Semi-supervised manifold-embedded hashing with joint feature representation and classifier learning

作者：

Highlights：

• We propose a semi-supervised hashing method which uses very limited labeled data.

• We integrate manifold embedding, feature representation and classifier learning into a joint optimization framework.

• We adopt the l2,1-norm in our formulation to obtain a robust model.

• We develop a two-stage hashing strategy to address the optimization problem.

摘要

•We propose a semi-supervised hashing method which uses very limited labeled data.•We integrate manifold embedding, feature representation and classifier learning into a joint optimization framework.•We adopt the l2,1-norm in our formulation to obtain a robust model.•We develop a two-stage hashing strategy to address the optimization problem.

论文关键词：Hashing,Manifold embedding,Locality sensitive hashing (LSH),Nearest neighbor search,Image retrieval

论文评审过程：Received 23 June 2016, Revised 25 December 2016, Accepted 1 March 2017, Available online 4 March 2017, Version of Record 15 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.004