A supervised learning to index model for approximate nearest neighbor image retrieval

作者：

Highlights：

• A supervised learning to index model is proposed to realize AKNN image retrieval.

• An image relabeling algorithm is proposed to reassign new labels to the images.

• A constraint optimization objective function is built to learn the codebook.

摘要

•A supervised learning to index model is proposed to realize AKNN image retrieval.•An image relabeling algorithm is proposed to reassign new labels to the images.•A constraint optimization objective function is built to learn the codebook.

论文关键词：Supervised learning to index,Approximate K-nearest neighbor search,Image relabeling,Codebook learning

论文评审过程：Received 11 March 2019, Revised 30 June 2019, Accepted 15 August 2019, Available online 20 August 2019, Version of Record 21 August 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.08.009