# Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT

arXiv: https://arxiv.org/abs/2407.18288 · HTML: https://mlsanity.com/paper/2407.18288/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [MOT16: A Benchmark for Multi-Object Tracking](https://mlsanity.com/paper/1603.00831/) (2016)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [TransTrack: Multiple Object Tracking with Transformer](https://mlsanity.com/paper/2012.15460/) (2020)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion](https://mlsanity.com/paper/2111.14690/) (2021)
- [Multiple Object Tracking: A Literature Review](https://mlsanity.com/paper/1409.7618/) (2014)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [An Attentive Survey of Attention Models](https://mlsanity.com/paper/1904.02874/) (2019)
- [Knowledge Distillation from Internal Representations](https://mlsanity.com/paper/1910.03723/) (2019)
- [Knowledge Distillation for Multi-task Learning](https://mlsanity.com/paper/2007.06889/) (2020)
- [SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth](https://mlsanity.com/paper/2306.05238/) (2023)
- [Simple Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2006.02609/) (2020)
- [Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2102.13002/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Framework for Multi-View Multiple Object Tracking using Single-View Multi-Object Trackers on Fish Data](https://mlsanity.com/paper/2505.17201/) (2025)
- [Evidential Deep Learning for Multi-Modal Anti-UAV Detection](https://mlsanity.com/paper/2609.01742/) (2026)
- [OW-Rep: Open World Object Detection with Instance Representation Learning](https://mlsanity.com/paper/2409.16073/) (2024)
- [VSD-MOT: End-to-End Multi-Object Tracking in Low-Quality Video Scenes Guided by Visual Semantic Distillation](https://mlsanity.com/paper/2603.20731/) (2026)
- [Capability neq Interpretability: Human Interpretability of Vision Foundation Models](https://mlsanity.com/paper/2605.20337/) (2026)
- [Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance](https://mlsanity.com/paper/2610.08315/) (2026)

## Abstract (arXiv)

Multiple Object Tracking (MOT) is a computer vision task that has been employed in a variety of sectors. Some common limitations in MOT are varying object appearances, occlusions, or crowded scenes. To address these challenges, machine learning methods have been extensively deployed, leveraging large datasets, sophisticated models, and substantial computational resources. Due to practical limitations, access to the above is not always an option. However, with the recent release of foundation models by prominent AI companies, pretrained models have been trained on vast datasets and resources using state-of-the-art methods. This work tries to leverage one such foundation model, called DINOv2, through using knowledge distillation. The proposed method uses a teacher-student architecture, where DINOv2 is the teacher and the FairMOT backbone HRNetv2 W18 is the student. The results imply that although the proposed method shows improvements in certain scenarios, it does not consistently outperform the original FairMOT model. These findings highlight the potential and limitations of applying foundation models in knowledge