# Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition

arXiv: https://arxiv.org/abs/2310.19258 · HTML: https://mlsanity.com/paper/2310.19258/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (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)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?](https://mlsanity.com/paper/1610.01983/) (2016)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation](https://mlsanity.com/paper/2206.08367/) (2022)
- [Exploring Categorical Regularization for Domain Adaptive Object Detection](https://mlsanity.com/paper/2003.09152/) (2020)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data](https://mlsanity.com/paper/2012.05400/) (2020)
- [Automatic adaptation of object detectors to new domains using self-training](https://mlsanity.com/paper/1904.07305/) (2019)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [Reducing Label Effort: Self-Supervised meets Active Learning](https://mlsanity.com/paper/2108.11458/) (2021)
- [Towards Online Domain Adaptive Object Detection](https://mlsanity.com/paper/2204.05289/) (2022)
- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning](https://mlsanity.com/paper/2110.03143/) (2021)
- [Casting a BAIT for Offline and Online Source-free Domain Adaptation](https://mlsanity.com/paper/2010.12427/) (2020)
- [To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2307.15063/) (2023)
- [An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions](https://mlsanity.com/paper/2203.03568/) (2022)
- [Bi-Dimensional Feature Alignment for Cross-Domain Object Detection](https://mlsanity.com/paper/2011.07205/) (2020)
- [Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detection](https://mlsanity.com/paper/2302.06039/) (2023)

## Built on by (most cited first, 1 of 1)

- [Embodied Domain Adaptation for Object Detection](https://mlsanity.com/paper/2506.21860/) (2025)

## Abstract (arXiv)

Effective object detection in autonomous vehicles is challenged by deployment in diverse and unfamiliar environments. Online Source-Free Domain Adaptation (O-SFDA) offers model adaptation using a stream of unlabeled data from a target domain in an online manner. However, not all captured frames contain information beneficial for adaptation, especially in the presence of redundant data and class imbalance issues. This paper introduces a novel approach to enhance O-SFDA for adaptive object detection through unsupervised data acquisition. Our methodology prioritizes the most informative unlabeled frames for inclusion in the online training process. Empirical evaluation on a real-world dataset reveals that our method outperforms existing state-of-the-art O-SFDA techniques, demonstrating the viability of unsupervised data acquisition for improving the adaptive object detector.