SIFT Meets CNN: A Decade Survey of Instance Retrieval

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…

• NS
  National Science Foundation
• NN
  National Natural Science Foundation of China

  Awards: W911NF-15-1-0290, 61429201
• AR
  Army Research Office

  Awards: 61429201, W911NF-15-1-, W911NF-15-1-0290, W911NF