# General Compression Framework for Efficient Transformer Object Tracking

arXiv: https://arxiv.org/abs/2409.17564 · HTML: https://mlsanity.com/paper/2409.17564/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 49 of its 68 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild](https://mlsanity.com/paper/1810.11981/) (2018)
- [SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks](https://mlsanity.com/paper/1812.11703/) (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)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [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)
- [Ocean: Object-aware Anchor-free Tracking](https://mlsanity.com/paper/2006.10721/) (2020)
- [Siamese Box Adaptive Network for Visual Tracking](https://mlsanity.com/paper/2003.06761/) (2020)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines](https://mlsanity.com/paper/1911.06188/) (2019)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [ODTrack: Online Dense Temporal Token Learning for Visual Tracking](https://mlsanity.com/paper/2401.01686/) (2024)
- [Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking](https://mlsanity.com/paper/2203.05328/) (2022)
- [BERT-of-Theseus: Compressing BERT by Progressive Module Replacing](https://mlsanity.com/paper/2002.02925/) (2020)
- [Generalized Relation Modeling for Transformer Tracking](https://mlsanity.com/paper/2303.16580/) (2023)
- [MiniViT: Compressing Vision Transformers with Weight Multiplexing](https://mlsanity.com/paper/2204.07154/) (2022)

## Built on by (most cited first, 10 of 10)

- [Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach](https://mlsanity.com/paper/2505.12903/) (2025)
- [FARTrack: Fast Autoregressive Visual Tracking with High Performance](https://mlsanity.com/paper/2602.03214/) (2026)
- [Progressive Scaling Visual Object Tracking](https://mlsanity.com/paper/2505.19990/) (2025)
- [SwiTrack: Tri-State Switch for Cross-Modal Object Tracking](https://mlsanity.com/paper/2511.16227/) (2025)
- [Unified Multimodal Visual Tracking with Dual Mixture-of-Experts](https://mlsanity.com/paper/2605.03716/) (2026)
- [VL-UniTrack: A Unified Framework with Visual-Language Prompts for UAV-Ground Visual Tracking](https://mlsanity.com/paper/2605.04574/) (2026)
- [MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method](https://mlsanity.com/paper/2602.18006/) (2026)
- [Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking](https://mlsanity.com/paper/2605.06112/) (2026)
- [MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking](https://mlsanity.com/paper/2608.24365/) (2026)
- [LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking](https://mlsanity.com/paper/2609.33306/) (2026)

## Abstract (arXiv)

Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. However, these solutions often sacrifice accuracy for speed to a great extent, and also have the problems of complex training process and structural limitations. Thus, we propose a general model compression framework for efficient transformer object tracking, named CompressTracker, to reduce model size while preserving tracking accuracy. Our approach features a novel stage division strategy that segments the transformer layers of the teacher model into distinct stages to break the limitation of model structure. Additionally, we also design a unique replacement training technique that randomly substitutes specific stages in the student model with those from the teacher model, as opposed to training the student model in isolation. Replacement training enhances the student model's ability to replicate the teacher model's behavior and simplifies the training process. To further forcing student model to emulate teacher model, we incorporate prediction guidance and stage-wise feature mimicking to provide additional supervision during the teacher model's compression process. CompressTracker is structurally agnostic, making it compatible with any transformer architecture. We conduct a series of experiment to verify the effectiveness and generalizability of our CompressTracker. Our CompressTracker-SUTrack, compressed from SUTrack, retains about 99 performance on LaSOT (72.2 AUC) while achieves 2.42x speed up. Code is available at https://github.com/LingyiHongfd/CompressTracker.