Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking

TL;DR

This paper introduces a novel contrastive learning approach to enhance discriminative feature representations for UAV tracking, achieving superior accuracy while maintaining efficiency and lightweight deployment.

Contribution

It is the first to apply contrastive learning to UAV tracking, improving discriminative power without manual annotations and enabling lightweight model development.

Findings

Significantly outperforms state-of-the-art UAV trackers on multiple benchmarks.

Effective contrastive learning enhances discriminative features for tracking.

Maintains high efficiency suitable for real-time UAV applications.

Abstract

Maintaining high efficiency and high precision are two fundamental challenges in UAV tracking due to the constraints of computing resources, battery capacity, and UAV maximum load. Discriminative correlation filters (DCF)-based trackers can yield high efficiency on a single CPU but with inferior precision. Lightweight Deep learning (DL)-based trackers can achieve a good balance between efficiency and precision but performance gains are limited by the compression rate. High compression rate often leads to poor discriminative representations. To this end, this paper aims to enhance the discriminative power of feature representations from a new feature-learning perspective. Specifically, we attempt to learn more disciminative representations with contrastive instances for UAV tracking in a simple yet effective manner, which not only requires no manual annotations but also allows for developing and deploying a lightweight model. We are the first to explore contrastive learning for UAV tracking. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and VisDrone2018, show that the proposed DRCI tracker significantly outperforms state-of-the-art UAV tracking methods.