Clustering-based k-nearest neighbor classification for large-scale data with neural codes representation

作者：

Highlights：

• A new scheme to conduct cluster-based kNN search is proposed.

• It includes the use of Deep Neural Networks for feature extraction.

• Comprehensive experimentation and analysis is presented.

• We demonstrate that the strategy is able to achieve better classification rates.

摘要

•A new scheme to conduct cluster-based kNN search is proposed.•It includes the use of Deep Neural Networks for feature extraction.•Comprehensive experimentation and analysis is presented.•We demonstrate that the strategy is able to achieve better classification rates.

论文关键词：Efficient kNN classification,Clustering,Deep neural networks

论文评审过程：Received 3 March 2017, Revised 22 August 2017, Accepted 24 September 2017, Available online 28 September 2017, Version of Record 10 October 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.038