GradNet: Gradient-Guided Network for Visual Object Tracking

TL;DR

This paper introduces GradNet, a gradient-guided network that updates templates in siamese-based visual trackers using gradient information, improving adaptability to target variations and clutter.

Contribution

It is the first to exploit gradient information for template updating in siamese trackers, enhancing tracking performance through a novel gradient-guided approach.

Findings

Achieves superior performance on benchmark datasets.

Effectively captures target variations and background clutter.

Outperforms existing state-of-the-art trackers.

Abstract

The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network. However, this manner cannot capture the temporal variations of targets or background clutter. In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations. Our algorithm performs feed-forward and backward operations to exploit the discriminative informaiton in gradients and capture the core attention of the target. To be specific, the algorithm can utilize the information from the gradient to update the template in the current frame. In addition, a template generalization training method is proposed to better use gradient information and avoid overfitting. To our knowledge, this work is the first attempt to exploit the information in the gradient for template update in siamese-based trackers. Extensive experiments on recent benchmarks demonstrate that our method achieves better performance than other state-of-the-art trackers.