Unsupervised Image Matching and Object Discovery as Optimization

Huy V. Vo
INRIA, Valeo.ai, ENS
Francis Bach
Minsu Cho
Kai Han
University of Oxford
Yann LeCun
Patrick PĂ©rez
Jean Ponce


Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important field of research. In computer vision, unsupervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object categories among images in a collection, following the work of Cho et al. 2015. We show that the original approach can be reformulated and solved as a proper optimization problem. Experiments on several benchmarks establish the merit of our approach. .


  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 = {Proceedings of the IEEE/CVF Conference in Computer Vision and Pattern Recognition ({CVPR})},
  year      = {2019}


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.