Additive deep feature optimization for semantic image retrieval

作者：

Highlights：

• An improved deep learning model for image retrieval.

• Semantic gap reduction between low and high level features.

• Sparse feature vector for semantic image retrieval.

• Deep feature aggregation.

• Benchmark for future studies.

摘要

•An improved deep learning model for image retrieval.•Semantic gap reduction between low and high level features.•Sparse feature vector for semantic image retrieval.•Deep feature aggregation.•Benchmark for future studies.

论文关键词：Image retrieval,Image search,Deep learning,Convolutional neural networks,MaxNet

论文评审过程：Received 25 June 2020, Revised 4 December 2020, Accepted 24 December 2020, Available online 1 January 2021, Version of Record 12 January 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114545