the attention mechanism. We propose two attention modules, a spatial attention module and a channel attention module. For the spatial attention module, we first capture the global information and model the relation between channels as a region evaluator, which evaluates and assigns new weights to local features. For the channel attention module, we use a vector with trainable parameters to weight the importance of each feature map. The two attention modules are cascaded to adjust the weight distribution for the feature map, which makes the extracted features more discriminative. Furthermore, we present a scale and mask scheme to scale the major components and filter out the meaningless local features. This scheme can reduce the disadvantages of the various scales of the major components in images by applying multiple scale filters, and filter out the redundant features with the MAX-Mask. Exhaustive experiments demonstrate that the two attention modules are complementary to improve performance, and our network with the three modules outperforms the state-of-the-art methods on four well-known image retrieval datasets.

Funder

National Natural Science Foundation of China

Natural Science Foundation of Guangdong Province of China

Science and Technology R&D Funds of Shenzhen

China University Industry-Academia-Research Innovation Funds

Publisher

World Scientific Pub Co Pte Ltd

Subject

Computer Networks and Communications,General Medicine

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A comprehensive guide to content-based image retrieval algorithms with visualsift ensembling;Journal of X-Ray Science and Technology;2024-09-11

2. Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks;International Journal of Neural Systems;2024-08-15

3. Improved YOLOv7 Based Fast Image Retrieval;2024 2nd International Conference on Intelligent Perception and Computer Vision (CIPCV);2024-05-17

4. Image retrieval using compact deep semantic correlation descriptors;Information Processing & Management;2024-05

5. A spatio-temporal fusion deep learning network with application to lightning nowcasting;Integrated Computer-Aided Engineering;2024-04-26

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3