# Source-Free Domain Adaptation for YOLO Object Detection

arXiv: https://arxiv.org/abs/2409.16538 · HTML: https://mlsanity.com/paper/2409.16538/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 67 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 30 of 51)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Progressive Domain Adaptation for Object Detection](https://mlsanity.com/paper/1910.11319/) (2019)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [Multi-adversarial Faster-RCNN for Unrestricted Object Detection](https://mlsanity.com/paper/1907.10343/) (2019)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)

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

- [VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors](https://mlsanity.com/paper/2510.00458/) (2025)
- [Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection](https://mlsanity.com/paper/2511.07301/) (2025)
- [Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection](https://mlsanity.com/paper/2512.17514/) (2025)
- [SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detection](https://mlsanity.com/paper/2507.12017/) (2025)
- [AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images](https://mlsanity.com/paper/2503.03370/) (2025)
- [Real-Time Source-Free Object Detection](https://mlsanity.com/paper/2606.31834/) (2026)
- [SFDATrack: Generalized Source-Free Domain Adaptive Tracking Under Adverse Weather Conditions](https://mlsanity.com/paper/2607.00369/) (2026)
- [YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family](https://mlsanity.com/paper/2608.07051/) (2026)
- [JMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency Learning](https://mlsanity.com/paper/2610.12901/) (2026)

## Abstract (arXiv)

Source-free domain adaptation (SFDA) is a challenging problem in object detection, where a pre-trained source model is adapted to a new target domain without using any source domain data for privacy and efficiency reasons. Most state-of-the-art SFDA methods for object detection have been proposed for Faster-RCNN, a detector that is known to have high computational complexity. This paper focuses on domain adaptation techniques for real-world vision systems, particularly for the YOLO family of single-shot detectors known for their fast baselines and practical applications. Our proposed SFDA method - Source-Free YOLO (SF-YOLO) - relies on a teacher-student framework in which the student receives images with a learned, target domain-specific augmentation, allowing the model to be trained with only unlabeled target data and without requiring feature alignment. A challenge with self-training using a mean-teacher architecture in the absence of labels is the rapid decline of accuracy due to noisy or drifting pseudo-labels. To address this issue, a teacher-to-student communication mechanism is introduced to help stabilize the training and reduce the reliance on annotated target data for model selection. Despite its simplicity, our approach is competitive with state-of-the-art detectors on several challenging benchmark datasets, even sometimes outperforming methods that use source data for adaptation.