Learning Deep Descriptors With Scale-Aware Triplet Networks

Michel Keller
Michel Keller
Patrik Schmuck
Patrik Schmuck

CVPR, pp. 2762-2770, 2018.

Cited by: 21|Bibtex|Views41
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

Research on learning suitable feature descriptors for Computer Vision has recently shifted to deep learning where the biggest challenge lies with the formulation of appropriate loss functions, especially since the descriptors to be learned are not known at training time. While approaches such as Siamese and triplet losses have been applie...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments