Unsupervised Image Matching and Object Discovery as Optimization

Autor:	Vo, Huy V., Bach, Francis, Cho, Minsu, Han, Kai, LeCun, Yann, Perez, Patrick, Ponce, Jean
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to CVPR 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1904.03148 Zobrazit plný text záznamu View this record from Arxiv