Rank-Based Filter Pruning for Real-Time UAV Tracking

TL;DR

This paper introduces P-SiamFC++, a novel rank-based filter pruning method that compresses deep learning models for UAV tracking, achieving a better balance of efficiency and accuracy suitable for resource-constrained UAVs.

Contribution

It is the first to apply rank-based filter pruning to UAV tracking models, significantly improving efficiency while maintaining high precision.

Findings

Outperforms state-of-the-art UAV tracking methods on four benchmarks.

Achieves a remarkable balance between efficiency and precision.

Demonstrates the generality of the proposed model compression approach.

Abstract

Unmanned aerial vehicle (UAV) tracking has wide potential applications in such as agriculture, navigation, and public security. However, the limitations of computing resources, battery capacity, and maximum load of UAV hinder the deployment of deep learning-based tracking algorithms on UAV. Consequently, discriminative correlation filters (DCF) trackers stand out in the UAV tracking community because of their high efficiency. However, their precision is usually much lower than trackers based on deep learning. Model compression is a promising way to narrow the gap (i.e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking. In this paper, we propose the P-SiamFC++ tracker, which is the first to use rank-based filter pruning to compress the SiamFC++ model, achieving a remarkable balance between efficiency and precision. Our method is general and may encourage further studies on UAV tracking with model compression. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and Vistrone2018, show that P-SiamFC++ tracker significantly outperforms state-of-the-art UAV tracking methods.