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

arXiv: https://arxiv.org/abs/2308.10262 · HTML: https://mlsanity.com/paper/2308.10262/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 20 Aug 2023.

## Builds on (most cited first, 23 of 23)

- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [On Mutual Information Maximization for Representation Learning](https://mlsanity.com/paper/1907.13625/) (2019)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [HiFT: Hierarchical Feature Transformer for Aerial Tracking](https://mlsanity.com/paper/2108.00202/) (2021)
- [Graph Attention Tracking](https://mlsanity.com/paper/2011.11204/) (2020)
- [TCTrack: Temporal Contexts for Aerial Tracking](https://mlsanity.com/paper/2203.01885/) (2022)
- [Learn to Match: Automatic Matching Network Design for Visual Tracking](https://mlsanity.com/paper/2108.00803/) (2021)
- [Learning Background-Aware Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1703.04590/) (2017)
- [Face Anti-Spoofing Via Disentangled Representation Learning](https://mlsanity.com/paper/2008.08250/) (2020)
- [Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1803.08679/) (2018)
- [AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization](https://mlsanity.com/paper/2003.12949/) (2020)
- [Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking](https://mlsanity.com/paper/1908.02231/) (2019)
- [SparseTT: Visual Tracking with Sparse Transformers](https://mlsanity.com/paper/2205.03776/) (2022)
- [Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning](https://mlsanity.com/paper/2103.09420/) (2021)
- [Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization](https://mlsanity.com/paper/2012.01405/) (2020)
- [Towards Sequence-Level Training for Visual Tracking](https://mlsanity.com/paper/2208.05810/) (2022)
- [Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking](https://mlsanity.com/paper/1609.06118/) (2016)
- [Tracking Small and Fast Moving Objects: A Benchmark](https://mlsanity.com/paper/2209.04284/) (2022)
- [Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking](https://mlsanity.com/paper/2104.03114/) (2021)
- [Rank-Based Filter Pruning for Real-Time UAV Tracking](https://mlsanity.com/paper/2207.01768/) (2022)
- [Equivalence of Correlation Filter and Convolution Filter in Visual Tracking](https://mlsanity.com/paper/2105.00158/) (2021)

## Built on by (most cited first, 5 of 5)

- [Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking](https://mlsanity.com/paper/2504.09228/) (2025)
- [Tracking Transforming Objects: A Benchmark](https://mlsanity.com/paper/2404.18143/) (2024)
- [Tracking Reflected Objects: A Benchmark](https://mlsanity.com/paper/2407.05235/) (2024)
- [Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking](https://mlsanity.com/paper/2412.20002/) (2024)
- [TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking](https://mlsanity.com/paper/2507.01535/) (2025)

## Abstract (arXiv)

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.