# Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

arXiv: https://arxiv.org/abs/2407.07586 · HTML: https://mlsanity.com/paper/2407.07586/

## Key facts

- Cited by 14 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 43 of its 55 references that are in the map.
- First posted on arXiv 10 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, 30 of 43)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [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)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [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)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Learning to Optimize Domain Specific Normalization for Domain Generalization](https://mlsanity.com/paper/1907.04275/) (2019)
- [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)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data](https://mlsanity.com/paper/2012.05400/) (2020)
- [Spatial Attention Pyramid Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2003.12979/) (2020)

## Built on by (most cited first, 14 of 14)

- [Embodied Domain Adaptation for Object Detection](https://mlsanity.com/paper/2506.21860/) (2025)
- [varphi-Adapt: A Physics-Informed Adaptation Learning Approach to 2D Quantum Material Discovery](https://mlsanity.com/paper/2507.05184/) (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)
- [Mitigating Negative Transfer via Reducing Environmental Disagreement](https://mlsanity.com/paper/2510.24044/) (2025)
- [Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection](https://mlsanity.com/paper/2501.10081/) (2025)
- [Context Aware Grounded Teacher for Source Free Object Detection](https://mlsanity.com/paper/2504.15404/) (2025)
- [Self-Supervised Uncalibrated Multi-View Video Anonymization in the Operating Room](https://mlsanity.com/paper/2602.02850/) (2026)
- [CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection](https://mlsanity.com/paper/2602.22621/) (2026)
- [Real-Time Source-Free Object Detection](https://mlsanity.com/paper/2606.31834/) (2026)
- [LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2607.17653/) (2026)
- [Degraded Infrared Small Object Detection via Degradation-Adapted Physics-Guided Restoration](https://mlsanity.com/paper/2608.09311/) (2026)
- [DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection](https://mlsanity.com/paper/2608.16632/) (2026)

## Abstract (arXiv)

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed various solutions for Source-Free Object Detection (SFOD), most being variations of teacher-student architectures with diverse feature alignment, regularization and pseudo-label selection strategies. Our work investigates simpler approaches and their performance compared to more complex SFOD methods in several adaptation scenarios. We highlight the importance of batch normalization layers in the detector backbone, and show that adapting only the batch statistics is a strong baseline for SFOD. We propose a simple extension of a Mean Teacher with strong-weak augmentation in the source-free setting, Source-Free Unbiased Teacher (SF-UT), and show that it actually outperforms most of the previous SFOD methods. Additionally, we showcase that an even simpler strategy consisting in training on a fixed set of pseudo-labels can achieve similar performance to the more complex teacher-student mutual learning, while being computationally efficient and mitigating the major issue of teacher-student collapse. We conduct experiments on several adaptation tasks using benchmark driving datasets including (Foggy)Cityscapes, Sim10k and KITTI, and achieve a notable improvement of 4.7% AP50 on CityscapesrightarrowFoggy-Cityscapes compared with the latest state-of-the-art in SFOD. Source code is available at https://github.com/EPFL-IMOS/simple-SFOD.