Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion (CROSBI ID 645791)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Markuš, Nenad ; Pandžić, Igor ; Ahlberg, Jörgen
engleski
Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion
Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We describe an end-to-end differentiable architecture that enables the learning of local keypoint descriptors from such weakly-labeled data.
local descriptors, image matching, image retrieval
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
2380-2385.
2016.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the 23rd International Conference on Pattern Recognition (ICPR)
Institute of Electrical and Electronics Engineers (IEEE)
Podaci o skupu
23rd International Conference on Pattern Recognition (ICPR)
predavanje
04.12.2016-08.12.2016
Cancún, Meksiko