mlsanityData to 7 Oct 2026

DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection

arXiv 2109.06148 ↗First posted 13 Sep 2021cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, it performs bounding box predictions on a dense grid over the input image, being architecturally simpler in design, as well as easier to optimize than its two-stage counterparts. Furthermore, as an anchor-free model, it reduces the prediction complexity by refraining from employing bounding box anchors. With DAFNe we introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions and a center-to-corner bounding box prediction strategy that improves object localization performance. Our experiments show that DAFNe outperforms all previous one-stage anchor-free models on DOTA 1.0, DOTA 1.5, and UCAS-AOD and is on par with the best models on HRSC2016.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

44 of 62 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  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. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  10. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  12. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
32 more
  1. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  2. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  3. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  4. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  5. 2021Oriented R-CNN for Object Detectioncited by 230
  6. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  7. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  8. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
  9. 2020Align Deep Features for Oriented Object Detectioncited by 186
  10. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  11. 2014Simultaneous Detection and Segmentationcited by 158
  12. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  13. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  14. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
  15. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 120
  16. 2019Learning Modulated Loss for Rotated Object Detectioncited by 73
  17. 2020Dynamic Anchor Learning for Arbitrary-Oriented Object Detectioncited by 70
  18. 2016T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videoscited by 67
  19. 2017Oriented Response Networkscited by 67
  20. 2020Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectorscited by 63
  21. 2020SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothingcited by 62
  22. 2020PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environmentscited by 56
  23. 2016Image Captioning and Visual Question Answering Based on Attributes and External Knowledgecited by 44
  24. 2019Oriented Objects as pairs of Middle Linescited by 43
  25. 2019FoveaBox: Beyond Anchor-based Object Detectorcited by 37
  26. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  27. 2021Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Losscited by 27
  28. 2017Learning a Rotation Invariant Detector with Rotatable Bounding Boxcited by 21
  29. 2019IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detectioncited by 17
  30. 2019Adaptive Period Embedding for Representing Oriented Objects in Aerial Imagescited by 14
  31. 2020Objects detection for remote sensing images based on polar coordinatescited by 8
  32. 2018Salience Biased Loss for Object Detection in Aerial Imagescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2; 2026: 1.

4 papers.

  1. 2022AO2-DETR: Arbitrary-Oriented Object Detection Transformercited by 55
  2. 2025GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detectioncited by 6
  3. 2025MKSNet: Advanced Small Object Detection in Remote Sensing Imagery with Multi-Kernel and Dual Attention Mechanismscited by 0
  4. 2026LOGOS: Language-guided Oriented Object Detection in Aerial Scenescited by 0