首页> 外文期刊>Journal of visual communication & image representation >Adaptive deep feature aggregation using Fourier transform and low-pass filtering for robust object retrieval
【24h】

Adaptive deep feature aggregation using Fourier transform and low-pass filtering for robust object retrieval

机译:使用傅立叶变换和低通滤波的自适应深度特征聚合,用于鲁棒对象检索

获取原文
获取原文并翻译 | 示例
           

摘要

With the rapid development of deep learning techniques, convolutional neural networks (CNN) have been widely investigated for the feature representations in the image retrieval task. However, the key step in CNN-based retrieval, i.e., feature aggregation has not been solved in a robust and general manner when tackling different kinds of images. In this paper, we present a deep feature aggregation method for image retrieval using the Fourier transform and low-pass filtering, which can adaptively compute the weights for each feature map with discrimination. Specifically, the low-pass filtering can preserve the semantic information in each feature map by transforming images to the frequency domain. In addition, we develop three adaptive methods to further improve the robustness of feature aggregation, i.e., Region of Interests (ROI) selection, spatial weighting and channel weighting. Experimental results demonstrate the superiority of the proposed method in comparison with other state-of-the-art, in achieving robust and accurate object retrieval under five benchmark datasets. (C) 2020 Published by Elsevier Inc.
机译:随着深度学习技术的快速发展,卷积神经网络(CNN)已被广泛研究了图像检索任务中的特征表示。然而,基于CNN的检索,即特征聚合的关键步骤尚未以稳健和一般的方式在解决不同种类的图像时以稳健和一般的方式解决。在本文中,我们介绍了一种使用傅里叶变换和低通滤波的图像检索的深度特征聚合方法,其可以自适应地计算每个特征图的权重。具体地,低通滤波可以通过将图像转换为频域来保护每个特征映射中的语义信息。此外,我们开发了三种自适应方法,以进一步提高特征聚合的鲁棒性,即感兴趣的区域(ROI)选择,空间加权和信道加权。实验结果表明,与其他现有技术相比,该方法的优越性在实现五个基准数据集下实现了强大和准确的对象检索。 (c)2020由elsevier公司发布

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号