Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking

TL;DR

This paper introduces a disentangled representation learning approach with mutual information maximization to improve the accuracy and efficiency of deep learning-based UAV trackers, outperforming existing methods on multiple benchmarks.

Contribution

It proposes a novel DR-MIM method that separates features into identity-related and unrelated parts, enhancing tracking precision and efficiency for UAV applications.

Findings

Significantly outperforms state-of-the-art UAV tracking methods

Achieves higher tracking precision with improved efficiency

Demonstrates robustness across four UAV benchmark datasets

Abstract

Efficiency has been a critical problem in UAV tracking due to limitations in computation resources, battery capacity, and unmanned aerial vehicle maximum load. Although discriminative correlation filters (DCF)-based trackers prevail in this field for their favorable efficiency, some recently proposed lightweight deep learning (DL)-based trackers using model compression demonstrated quite remarkable CPU efficiency as well as precision. Unfortunately, the model compression methods utilized by these works, though simple, are still unable to achieve satisfying tracking precision with higher compression rates. This paper aims to exploit disentangled representation learning with mutual information maximization (DR-MIM) to further improve DL-based trackers' precision and efficiency for UAV tracking. The proposed disentangled representation separates the feature into an identity-related and an identity-unrelated features. Only the latter is used, which enhances the effectiveness of the feature representation for subsequent classification and regression tasks. Extensive experiments on four UAV benchmarks, including UAV123@10fps, DTB70, UAVDT and VisDrone2018, show that our DR-MIM tracker significantly outperforms state-of-the-art UAV tracking methods.