Naslov
Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion

Autori
Markuš, Nenad ; Pandžić, Igor ; Ahlberg, Jörgen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 23rd International Conference on Pattern Recognition (ICPR) / - : Institute of Electrical and Electronics Engineers (IEEE), 2016, 2380-2385

Skup
23rd International Conference on Pattern Recognition (ICPR)

Mjesto i datum
Cancún, Meksiko, 04.12.2016. - 08.12.2016

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
local descriptors, image matching, image retrieval

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA