Improving Car Model Classification through Vehicle Keypoint Localization
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.
Citation:Simoni, Alessandro; D'Eusanio, Andrea; Pini, Stefano; Borghi, Guido; Vezzani, Roberto "Improving Car Model Classification through Vehicle Keypoint Localization" Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021), vol. 5, Online, pp. 354 -361 , 8-10 February 2021, 2021 DOI: 10.5220/0010207803540361
- Author version:
- DOI: 10.5220/0010207803540361