Updatable Siamese Tracker with Two-stage One-shot Learning
This addresses the need for robust object tracking in dynamic environments, representing an incremental improvement over existing Siamese trackers.
The paper tackles the problem of Siamese trackers failing in complex scenes due to lack of online update capacity by proposing an updatable Siamese network (SiamTOL) with a two-stage one-shot learner, achieving leading performance on benchmarks like OTB100 and VOT2018.
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