# Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning

arXiv: https://arxiv.org/abs/2608.01488 · HTML: https://mlsanity.com/paper/2608.01488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 54 of its 73 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 54)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Transformer Tracking](https://mlsanity.com/paper/2103.15436/) (2021)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild](https://mlsanity.com/paper/1803.10794/) (2018)
- [Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework](https://mlsanity.com/paper/2203.11991/) (2022)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [Probabilistic Regression for Visual Tracking](https://mlsanity.com/paper/2003.12565/) (2020)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Siam R-CNN: Visual Tracking by Re-Detection](https://mlsanity.com/paper/1911.12836/) (2019)
- [Channel-wise Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/2011.13256/) (2020)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking](https://mlsanity.com/paper/2104.13202/) (2021)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [High-Performance Long-Term Tracking with Meta-Updater](https://mlsanity.com/paper/2004.00305/) (2020)
- [DepthTrack : Unveiling the Power of RGBD Tracking](https://mlsanity.com/paper/2108.13962/) (2021)
- [VITAL: VIsual Tracking via Adversarial Learning](https://mlsanity.com/paper/1804.04273/) (2018)
- [Single-Model and Any-Modality for Video Object Tracking](https://mlsanity.com/paper/2311.15851/) (2023)

## Abstract (arXiv)

Unified multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data (e.g., RGB, Thermal, Depth), yet the heavy computational burden of state-of-the-art models hinders their deployment on resource-constrained edge devices. In this work, we identify the prediction head as a critical but often overlooked efficiency bottleneck. By strategically streamlining the decoder architecture, we unlock the potential for real-time inference but simultaneously introduce a capacity gap between the lightweight student and the heavy teacher. To resolve this, we conduct a systematic analysis of 17 distillation strategies and introduce a Dual-Alignment Distillation framework. Our key insight is that effective compression requires decoupling knowledge transfer into two complementary streams: (1) Spatial Representation Alignment, which employs feature distillation to sharpen the student's spatial focus on foreground targets ("Where to track"); and (2) Semantic Distribution Alignment, which utilizes logit-based distillation to align decision boundaries and transfer discriminative dark knowledge ("What to track"). Extensive experiments across five benchmarks demonstrate that our approach significantly outperforms complex state-of-the-art methods. Notably, our distilled model achieves 91.5% MPR on RGBT234 and operates at 54 FPS on a single RTX 4090, representing a 5x speedup over the teacher model while maintaining superior accuracy.