mlsanityData to 7 Oct 2026

Domain Adaptive YOLO for One-Stage Cross-Domain Detection

arXiv 2106.13939 ↗First posted 26 Jun 2021cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Domain shift is a major challenge for object detectors to generalize well to real world applications. Emerging techniques of domain adaptation for two-stage detectors help to tackle this problem. However, two-stage detectors are not the first choice for industrial applications due to its long time consumption. In this paper, a novel Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. Image level features alignment is used to strictly match for local features like texture, and loosely match for global features like illumination. Multi-scale instance level features alignment is presented to reduce instance domain shift effectively , such as variations in object appearance and viewpoint. A consensus regularization to these domain classifiers is employed to help the network generate domain-invariant detections. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and etc.. The results demonstrate significant improvement when tested under different cross-domain scenarios.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 26 Jun 2021.

Builds on

23 of 33 references.

References · 23

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2015Fast R-CNNcited by 2,930
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  11. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
11 more
  1. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  2. 2016Domain Separation Networkscited by 317
  3. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  4. 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
  5. 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 111
  6. 2017Partial Transfer Learning with Selective Adversarial Networkscited by 84
  7. 2020PP-YOLO: An Effective and Efficient Implementation of Object Detectorcited by 44
  8. 2019Few-shot Adaptive Faster R-CNNcited by 42
  9. 2019SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Lossescited by 35
  10. 2019Multi-level Domain Adaptive learning for Cross-Domain Detectioncited by 30
  11. 2021Multiscale Domain Adaptive YOLO for Cross-Domain Object Detectioncited by 22

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 5; 2023: 4; 2024: 9; 2025: 2.

22 papers.

Sort:

  1. 2021Image-Adaptive YOLO for Object Detection in Adverse Weather Conditionscited by 85
  2. 2023FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Visioncited by 22
  3. 2022GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditionscited by 20
  4. 2024Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentationcited by 20
  5. 2022SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detectioncited by 19
  6. 2022TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learningcited by 10
  7. 2022Integrated Multiscale Domain Adaptive YOLOcited by 8
  8. 2022Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modelingcited by 8
  9. 2024Source-Free Domain Adaptation for YOLO Object Detectioncited by 8
  10. 2023Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectorscited by 5
  11. 2025Source-Free Object Detection with Detection Transformercited by 4
  12. 2024Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptationcited by 3
10 more
  1. 2023You Only Crash Once: Improved Object Detection for Real-Time, Sim-to-Real Hazardous Terrain Detection and Classification for Autonomous Planetary Landingscited by 2
  2. 2024FriendNet: Detection-Friendly Dehazing Networkcited by 2
  3. 2024D-YOLO a robust framework for object detection in adverse weather conditionscited by 2
  4. 2021Self-Adaptive Partial Domain Adaptationcited by 1
  5. 2023DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditionscited by 1
  6. 2024CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradationscited by 1
  7. 2024WARLearn: Weather-Adaptive Representation Learningcited by 1
  8. 2024SDNIA-YOLO: A Robust Object Detection Model for Extreme Weather Conditionscited by 0
  9. 2024CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detectorcited by 0
  10. 2025Ecological Legacies of Pre-Columbian Settlements Evident in Palm Clusters of Neotropical Mountain Forestscited by 0