A

Deep Learning for Instance Retrieval: A Survey

arXiv (Cornell University)

Abstract

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, particularly that of searching databases for similar content-Content Based Image Retrieval (CBIR)-a long-established research area in which improved efficiency and accuracy are needed for real-time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of instance search. In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep network architecture types, deep features, feature embedding and aggregation methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, whereby we identify milestone work, reveal connections among various methods and present the commonly used benchmarks, evaluation results, common challenges, and propose promising future directions.

Authors 7

  1. Hunan Research Academy of Environmental Sciences

    Affiliation as printed

    is with Academy of Advanced Technology Research of Hunan , Changsha , China

  2. Dalian University of Technology

    Affiliation as printed

    is with DUTRU International School of Information Science and Engineering , Dalian University of Technology , China

  3. Hunan Research Academy of Environmental Sciences

    Affiliation as printed

    is with Academy of Advanced Technology Research of Hunan , Changsha

  4. Leiden University

    Affiliation as printed

    Leiden Institute of Advanced Computer Science , Leiden University , the Netherlands

  5. Dalian University of Technology

    Affiliation as printed

    is with DUTRU International School of Information Science and Engineering , Dalian University of Technology , China

  6. Leiden University

    Affiliation as printed

    Leiden Institute of Advanced Computer Science , Leiden University , the Netherlands

Cited by 5 stored of 5

5 results

No patents citing this paper on Lens.org (checked 2026-10-11).

References 0