Fine-grained vehicle classificationusing deep residual networks with multiscale attention windows

Fine-grained vehicle classification is a challenging task due to the subtle differences between vehicle classes. Several successful approaches to fine-grained image classification rely on part-based models, where the image is classified according to discriminative object parts. Such approaches requi...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP) pp. 1 - 6
Main Authors Ghassemi, Sina, Fiandrotti, Attilio, Magli, Enrico, Francini, Gianluca
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2017
Subjects
attention windows
Computer architecture
Feature extraction
fine-grained
Image classification
residual networks
Training
transform networks
Transforms
vehicle classification
Online AccessGet full text

Cover

More Information
Summary:Fine-grained vehicle classification is a challenging task due to the subtle differences between vehicle classes. Several successful approaches to fine-grained image classification rely on part-based models, where the image is classified according to discriminative object parts. Such approaches require however that parts in the training images be manually annotated, a labor-intensive process. We propose a convolutional architecture realizing a transform network capable of discovering the most discriminative parts of a vehicle at multiple scales. We experimentally show that our architecture outperforms a baseline reference if trained on class labels only, and performs closely to a reference based on a part-model if trained on loose vehicle localization bounding boxes.
ISSN:2473-3628
DOI:10.1109/MMSP.2017.8122262