TCDCaps: Visual Tracking via Cascaded Dense Capsules

TL;DR

TCDCaps introduces a cascaded dense capsule architecture to enhance visual tracking by improving feature robustness and candidate quality, effectively addressing drift and IoU threshold challenges in tracking-by-detection methods.

Contribution

The paper proposes a novel cascaded dense capsule network (CDCaps) that captures appearance variations and improves candidate quality in visual tracking.

Findings

Demonstrates robustness on three popular benchmarks.

Effectively handles appearance variations and drift.

Improves candidate quality through sequential IoU threshold training.

Abstract

The critical challenge in tracking-by-detection framework is how to avoid drift problem during online learning, where the robust features for a variety of appearance changes are difficult to be learned and a reasonable intersection over union (IoU) threshold that defines the true/false positives is hard to set. This paper presents the TCDCaps method to address the problems above via a cascaded dense capsule architecture. To get robust features, we extend original capsules with dense-connected routing, which are referred as DCaps. Depending on the preservation of part-whole relationships in the Capsule Networks, our dense-connected capsules can capture a variety of appearance variations. In addition, to handle the issue of IoU threshold, a cascaded DCaps model (CDCaps) is proposed to improve the quality of candidates, it consists of sequential DCaps trained with increasing IoU thresholds so as to sequentially improve the quality of candidates. Extensive experiments on 3 popular benchmarks demonstrate the robustness of the proposed TCDCaps.