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

Dan Zeng1; Mingliang Zou2; Xucheng Wang2; Shuiwang Li2

10.1109/ICME55011.2023.00234

2023

1945-7871

978-1-6654-6892-3

2023 IEEE International Conference on Multimedia and Expo (ICME)

2023-July

1349-1354

10-14 July 2023

Brisbane, Australia

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.

UAV tracking Discriminative representation Contrastive learning Contrastive Instances

第一

CPCI-S ; EI

WOS:001062707300217

20233814738407

Aircraft detection ; Deep learning ; Efficiency

Ergonomics and Human Factors Engineering:461.4 ; Aircraft, General:652.1 ; Radar Systems and Equipment:716.2 ; Production Engineering:913.1

IEEE

1.Southern University of Science and Technology, Shenzhen, China
2.Guilin University of Technology, Guilin, China

Dan Zeng,Mingliang Zou,Xucheng Wang,et al. Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking[C],2023:1349-1354.