Recently, most siamese network based trackers locate targets via object classification and bounding-box regression. Generally, they select the bounding-box with maximum classification confidence as the final prediction. This strategy may miss the right result due to the accuracy misalignment between classification and regression. In this paper, we propose a novel siamese tracking algorithm called SiamRCR, addressing this problem with a simple, light and effective solution. It builds reciprocal links between classification and regression branches, which can dynamically re-weight their losses for each positive sample. In addition, we add a localization branch to predict the localization accuracy, so that it can work as the replacement of the regression assistance link during inference. This branch makes the training and inference more consistent. Extensive experimental results demonstrate the effectiveness of SiamRCR and its superiority over the state-of-the-art competitors on GOT-10k, LaSOT, TrackingNet, OTB-2015, VOT-2018 and VOT-2019. Moreover, our SiamRCR runs at 65 FPS, far above the real-time requirement.
@article{arxiv.2105.11237,
title = {SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking},
author = {Jinlong Peng and Zhengkai Jiang and Yueyang Gu and Yang Wu and Yabiao Wang and Ying Tai and Chengjie Wang and Weiyao Lin},
journal= {arXiv preprint arXiv:2105.11237},
year = {2021}
}
Comments
The 30th International Joint Conference on Artificial Intelligence (IJCAI 2021)