{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sift-meets-cnn-a-decade-survey-of-instance","title":"SIFT Meets CNN: A Decade Survey of Instance Retrieval","arxiv_id":"1608.01807","date":"2016-08-05","proceeding":null,"authors":["Liang Zheng","Yi Yang","Qi Tian"],"abstract":"In the early days, content-based image retrieval (CBIR) was studied with\nglobal features. Since 2003, image retrieval based on local descriptors (de\nfacto SIFT) has been extensively studied for over a decade due to the advantage\nof SIFT in dealing with image transformations. Recently, image representations\nbased on the convolutional neural network (CNN) have attracted increasing\ninterest in the community and demonstrated impressive performance. Given this\ntime of rapid evolution, this article provides a comprehensive survey of\ninstance retrieval over the last decade. Two broad categories, SIFT-based and\nCNN-based methods, are presented. For the former, according to the codebook\nsize, we organize the literature into using large/medium-sized/small codebooks.\nFor the latter, we discuss three lines of methods, i.e., using pre-trained or\nfine-tuned CNN models, and hybrid methods. The first two perform a single-pass\nof an image to the network, while the last category employs a patch-based\nfeature extraction scheme. This survey presents milestones in modern instance\nretrieval, reviews a broad selection of previous works in different categories,\nand provides insights on the connection between SIFT and CNN-based methods.\nAfter analyzing and comparing retrieval performance of different categories on\nseveral datasets, we discuss promising directions towards generic and\nspecialized instance retrieval.","url_abs":"http://arxiv.org/abs/1608.01807v2","url_pdf":"http://arxiv.org/pdf/1608.01807v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sift-meets-cnn-a-decade-survey-of-instance","repo_url":"https://github.com/ChuuyaZZZ/6787-Final-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"content-based-image-retrieval","task_name":"Content-Based Image Retrieval"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1608.01807","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}