Class-Balanced Siamese Neural Networks

Abstract : 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.
Liste complète des métadonnées
Contributeur : Grégoire Lefebvre <>
Soumis le : vendredi 1 septembre 2017 - 16:24:40
Dernière modification le : mardi 16 janvier 2018 - 16:33:10


  • HAL Id : hal-01580527, version 1



Samuel Berlemont, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia. Class-Balanced Siamese Neural Networks. Neurocomputing, Elsevier, 2017. 〈hal-01580527〉



Consultations de la notice