Learning Deep Descriptors with Scale-Aware Triplet Networks


Loading...

Date

2018

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

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 applied with success, it is still not well understood what makes a good loss function. In this spirit, this work demonstrates that many commonly used losses suffer from a range of problems. Based on this analysis, we introduce mixed-context losses and scale-aware sampling, two methods that when combined enable networks to learn consistently scaled descriptors for the first time.

Publication status

published

Editor

Book title

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Journal / series

Volume

Pages / Article No.

2762 - 2770

Publisher

IEEE

Event

31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Feature Encoding; Triplet Network

Organisational unit

09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former) check_circle

Notes

Funding

644128 - Collaborative Aerial Robotic Workers (SBFI)

Related publications and datasets