Adaptive Siamese Tracking with a Compact Latent Network
Xingping Dong, Jianbing Shen, Fatih Porikli, Jiebo Luo, and Ling Shao

TL;DR
This paper introduces an adaptive Siamese tracking method using a compact latent network that leverages decisive initial frame samples for quick scene adaptation, improving accuracy and speed across multiple trackers.
Contribution
It proposes a novel compact latent network and training strategy that enhances Siamese trackers' adaptability and discrimination with minimal computational overhead.
Findings
Achieves superior accuracy on six datasets
Maintains high running speed during tracking
Effectively adapts to scene variations
Abstract
In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training. Since the samples in the initial (first) frame contain rich sequence-specific information, we can regard them as the decisive samples to represent the whole sequence. To quickly adapt the base model to new scenes, a compact latent network is presented via fully using these decisive samples. Specifically, we present a statistics-based compact latent feature for fast adjustment by efficiently extracting the sequence-specific information. Furthermore, a new diverse sample mining strategy is designed…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsBalanced Selection
