# Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

arXiv: https://arxiv.org/abs/2103.14496 · HTML: https://mlsanity.com/paper/2103.14496/

## Key facts

- Cited by 9 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 24 of its 45 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Learning Discriminative Model Prediction for Tracking](https://mlsanity.com/paper/1904.07220/) (2019)
- [ATOM: Accurate Tracking by Overlap Maximization](https://mlsanity.com/paper/1811.07628/) (2018)
- [Learning Multi-Domain Convolutional Neural Networks for Visual Tracking](https://mlsanity.com/paper/1510.07945/) (2015)
- [Learning to Track at 100 FPS with Deep Regression Networks](https://mlsanity.com/paper/1604.01802/) (2016)
- [Massively Parallel Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1507.04296/) (2015)
- [Track to Reconstruct and Reconstruct to Track](https://mlsanity.com/paper/1910.00130/) (2019)
- [Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulation](https://mlsanity.com/paper/1710.06422/) (2017)
- [VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control](https://mlsanity.com/paper/1802.00265/) (2018)
- [PTB-TIR: A Thermal Infrared Pedestrian Tracking Benchmark](https://mlsanity.com/paper/1801.05944/) (2018)
- [RoadText-1K: Text Detection & Recognition Dataset for Driving Videos](https://mlsanity.com/paper/2005.09496/) (2020)
- [Kitting in the Wild through Online Domain Adaptation](https://mlsanity.com/paper/1807.01028/) (2018)
- [Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation](https://mlsanity.com/paper/1703.01461/) (2017)
- [Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition](https://mlsanity.com/paper/2004.10016/) (2020)
- [Sensor Transfer: Learning Optimal Sensor Effect Image Augmentation for Sim-to-Real Domain Adaptation](https://mlsanity.com/paper/1809.06256/) (2018)
- [Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator](https://mlsanity.com/paper/1909.08487/) (2019)
- [Adaptive Deep Learning through Visual Domain Localization](https://mlsanity.com/paper/1802.08833/) (2018)
- [Real-Time Multi-Diver Tracking and Re-identification for Underwater Human-Robot Collaboration](https://mlsanity.com/paper/1910.09636/) (2019)
- [Underwater Multi-Robot Convoying using Visual Tracking by Detection](https://mlsanity.com/paper/1709.08292/) (2017)

## Built on by (most cited first, 9 of 9)

- [Visual Object Tracking in First Person Vision](https://mlsanity.com/paper/2209.13502/) (2022)
- [Is First Person Vision Challenging for Object Tracking?](https://mlsanity.com/paper/2108.13665/) (2021)
- [PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search](https://mlsanity.com/paper/2403.15712/) (2024)
- [Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network](https://mlsanity.com/paper/2207.05497/) (2022)
- [Tracking Skiers from the Top to the Bottom](https://mlsanity.com/paper/2312.09723/) (2023)
- [RELO: Reinforcement Learning to Localize for Visual Object Tracking](https://mlsanity.com/paper/2605.07379/) (2026)
- [CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking](https://mlsanity.com/paper/2205.04261/) (2022)
- [Visualizing Skiers' Trajectories in Monocular Videos](https://mlsanity.com/paper/2304.02994/) (2023)
- [Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones](https://mlsanity.com/paper/2603.26551/) (2026)

## Abstract (arXiv)

Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In this paper we overcome such limitations by presenting the first methodology for domain adaption of such a class of trackers. To reduce the labeling effort we propose a weakly-supervised adaptation strategy, in which reinforcement learning is used to express weak supervision as a scalar application-dependent and temporally-delayed feedback. At the same time, knowledge distillation is employed to guarantee learning stability and to compress and transfer knowledge from more powerful but slower trackers. Extensive experiments on five different robotic vision domains demonstrate the relevance of our methodology. Real-time speed is achieved on embedded devices and on machines without GPUs, while accuracy reaches significant results.