SIFT Meets CNN: A Decade Survey of Instance Retrieval
SIFT Meets CNN: A Decade Survey of Instance Retrieval
复制标题
DOI：
10.1109/tpami.2017.2709749
复制
发表时间：
2018-05-01
影响因子：
23.6
通讯作者：
Tian, Qi
中科院分区：
文献类型：
--
作者：
Zheng, Liang;Yang, Yi;Tian, Qi
早期，基于内容的图像检索（CBIR）研究的是全局特征。自2003年以来，由于SIFT在处理图像变换方面的优势，基于局部描述符的图像检索（事实上的SIFT）得到了十多年的广泛研究。最近，基于卷积神经网络（CNN）的图像表示引起了越来越多的关注，并展示了令人印象深刻的性能。考虑到这个快速发展的时代，本文提供了过去十年中实例检索的全面调查。提出了基于sift和基于cnn的两大类方法。对于前者，我们根据码本的大小，将文献组织成使用大/中/小码本。对于后者，我们讨论了三种方法，即使用预训练或微调的CNN模型和混合方法。前两种方法将图像单次传递到网络，而最后一类方法采用基于补丁的特征提取方案。本调查提出了现代实例检索的里程碑，回顾了不同类别的广泛选择的先前工作，并提供了关于SIFT和基于cnn的方法之间联系的见解。在分析和比较了不同类别在多个数据集上的检索性能后，讨论了通用实例检索和专用实例检索的发展方向。
In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.