Tackling Occlusion in Siamese Tracking with Structured Dropouts

TL;DR

This paper introduces structured dropout techniques to simulate occlusion effects in the latent space of Siamese trackers, improving robustness against occlusion without complex modifications.

Contribution

It proposes three types of structured dropout methods to model occlusion effects and integrates them into existing Siamese trackers for enhanced robustness.

Findings

Structured dropouts improve tracking accuracy under occlusion.

The method requires minimal modifications to existing models.

Experiments demonstrate consistent performance gains across benchmarks.

Abstract

Occlusion is one of the most difficult challenges in object tracking to model. This is because unlike other challenges, where data augmentation can be of help, occlusion is hard to simulate as the occluding object can be anything in any shape. In this paper, we propose a simple solution to simulate the effects of occlusion in the latent space. Specifically, we present structured dropout to mimick the change in latent codes under occlusion. We present three forms of dropout (channel dropout, segment dropout and slice dropout) with the various forms of occlusion in mind. To demonstrate its effectiveness, the dropouts are incorporated into two modern Siamese trackers (SiamFC and SiamRPN++). The outputs from multiple dropouts are combined using an encoder network to obtain the final prediction. Experiments on several tracking benchmarks show the benefits of structured dropouts, while due to their simplicity requiring only small changes to the existing tracker models.