Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking

TL;DR

This paper introduces a change detection-based method for dynamic template selection in adaptive Siamese trackers, improving their robustness and accuracy by preventing template corruption during online learning.

Contribution

It proposes a novel change detection mechanism and entropy-based sample selection strategy for online adaptation in Siamese tracking, enhancing performance and preventing template corruption.

Findings

Improved tracking accuracy on multiple datasets.

Enhanced robustness against target appearance changes.

Effective online adaptation with reduced template corruption.

Abstract

Deep Siamese trackers have recently gained much attention in recent years since they can track visual objects at high speeds. Additionally, adaptive tracking methods, where target samples collected by the tracker are employed for online learning, have achieved state-of-the-art accuracy. However, single object tracking (SOT) remains a challenging task in real-world application due to changes and deformations in a target object's appearance. Learning on all the collected samples may lead to catastrophic forgetting, and thereby corrupt the tracking model. In this paper, SOT is formulated as an online incremental learning problem. A new method is proposed for dynamic sample selection and memory replay, preventing template corruption. In particular, we propose a change detection mechanism to detect gradual changes in object appearance and select the corresponding samples for online adaption. In addition, an entropy-based sample selection strategy is introduced to maintain a diversified auxiliary buffer for memory replay. Our proposed method can be integrated into any object tracking algorithm that leverages online learning for model adaptation. Extensive experiments conducted on the OTB-100, LaSOT, UAV123, and TrackingNet datasets highlight the cost-effectiveness of our method, along with the contribution of its key components. Results indicate that integrating our proposed method into state-of-art adaptive Siamese trackers can increase the potential benefits of a template update strategy, and significantly improve performance.