CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking

TL;DR

CGTrack introduces a hierarchical feature aggregation and gating mechanism to enhance UAV tracking accuracy and efficiency, addressing occlusion and viewpoint challenges with minimal computational overhead.

Contribution

The paper proposes a novel hierarchical feature cascade and gated center head to improve network capacity and discriminative ability in UAV tracking.

Findings

Achieves state-of-the-art performance on UAV benchmarks.

Runs at high speed with minimal computational cost.

Effectively handles occlusions and view angle variations.

Abstract

Recent advancements in visual object tracking have markedly improved the capabilities of unmanned aerial vehicle (UAV) tracking, which is a critical component in real-world robotics applications. While the integration of hierarchical lightweight networks has become a prevalent strategy for enhancing efficiency in UAV tracking, it often results in a significant drop in network capacity, which further exacerbates challenges in UAV scenarios, such as frequent occlusions and extreme changes in viewing angles. To address these issues, we introduce a novel family of UAV trackers, termed CGTrack, which combines explicit and implicit techniques to expand network capacity within a coarse-to-fine framework. Specifically, we first introduce a Hierarchical Feature Cascade (HFC) module that leverages the spirit of feature reuse to increase network capacity by integrating the deep semantic cues with the rich spatial information, incurring minimal computational costs while enhancing feature representation. Based on this, we design a novel Lightweight Gated Center Head (LGCH) that utilizes gating mechanisms to decouple target-oriented coordinates from previously expanded features, which contain dense local discriminative information. Extensive experiments on three challenging UAV tracking benchmarks demonstrate that CGTrack achieves state-of-the-art performance while running fast. Code will be available at https://github.com/Nightwatch-Fox11/CGTrack.