# A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

arXiv: https://arxiv.org/abs/2012.05400 · HTML: https://mlsanity.com/paper/2012.05400/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 30 of 79)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [On Pitfalls of Test-Time Adaptation](https://mlsanity.com/paper/2306.03536/) (2023)
- [Learning Domain Adaptive Object Detection with Probabilistic Teacher](https://mlsanity.com/paper/2206.06293/) (2022)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Contrastive Mean Teacher for Domain Adaptive Object Detectors](https://mlsanity.com/paper/2305.03034/) (2023)
- [Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2102.11614/) (2021)
- [Label Matching Semi-Supervised Object Detection](https://mlsanity.com/paper/2206.06608/) (2022)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Domain Adaptive Semantic Segmentation without Source Data](https://mlsanity.com/paper/2110.06484/) (2021)
- [Multi-Granularity Alignment Domain Adaptation for Object Detection](https://mlsanity.com/paper/2203.16897/) (2022)
- [Attention Diversification for Domain Generalization](https://mlsanity.com/paper/2210.04206/) (2022)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing](https://mlsanity.com/paper/2210.11539/) (2022)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [Periodically Exchange Teacher-Student for Source-Free Object Detection](https://mlsanity.com/paper/2311.13930/) (2023)
- [UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2309.10244/) (2023)
- [Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2109.14651/) (2021)
- [Active Test-Time Adaptation: Theoretical Analyses and An Algorithm](https://mlsanity.com/paper/2404.05094/) (2024)
- [Efficient Teacher: Semi-Supervised Object Detection for YOLOv5](https://mlsanity.com/paper/2302.07577/) (2023)
- [PrivateSNN: Privacy-Preserving Spiking Neural Networks](https://mlsanity.com/paper/2104.03414/) (2021)
- [Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation](https://mlsanity.com/paper/2209.07910/) (2022)
- [DARTH: Holistic Test-time Adaptation for Multiple Object Tracking](https://mlsanity.com/paper/2310.01926/) (2023)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights](https://mlsanity.com/paper/2407.07586/) (2024)
- [Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation](https://mlsanity.com/paper/2407.13524/) (2024)
- [Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection](https://mlsanity.com/paper/2111.15656/) (2021)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. However, considering the data privacy and the inefficiency of data transmission, it is impractical in real scenarios. Hence, it draws our eyes to optimize the network in the target domain without accessing labeled source data. To explore this direction in object detection, for the first time, we propose a source data-free domain adaptive object detection (SFOD) framework via modeling it into a problem of learning with noisy labels. Generally, a straightforward method is to leverage the pre-trained network from the source domain to generate the pseudo labels for target domain optimization. However, it is difficult to evaluate the quality of pseudo labels since no labels are available in target domain. In this paper, self-entropy descent (SED) is a metric proposed to search an appropriate confidence threshold for reliable pseudo label generation without using any handcrafted labels. Nonetheless, completely clean labels are still unattainable. After a thorough experimental analysis, false negatives are found to dominate in the generated noisy labels. Undoubtedly, false negatives mining is helpful for performance improvement, and we ease it to false negatives simulation through data augmentation like Mosaic. Extensive experiments conducted in four representative adaptation tasks have demonstrated that the proposed framework can easily achieve state-of-the-art performance. From another view, it also reminds the UDA community that the labeled source data are not fully exploited in the existing methods.