mlsanityData to 14 Oct 2026

Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection

arXiv 2308.15353 ↗First posted 29 Aug 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data. In this paper, we propose a novel and effective four-step UDA approach that leverages self-supervision and trains source and target data concurrently. We harness self-supervised learning to mitigate the lack of ground truth in the target domain. Our method consists of the following steps: (1) identify the region with the highest-confidence set of detections in each target image, which serve as our pseudo-labels; (2) crop the identified region and generate a collection of its augmented versions; (3) combine these latter into a composite image; (4) adapt the network to the target domain using the composed image. Through extensive experiments under cross-camera, cross-weather, and synthetic-to-real scenarios, our approach achieves state-of-the-art performance, improving upon the nearest competitor by more than 2% in terms of mean Average Precision (mAP). The code is available at https://github.com/MohamedTEV/DACA.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

44 of 61 references.

References · 44

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2015Fast R-CNNcited by 2,933
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  5. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  7. 2017Random Erasing Data Augmentationcited by 1,239
  8. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  9. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  10. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 403
  11. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  12. 2018Few-shot Object Detection via Feature Reweightingcited by 265
32 more
  1. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  2. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  3. 2021Generalized Source-free Domain Adaptationcited by 175
  4. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 163
  5. 2019A review of domain adaptation without target labelscited by 156
  6. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  7. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 126
  8. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  9. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  10. 2020Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detectorcited by 107
  11. 2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
  12. 2020Dual Mixup Regularized Learning for Adversarial Domain Adaptationcited by 99
  13. 2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
  14. 2020A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Datacited by 79
  15. 2022SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detectioncited by 74
  16. 2020Spatial Attention Pyramid Network for Unsupervised Domain Adaptationcited by 56
  17. 2020Adapting Object Detectors with Conditional Domain Normalizationcited by 55
  18. 2022Instance Relation Graph Guided Source-Free Domain Adaptive Object Detectioncited by 55
  19. 2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
  20. 2019Domain Adaptation for Object Detection via Style Consistencycited by 45
  21. 2021Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detectioncited by 45
  22. 2020Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detectioncited by 44
  23. 2018A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenescited by 43
  24. 2019Few-shot Adaptive Faster R-CNNcited by 42
  25. 2019Curriculum Self-Paced Learning for Cross-Domain Object Detectioncited by 39
  26. 2022Task-specific Inconsistency Alignment for Domain Adaptive Object Detectioncited by 38
  27. 2022Multi-Granularity Alignment Domain Adaptation for Object Detectioncited by 29
  28. 2022ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixingcited by 28
  29. 2022Multi-Representation Adaptation Network for Cross-domain Image Classificationcited by 19
  30. 2022SMMix: Self-Motivated Image Mixing for Vision Transformerscited by 8
  31. 2022Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classificationcited by 5
  32. 2022D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptationcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024A Large-scale Multi Domain Leukemia Dataset for the White Blood Cells Detection with Morphological Attributes for Explainabilitycited by 4
  2. 2024Wild Berry image dataset collected in Finnish forests and peatlands using dronescited by 1
  3. 2025Leveraging Sparse Annotations for Leukemia Diagnosis on the Large Leukemia Datasetcited by 1
  4. 2025Leveraging Confident Image Regions for Source-Free Domain-Adaptive Object Detectioncited by 0