SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking
This work addresses a specific bottleneck in visual object tracking for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of accuracy misalignment between classification and regression in siamese network-based visual object tracking by proposing SiamRCR, which introduces reciprocal links and a localization branch, achieving state-of-the-art results on multiple benchmarks and running at 65 FPS.
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.