# Distilling Channels for Efficient Deep Tracking

arXiv: https://arxiv.org/abs/2409.11785 · HTML: https://mlsanity.com/paper/2409.11785/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [ECO: Efficient Convolution Operators for Tracking](https://mlsanity.com/paper/1611.09224/) (2016)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Need for Speed: A Benchmark for Higher Frame Rate Object Tracking](https://mlsanity.com/paper/1703.05884/) (2017)
- [Detect to Track and Track to Detect](https://mlsanity.com/paper/1710.03958/) (2017)
- [End-to-end representation learning for Correlation Filter based tracking](https://mlsanity.com/paper/1704.06036/) (2017)
- [Learning to Track at 100 FPS with Deep Regression Networks](https://mlsanity.com/paper/1604.01802/) (2016)
- [Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking](https://mlsanity.com/paper/1608.03773/) (2016)
- [Learning Spatially Regularized Correlation Filters for Visual Tracking](https://mlsanity.com/paper/1608.05571/) (2016)
- [A Twofold Siamese Network for Real-Time Object Tracking](https://mlsanity.com/paper/1802.08817/) (2018)
- [Discriminative Scale Space Tracking](https://mlsanity.com/paper/1609.06141/) (2016)
- [Discriminative Correlation Filter with Channel and Spatial Reliability](https://mlsanity.com/paper/1611.08461/) (2016)
- [CREST: Convolutional Residual Learning for Visual Tracking](https://mlsanity.com/paper/1708.00225/) (2017)
- [Learning Policies for Adaptive Tracking with Deep Feature Cascades](https://mlsanity.com/paper/1708.02973/) (2017)
- [Context-aware Deep Feature Compression for High-speed Visual Tracking](https://mlsanity.com/paper/1803.10537/) (2018)
- [Good Features to Correlate for Visual Tracking](https://mlsanity.com/paper/1704.06326/) (2017)
- [Robust Visual Tracking Revisited: From Correlation Filter to Template Matching](https://mlsanity.com/paper/1904.06842/) (2019)
- [Convolutional Regression for Visual Tracking](https://mlsanity.com/paper/1611.04215/) (2016)
- [Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation](https://mlsanity.com/paper/1701.00561/) (2017)

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

- [Underwater Camouflaged Object Tracking Meets Vision-Language SAM2](https://mlsanity.com/paper/2409.16902/) (2024)
- [MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking](https://mlsanity.com/paper/2411.15761/) (2024)
- [Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark](https://mlsanity.com/paper/2502.05574/) (2025)
- [MVTD: A Benchmark Dataset for Maritime Visual Object Tracking](https://mlsanity.com/paper/2506.02866/) (2025)
- [How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2512.07385/) (2025)

## Abstract (arXiv)

Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep networks employed are usually trained to extract rich knowledge from massive data used in object classification and so they are capable to represent generic objects very well. However, these networks are too complex to represent a specific moving object, leading to poor generalization as well as high computational and memory costs. This paper presents a novel and general framework termed channel distillation to facilitate deep trackers. To validate the effectiveness of channel distillation, we take discriminative correlation filter (DCF) and ECO for example. We demonstrate that an integrated formulation can turn feature compression, response map generation, and model update into a unified energy minimization problem to adaptively select informative feature channels that improve the efficacy of tracking moving objects on the fly. Channel distillation can accurately extract good channels, alleviating the influence of noisy channels and generally reducing the number of channels, as well as adaptively generalizing to different channels and networks. The resulting deep tracker is accurate, fast, and has low memory requirements. Extensive experimental evaluations on popular benchmarks clearly demonstrate the effectiveness and generalizability of our framework.