mlsanityData to 7 Oct 2026

Assessing Domain Gap for Continual Domain Adaptation in Object Detection

arXiv 2302.10396 ↗First posted 21 Feb 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons. Continually adapting the detector to incorporate these changes is a promising solution, but it can be computationally costly. Our proposed approach is to selectively adapt the detector only when necessary, using new data that does not have the same distribution as the current training data. To this end, we investigate three popular metrics for domain gap evaluation and find that there is a correlation between the domain gap and detection accuracy. Therefore, we apply the domain gap as a criterion to decide when to adapt the detector. Our experiments show that our approach has the potential to improve the efficiency of the detector's operation in real-world scenarios, where environmental conditions change in a cyclical manner, without sacrificing the overall performance of the detector. Our code is publicly available at https://github.com/dadung/DGE-CDA.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 42 of its 75 references that are in the map. First posted on arXiv 21 Feb 2023.

Builds on

42 of 75 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  9. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  10. 2022Continual Test-Time Domain Adaptationcited by 520
  11. 2015Optimal Transport for Domain Adaptationcited by 457
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
30 more
  1. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  2. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  3. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  4. 2015Weakly Supervised Deep Detection Networkscited by 183
  5. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
  6. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
  7. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  8. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  9. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  10. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  11. 2021Multiple instance active learning for object detectioncited by 77
  12. 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
  13. 2018Banach Wasserstein GANcited by 56
  14. 2018Active Learning for Deep Object Detectioncited by 49
  15. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  16. 2019Scalable Place Recognition Under Appearance Change for Autonomous Drivingcited by 42
  17. 2021Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signalscited by 41
  18. 2015Weakly Supervised Object Localization with Multi-fold Multiple Instance Learningcited by 39
  19. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  20. 2021Consistency-based Active Learning for Object Detectioncited by 32
  21. 2019Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Nightcited by 30
  22. 2021Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehiclescited by 22
  23. 2020One-Shot Unsupervised Cross-Domain Detectioncited by 19
  24. 2014On learning to localize objects with minimal supervisioncited by 17
  25. 2017Deep Domain Adaptation by Geodesic Distance Minimizationcited by 17
  26. 2017Training object class detectors with click supervisioncited by 10
  27. 2019Wasserstein Distance Based Domain Adaptation for Object Detectioncited by 10
  28. 2022Update Compression for Deep Neural Networks on the Edgecited by 6
  29. 2020HM4: Hidden Markov Model with Memory Management for Visual Place Recognitioncited by 3
  30. 2021Autonomy and Perception for Space Miningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modelingcited by 18
  2. 2024Weakly Supervised Test-Time Domain Adaptation for Object Detectioncited by 2
  3. 2026Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexitycited by 0