Inductive hashing on Manifolds

Inductive Hashing on manifolds (Fumin shen, chunhua shen......)

主要工作：How to learn compact binary embeddings on their intrinsic manifolds.

（Non-parametric manifold learning）

Learning based hashing methods (随着数据的增加，受关注。。。)

Euclidean distance in the original space(Most)  

Manifold learning techniques (better): model the intrinsic structure embedded in the original high dimensional data. 

 (流形：maintain aspects of the structure of the original data)

Hashing methods: encode documents or images as a set of short binary codes.

研究现状：

  Locality sensitive hashing (LSH) : Data-independent hashing methods, and generates hash codes based on random projections.

  对于hashing， 现有的流形学习方法，不能直接应用到大数据上~