Updatable Siamese Tracker with Two-stage One-shot Learning

by   Xinglong Sun, et al.

Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency. However, they often fail to track an object in complex scenes due to the incapacity in online update. Traditional updaters are difficult to process the irregular variations and sampling noises of objects, so it is quite risky to adopt them to update Siamese networks. In this paper, we first present a two-stage one-shot learner, which can predict the local parameters of primary classifier with object samples from diverse stages. Then, an updatable Siamese network is proposed based on the learner (SiamTOL), which is able to complement online update by itself. Concretely, we introduce an extra inputting branch to sequentially capture the latest object features, and design a residual module to update the initial exemplar using these features. Besides, an effective multi-aspect training loss is designed for our network to avoid overfit. Extensive experimental results on several popular benchmarks including OTB100, VOT2018, VOT2019, LaSOT, UAV123 and GOT10k manifest that the proposed tracker achieves the leading performance and outperforms other state-of-the-art methods


AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking

Siamese approaches have achieved promising performance in visual object ...

Discriminative and Robust Online Learning for Siamese Visual Tracking

The problem of visual object tracking has traditionally been handled by ...

Hierarchical Siamese Network for Thermal Infrared Object Tracking

Most thermal infrared (TIR) tracking methods are discriminative, which t...

Learning to Filter: Siamese Relation Network for Robust Tracking

Despite the great success of Siamese-based trackers, their performance u...

Learning Cascaded Siamese Networks for High Performance Visual Tracking

Visual tracking is one of the most challenging computer vision problems....

Learning to Track Objects from Unlabeled Videos

In this paper, we propose to learn an Unsupervised Single Object Tracker...

Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking

Existing deep Thermal InfraRed (TIR) trackers only use semantic features...