Robust discrete code modeling for supervised hashing

作者：

Highlights：

• We propose a novel supervised hashing scheme to generate high-quality hash codes and hash functions for facilitating large-scale multimedia applications.

• We devise an effective binary code modeling approach based on l2,p-norm, which can adaptively induce sample-wise sparsity, to perform automatic code selection as well as noisy samples identification.

• We preserve the discrete constraint in the proposed model to directly produce discrete codes with minimal quantization error. An efficient algorithm is designed to solve the discrete optimization problem, where a weighted discrete cyclic coordinate decent (WDCC) algorithm is proposed to derive robust binary codes.

• Extensive experiments conducted on various real-world datasets demonstrate the promising results of the RDCM approach in retrieval and classification tasks.

摘要

•We propose a novel supervised hashing scheme to generate high-quality hash codes and hash functions for facilitating large-scale multimedia applications.•We devise an effective binary code modeling approach based on l2,p-norm, which can adaptively induce sample-wise sparsity, to perform automatic code selection as well as noisy samples identification.•We preserve the discrete constraint in the proposed model to directly produce discrete codes with minimal quantization error. An efficient algorithm is designed to solve the discrete optimization problem, where a weighted discrete cyclic coordinate decent (WDCC) algorithm is proposed to derive robust binary codes.•Extensive experiments conducted on various real-world datasets demonstrate the promising results of the RDCM approach in retrieval and classification tasks.

论文关键词：Supervised hashing,Robust modeling,Discrete optimization.

论文评审过程：Received 31 August 2016, Revised 13 February 2017, Accepted 27 February 2017, Available online 2 March 2017, Version of Record 21 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.02.034