Mobile Vision Transformer-based Visual Object Tracking
Goutam Yelluru Gopal (Concordia University),* Maria Amer (Concordia University)
The 34th British Machine Vision Conference
Abstract
The introduction of robust backbones, such as Vision Transformers, has improved the performance of object tracking algorithms in recent years. However, these state-of-the-art trackers are computationally expensive since they have a large number of model parameters and rely on specialized hardware (e.g., GPU) for faster inference. On the other hand, recent lightweight trackers are fast but are less accurate, especially on large-scale datasets. We propose a lightweight, accurate, and fast tracking algorithm using Mobile Vision Transformers (MobileViT) as the backbone for the first time. We also present a novel approach of fusing the template and search region representations in the MobileViT backbone, thereby generating superior feature encoding for target localization. The experimental results show that our MobileViT-based Tracker, MVT, surpasses the performance of recent lightweight trackers on the large-scale datasets GOT10k and TrackingNet, and with a high inference speed. In addition, our method outperforms the popular DiMP-50 tracker despite having 4.7× fewer model parameters and running at 2.8× its speed on a GPU. The tracker code and models are available at https://github.com/goutamyg/MVTVideo
Citation
@inproceedings{Gopal_2023_BMVC,
author = {Goutam Yelluru Gopal and Maria Amer},
title = {Mobile Vision Transformer-based Visual Object Tracking},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0800.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by