Improving Car Model Classification through Vehicle Keypoint Localization

Alessandro Simoni, Andrea D’Eusanio, Stefano Pini, Guido Borghi, Roberto Vezzani, Roberto Vezzani

Abstract

In this paper, we present a novel multi-task framework which aims to improve the performance of car model classification leveraging visual features and pose information extracted from single RGB images. In particular, we merge the visual features obtained through an image classification network and the features computed by a model able to predict the pose in terms of 2D car keypoints. We show how this approach considerably improves the performance on the model classification task testing our framework on a subset of the Pascal3D+ dataset containing the car classes. Finally, we conduct an ablation study to demonstrate the performance improvement obtained with respect to a single visual classifier network.

Download


Paper Citation


in Harvard Style

Simoni A., D’Eusanio A., Pini S., Borghi G. and Vezzani R. (2021). Improving Car Model Classification through Vehicle Keypoint Localization.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 354-361. DOI: 10.5220/0010207803540361


in Bibtex Style

@conference{visapp21,
author={Alessandro Simoni and Andrea D’Eusanio and Stefano Pini and Guido Borghi and Roberto Vezzani},
title={Improving Car Model Classification through Vehicle Keypoint Localization},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={354-361},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010207803540361},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Improving Car Model Classification through Vehicle Keypoint Localization
SN - 978-989-758-488-6
AU - Simoni A.
AU - D’Eusanio A.
AU - Pini S.
AU - Borghi G.
AU - Vezzani R.
PY - 2021
SP - 354
EP - 361
DO - 10.5220/0010207803540361