mlsanityData to 7 Oct 2026

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

arXiv 2310.19258 ↗First posted 30 Oct 2023cs.CVcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 38 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

25 of 38 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  6. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  7. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  8. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  9. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  10. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  11. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  12. 2020Exploring Categorical Regularization for Domain Adaptive Object Detectioncited by 130
13 more
  1. 2019Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detectioncited by 122
  2. 2020A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Datacited by 79
  3. 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
  4. 2022Instance Relation Graph Guided Source-Free Domain Adaptive Object Detectioncited by 55
  5. 2021Reducing Label Effort: Self-Supervised meets Active Learningcited by 42
  6. 2022Towards Online Domain Adaptive Object Detectioncited by 36
  7. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  8. 2021Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learningcited by 25
  9. 2020Casting a BAIT for Offline and Online Source-free Domain Adaptationcited by 23
  10. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  11. 2022An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditionscited by 6
  12. 2020Bi-Dimensional Feature Alignment for Cross-Domain Object Detectioncited by 4
  13. 2023Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detectioncited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Embodied Domain Adaptation for Object Detectioncited by 3