Deep Learning For Instance Retrieval: A Survey

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

Stats

• citations137
• S2 citations—
• github stars0
• HF likes0
• heat score16.05
• arxiv keychen2021deep

Related papers

• A Decade Survey Of Content Based Image Retrieval Using Deep Learning (2020)18.33
• End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66
• Content-based Image Retrieval And The Semantic Gap In The Deep Learning Era (2020)7.50
• SIFT Meets CNN: A Decade Survey Of Instance Retrieval (2016)20.72
• CBIR Using Features Derived By Deep Learning (2020)12.02
• Deep Learning For Image Search And Retrieval In Large Remote Sensing Archives (2020)10.74
• Medical Image Retrieval Using Deep Convolutional Neural Network (2017)19.35
• Recent Advance In Content-based Image Retrieval: A Literature Survey (2017)0.00