DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

TL;DR

DomainSiam introduces a domain-aware Siamese network that leverages semantic and objectness information with a novel ridge regression approach, significantly improving visual object tracking performance across multiple benchmarks.

Contribution

It proposes a fully utilizing semantic/objectness-aware Siamese tracker with a differentiable weighted-dynamic loss, enhancing generalization and efficiency.

Findings

Achieves state-of-the-art results on five benchmarks.

Runs at 53 FPS, demonstrating real-time capability.

Improves feature learning and domain generalization.

Abstract

Visual object tracking is a fundamental task in the field of computer vision. Recently, Siamese trackers have achieved state-of-the-art performance on recent benchmarks. However, Siamese trackers do not fully utilize semantic and objectness information from pre-trained networks that have been trained on the image classification task. Furthermore, the pre-trained Siamese architecture is sparsely activated by the category label which leads to unnecessary calculations and overfitting. In this paper, we propose to learn a Domain-Aware, that is fully utilizing semantic and objectness information while producing a class-agnostic using a ridge regression network. Moreover, to reduce the sparsity problem, we solve the ridge regression problem with a differentiable weighted-dynamic loss function. Our tracker, dubbed DomainSiam, improves the feature learning in the training phase and generalization capability to other domains. Extensive experiments are performed on five tracking benchmarks including OTB2013 and OTB2015 for a validation set; as well as the VOT2017, VOT2018, LaSOT, TrackingNet, and GOT10k for a testing set. DomainSiam achieves state-of-the-art performance on these benchmarks while running at 53 FPS.