Zhang, T., Guo, H., Jiao, Q. et al. (2 more authors) (2023) Efficient RGB-T tracking via cross-modality distillation. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Proceedings. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17-24 Jun 2023, Vancouver, BC, Canada. Institute of Electrical and Electronics Engineers (IEEE) , pp. 5404-5413. ISBN 9798350301304
Abstract
Most current RGB-T trackers adopt a two-stream structure to extract unimodal RGB and thermal features and complex fusion strategies to achieve multi-modal feature fusion, which require a huge number of parameters, thus hindering their real-life applications. On the other hand, a compact RGB-T tracker may be computationally efficient but encounter non-negligible performance degradation, due to the weakening of feature representation ability. To remedy this situation, a cross-modality distillation framework is presented to bridge the performance gap between a compact tracker and a powerful tracker. Specifically, a specific-common feature distillation module is proposed to transform the modality-common information as well as the modality-specific information from a deeper two-stream network to a shallower single-stream network. In addition, a multi-path selection distillation module is proposed to instruct a simple fusion module to learn more accurate multi-modal information from a well-designed fusion mechanism by using multiple paths. We validate the effectiveness of our method with extensive experiments on three RGB-T benchmarks, which achieves state-of-the-art performance but consumes much less computational resources.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 The Authors. Except as otherwise noted, this author-accepted version of a paper published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Proceedings is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ |
Keywords: | Video: Low-level analysis; motion and tracking |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 26 Apr 2023 15:48 |
Last Modified: | 15 Sep 2023 15:33 |
Status: | Published |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Refereed: | Yes |
Identification Number: | 10.1109/CVPR52729.2023.00523 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:198539 |
Download
Filename: 4808_efficient_rgb_t_tracking_via_c-Camera-ready PDF.pdf
Licence: CC-BY 4.0