Class-Balanced Siamese Neural Networks

This paper focuses on metric learning with Siamese Neural Networks (SNN). Without any prior, SNNs learn to compute a non-linear metric using only similarity and dissimilarity relationships between input data. Our SNN model proposes three contributions: a tuple-based architecture, an objective functi...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2017-08
Main Authors: Berlemont, Samuel, Lefebvre, Grégoire, Duffner, Stefan, Garcia, Christophe
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Science
Computer Vision and Pattern Recognition
Machine Learning
Signal and Image Processing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper focuses on metric learning with Siamese Neural Networks (SNN). Without any prior, SNNs learn to compute a non-linear metric using only similarity and dissimilarity relationships between input data. Our SNN model proposes three contributions: a tuple-based architecture, an objective function with a norm regularisation and a polar sine-based angular reformulation for cosine dissimilarity learning. Applying our SNN model for Human Action Recognition (HAR) gives very competitive results using only one accelerometer or one motion capture point on the Multimodal Human Action Dataset (MHAD). Performances and properties of our proposals in terms of accuracy, convergence and complexity are assessed, with very favourable results. Additional experiments on the ”Challenge for Multimodal Mid-Air Gesture Recognition for Close Human Computer Interaction” Dataset (ChAirGest) confirm the competitive comparison of our proposals with state-of-the-arts models.
ISSN:0925-2312