Image Home
Image People
Image Publication
Image Applications
Image Data & Code
Image Library
Image Seminar
Image Link
Image Album

Search LAMDA


Description: This package provides an implementation of the UM2L algorithm proposed in 1. UM2L is a unified distance multi-metric learning approach. We implement 3 types of similarity, namely the ADS, OVS, RGS in the package. More details can be found in our paper 1.

Reference: [1]Han-Jia Ye, De-Chuan Zhan, Xue-Min Si, Yuan Jiang and Zhi-Hua Zhou. What Makes Objects Similar: A Unified Multi-Metric Learning Approach. In: Advances in Neural Information Processing Systems 29 (NIPS'16), Barcelona, Spain, 2016.

ATTN: This package is free for academic usage. You can run it at your own risk. For other purposes, please contact Prof. Zhi-Hua Zhou (

Requirement: This package is developed with MATLAB, and C MEX-file is used to implement certain key step. We provide Windows 64-bit mex-file (with .maxw64 extension), so the code should be run on Windows (64-bit). If you want to run it on other platforms, please compile the C codes using MEX with MATLAB.

ATTN2: This package was developed by Mr. Han-Jia Ye ( The readme file and demo roughly explains how to use the codes. For any problem concerning the codes, please feel free to contact Mr. Ye.

Download: code (170KB)
  Name Size

(for FireFox 3+ and IE 7+)
Contact LAMDA: (email) (tel) +86-025-89681608 © LAMDA, 2016