Augmenting Deep Learning Performance in an Evidential Multiple Classifier System

Jennifer Vandoni (1) , S. Le Hégarat-Mascle (2) , Emanuel Aldea (1)

1 SATIE-MOSS - Méthodes et Outils pour les Signaux et Systèmes
2 SATIE - Systèmes et Applications des Technologies de l'Information et de l'Energie

The main objective of this work is to study the applicability of ensemble methods in the context of deep learning with limited amounts of labeled data. We exploit an ensemble of neural networks derived using Monte Carlo dropout, along with an ensemble of SVM classifiers which owes its effectiveness to the hand-crafted features used as inputs and to an active learning procedure. In order to leverage each classifier's respective strengths, we combine them in an evidential framework, which models specifically their imprecision and uncertainty. The application we consider in order to illustrate the interest of our Multiple Classifier System is pedestrian detection in high-density crowds, which is ideally suited for its difficulty, cost of labeling and intrinsic imprecision of annotation data. We show that the fusion resulting from the effective modeling of uncertainty allows for performance improvement, and at the same time, for a deeper interpretation of the result in terms of commitment of the decision.

Mots clés: Belief Function Theory; ensemble classifiers; deep learning; high-density crowds; pedestrian detection

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Jennifer Vandoni, S. Le Hégarat-Mascle, Emanuel Aldea. Augmenting Deep Learning Performance in an Evidential Multiple Classifier System. Sensors, 2019, 19 (21), pp.4664. ⟨10.3390/s19214664⟩. ⟨hal-02338018⟩