TY - GEN
T1 - Unsupervised image matching and object discovery as optimization
AU - Vo, Huy V.
AU - Bach, Francis
AU - Cho, Minsu
AU - Han, Kai
AU - Lecun, Yann
AU - Perez, Patrick
AU - Ponce, Jean
N1 - Funding Information:
Acknowledgments. This work was supported in part by the Inria/NYU collaboration agreement, the Louis Vuit-ton/ENS chair on artificial intellgence and the EPSRC Programme Grant Seebibyte EP/M013774/1. We also thank Simon Lacoste-Julien for his valuable comments and suggestions.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Learning with complete or partial supervision is power-ful 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, unsu-pervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object cate-gories among images in a collection, following the work of Cho et al. [12]. 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.
AB - Learning with complete or partial supervision is power-ful 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, unsu-pervised learning comes in various guises. We focus here on the unsupervised discovery and matching of object cate-gories among images in a collection, following the work of Cho et al. [12]. 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.
KW - Optimization Methods
KW - Scene Analysis and Understanding
UR - http://www.scopus.com/inward/record.url?scp=85078752019&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078752019&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00848
DO - 10.1109/CVPR.2019.00848
M3 - Conference contribution
AN - SCOPUS:85078752019
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 8279
EP - 8288
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -