Deep Total Variation Support Vector Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Deep Total Variation Support Vector Networks

Hichem Sahbi

Résumé

Support vector machines (SVMs) have been successful in solving many computer vision tasks including image and video category recognition especially for small and mid-scale training problems. The principle of these non-parametric models is to learn hyperplanes that separate data belonging to different classes while maximizing their margins. However, SVMs constrain the learned hyperplanes to lie in the span of support vectors, fixed/taken from training data, and this reduces their representational power and may lead to limited generalization performances. In this paper, we relax this constraint and allow the support vectors to be learned (instead of being fixed/taken from training data) in order to better fit a given classification task. Our approach, referred to as deep total variation support vector machines, is parametric and relies on a novel deep architecture that learns not only the SVM and the kernel parameters but also the support vectors, resulting into highly effective classifiers. We also show (under a particular setting of the activation functions in this deep architecture) that a large class of kernels and their combinations can be learned. Experiments conducted on the challenging task of skeleton-based action recognition show the outperformance of our deep total variation SVMs w.r.t different baselines as well as the related work.
Fichier principal
Vignette du fichier
Sahbi_Deep_Total_Variation_Support_Vector_Networks_ICCVW_2019_paper.pdf (307.28 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03087046 , version 1 (23-12-2020)

Identifiants

Citer

Hichem Sahbi. Deep Total Variation Support Vector Networks. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Oct 2019, Seoul, South Korea. pp.3028-3038, ⟨10.1109/ICCVW.2019.00365⟩. ⟨hal-03087046⟩
40 Consultations
73 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More