Skip to content
No description, website, or topics provided.
HTML C MATLAB Python Makefile CSS Other
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Unsupervised image matching and object discovery as optimization

Huy V. Vo, Francis Bach, Minsu Cho, Kai Han, Yann LeCun, Patrick Pérez, Jean Ponce - CVPR 2019

Getting started

The code is written and tested with Matlab 2017a. Modifications might be necessary to run it with other versions of Matlab.


git clone
cd UODOptim


You need to download the code for generating region proposals with randomized Prim's algorithm and put it in the UODOptim/ folder

git clone

then run

cd rp; matlab -r "setup"

Running the tests

The main script for testing the code on VOC_6x2 is scripts/run_UOD.m. In a terminal, from the UODOptim folder, run

cd scripts; matlab -r "run_UOD"


  title     = {Unsupervised image matching and object discovery as optimization},
  author    = {Vo, Huy V. and Bach, Francis and Cho, Minsu and Han, Kai and LeCun, Yann and P{\'e}rez, Patrick and Ponce, Jean},
  booktitle = {CVPR},
  year      = {2019}


This project is licensed under the MIT License - see the LICENSE file for details.


The code for Probabilistic Hough Matching (PHM) algorithm is taken from the project page of the paper "Unsupervised Object Discovery and Localization in the Wild".

This work was supported in part by the Inria/NYU collaboration agreement, the Louis Vuitton/ENS chair on artificial intellgence and the EPSRC Programme Grant Seebibyte EP/M013774/1.

You can’t perform that action at this time.