mlsanityData to 7 Oct 2026

Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detection

arXiv 2501.10081 ↗First posted 17 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Source-free domain-adaptive object detection is an interesting but scarcely addressed topic. It aims at adapting a source-pretrained detector to a distinct target domain without resorting to source data during adaptation. So far, there is no data augmentation scheme tailored to source-free domain-adaptive object detection. To this end, this paper presents a novel data augmentation approach that cuts out target image regions where the detector is confident, augments them along with their respective pseudo-labels, and joins them into a challenging target image to adapt the detector. As the source data is out of reach during adaptation, we implement our approach within a teacher-student learning paradigm to ensure that the model does not collapse during the adaptation procedure. We evaluated our approach on three adaptation benchmarks of traffic scenes, scoring new state-of-the-art on two of them.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

41 of 59 references.

References · 41

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2019Objects as Pointscited by 1,172
  12. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
29 more
  1. 2019Object Detection in 20 Years: A Surveycited by 528
  2. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  3. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  4. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  5. 2019Progressive Domain Adaptation for Object Detectioncited by 134
  6. 2020A Review and Comparative Study on Probabilistic Object Detection in Autonomous Drivingcited by 115
  7. 2020Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detectorcited by 106
  8. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  9. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  10. 2020A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Datacited by 79
  11. 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
  12. 2023Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networkscited by 55
  13. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  14. 2019Domain Adaptation for Object Detection via Style Consistencycited by 45
  15. 2021Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detectioncited by 45
  16. 2022Domain Adaptive Object Detection for Autonomous Driving under Foggy Weathercited by 41
  17. 2019Curriculum Self-Paced Learning for Cross-Domain Object Detectioncited by 39
  18. 2022ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixingcited by 28
  19. 2023Adversarial Alignment for Source Free Object Detectioncited by 25
  20. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  21. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  22. 2022SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detectioncited by 19
  23. 2023Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performancescited by 15
  24. 2024Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insightscited by 14
  25. 2023Exploiting Low-confidence Pseudo-labels for Source-free Object Detectioncited by 13
  26. 2021A fast accurate fine-grain object detection model based on YOLOv4 deep neural networkcited by 9
  27. 2024ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentationcited by 6
  28. 2023Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detectioncited by 4
  29. 2023Spectral Transfer Guided Active Domain Adaptation For Thermal Imagerycited by 3

Built on by

Not cited yet.