On Sensitive Minima in Margin-Based Deep Distance Learning

On Sensitive Minima in Margin-Based Deep Distance Learning

This paper investigates sensitive minima in popular deep distance learning techniques such as Siamese and Triplet networks. We demonstrate that standard formulations may find solutions that are sensitive to small changes and thus do not generalize well. To alleviate sensitive minima we propose a new...

Full description

Bibliographic Details
Main Authors: Reza Serajeh, Seyran Khademi, Amir Mousavinia, Jan C. Van Gemert
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Deep metric learning
regularization
generalization
feature point matching
contrastive loss
triplet loss
Online Access:https://ieeexplore.ieee.org/document/9154359/

Internet

https://ieeexplore.ieee.org/document/9154359/

Similar Items