Share Email Print
cover

Proceedings Paper

A systematic evaluation of recent deep learning architectures for fine-grained vehicle classification
Author(s): Krassimir Valev; Arne Schumann; Lars Sommer; Jurgen Beyerer
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Fine-grained vehicle classification is the task of classifying make, model, and year of a vehicle. This is a very challenging task, because vehicles of different types but similar color and viewpoint can often look much more similar than vehicles of same type but differing color and viewpoint. Vehicle make, model, and year in combination with vehicle color - are of importance in several applications such as vehicle search, re-identification, tracking, and traffic analysis. In this work we investigate the suitability of several recent landmark convolutional neural network (CNN) architectures, which have shown top results on large scale image classification tasks, for the task of fine-grained classification of vehicles. We compare the performance of the networks VGG16, several ResNets, Inception architectures, the recent DenseNets, and MobileNet. For classification we use the Stanford Cars-196 dataset which features 196 different types of vehicles. We investigate several aspects of CNN training, such as data augmentation and training from scratch vs. fine-tuning. Importantly, we introduce no aspects in the architectures or training process which are specific to vehicle classification. Our final model achieves a state-of-the-art classification accuracy of 94.6% outperforming all related works, even approaches which are specifically tailored for the task, e.g. by including vehicle part detections.

Paper Details

Date Published: 27 April 2018
PDF: 11 pages
Proc. SPIE 10649, Pattern Recognition and Tracking XXIX, 1064902 (27 April 2018); doi: 10.1117/12.2305062
Show Author Affiliations
Krassimir Valev, Karlsruher Institut für Technologie (Germany)
BMW Car IT GmbH (Germany)
Arne Schumann, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Lars Sommer, Karlsruher Institut für Technologie (Germany)
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Jurgen Beyerer, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Karlsruher Institut für Technologie (Germany)


Published in SPIE Proceedings Vol. 10649:
Pattern Recognition and Tracking XXIX
Mohammad S. Alam, Editor(s)

© SPIE. Terms of Use
Back to Top