SIFT Meets CNN: A Decade Survey Of Instance Retrieval

Abstract

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 fe

Stats

• citations578
• S2 citations—
• github stars0
• HF likes0
• heat score20.72
• arxiv keyzheng2016sift

Related papers

• A Decade Survey Of Content Based Image Retrieval Using Deep Learning (2020)18.33
• Deep Learning For Instance Retrieval: A Survey (2021)16.05
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• Content-based Image Retrieval Based On Late Fusion Of Binary And Local Descriptors (2017)4.52
• A Comparison Of CNN And Classic Features For Image Retrieval (2019)7.50
• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47