mlsanityData to 7 Oct 2026

Improving the Detection of Small Oriented Objects in Aerial Images

arXiv 2401.06503 ↗First posted 12 Jan 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Small oriented objects that represent tiny pixel-area in large-scale aerial images are difficult to detect due to their size and orientation. Existing oriented aerial detectors have shown promising results but are mainly focused on orientation modeling with less regard to the size of the objects. In this work, we proposed a method to accurately detect small oriented objects in aerial images by enhancing the classification and regression tasks of the oriented object detection model. We designed the Attention-Points Network consisting of two losses: Guided-Attention Loss (GALoss) and Box-Points Loss (BPLoss). GALoss uses an instance segmentation mask as ground-truth to learn the attention features needed to improve the detection of small objects. These attention features are then used to predict box points for BPLoss, which determines the points' position relative to the target oriented bounding box. Experimental results show the effectiveness of our Attention-Points Network on a standard oriented aerial dataset with small object instances (DOTA-v1.5) and on a maritime-related dataset (HRSC2016). The code is publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 12 Jan 2024.

Builds on

37 of 49 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  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. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  9. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  10. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  11. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  12. 2018Efficient Attention: Attention with Linear Complexitiescited by 366
25 more
  1. 2021Oriented R-CNN for Object Detectioncited by 230
  2. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  3. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  4. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
  5. 2020Align Deep Features for Oriented Object Detectioncited by 186
  6. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  7. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  8. 2019Gliding vertex on the horizontal bounding box for multi-oriented object detectioncited by 134
  9. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  10. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  11. 2020Dense Label Encoding for Boundary Discontinuity Free Rotation Detectioncited by 79
  12. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  13. 2020Dynamic Anchor Learning for Arbitrary-Oriented Object Detectioncited by 70
  14. 2020Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectorscited by 63
  15. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 59
  16. 2020PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environmentscited by 56
  17. 2017R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detectioncited by 51
  18. 2019Mask-Guided Attention Network for Occluded Pedestrian Detectioncited by 36
  19. 2022Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalizationcited by 36
  20. 2021HLA-Face: Joint High-Low Adaptation for Low Light Face Detectioncited by 28
  21. 2021RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detectioncited by 16
  22. 2021MogFace: Towards a Deeper Appreciation on Face Detectioncited by 9
  23. 2021Learning Maritime Obstacle Detection from Weak Annotations by Scaffoldingcited by 8
  24. 2021AlphaRotate: A Rotation Detection Benchmark using TensorFlowcited by 7
  25. 2021Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracingcited by 4

Built on by

Not cited yet.