mlsanityData to 7 Oct 2026

Oriented Response Networks

arXiv 1701.01833 ↗First posted 7 Jan 2017cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

Deep Convolution Neural Networks (DCNNs) are capable of learning unprecedentedly effective image representations. However, their ability in handling significant local and global image rotations remains limited. In this paper, we propose Active Rotating Filters (ARFs) that actively rotate during convolution and produce feature maps with location and orientation explicitly encoded. An ARF acts as a virtual filter bank containing the filter itself and its multiple unmaterialised rotated versions. During back-propagation, an ARF is collectively updated using errors from all its rotated versions. DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks. The oriented response produced by ORNs can also be used for image and object orientation estimation tasks. Over multiple state-of-the-art DCNN architectures, such as VGG, ResNet, and STN, we consistently observe that replacing regular filters with the proposed ARFs leads to significant reduction in the number of network parameters and improvement in classification performance. We report the best results on several commonly used benchmarks.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 14; 2023: 14; 2024: 5; 2025: 9; 2026: 4.

67 papers.

Sort:

By area:

  1. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  2. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  3. 2021Residual Pathway Priors for Soft Equivariance Constraintscited by 74
  4. 2022The Lie Derivative for Measuring Learned Equivariancecited by 51
  5. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  6. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  7. 2022Sample Efficiency of Data Augmentation Consistency Regularizationcited by 28
  8. 2023E(2)-Equivariant Vision Transformercited by 27
  9. 2021Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutionscited by 26
  10. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  11. 2022On the Strong Correlation Between Model Invariance and Generalizationcited by 23
  12. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
38 more
  1. 2022RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Networkcited by 20
  2. 2023From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communicationcited by 20
  3. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  4. 2023Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restorationcited by 17
  5. 2023Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networkscited by 16
  6. 2022Learning Instance-Specific Augmentations by Capturing Local Invariancescited by 15
  7. 2023Spatial Transform Decoupling for Oriented Object Detectioncited by 12
  8. 2021Arbitrary-Oriented Ship Detection through Center-Head Point Extractioncited by 9
  9. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
  10. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 7
  11. 2021Sampling Equivariant Self-attention Networks for Object Detection in Aerial Imagescited by 6
  12. 2022PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformercited by 6
  13. 2025Rotation-Equivariant Self-Supervised Method in Image Denoisingcited by 6
  14. 2021Plot2Spectra: an Automatic Spectra Extraction Toolcited by 5
  15. 2025A Regularization-Guided Equivariant Approach for Image Restorationcited by 5
  16. 2025Rotation Equivariant Arbitrary-scale Image Super-Resolutioncited by 5
  17. 2021Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapescited by 4
  18. 2021DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detectioncited by 4
  19. 2022PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNscited by 4
  20. 2023Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolutioncited by 4
  21. 2023SparseSwin: Swin Transformer with Sparse Transformer Blockcited by 4
  22. 2025Spectral State Space Model for Rotation-Invariant Visual Representation Learningcited by 4
  23. 2022Rotationally Equivariant Super-Resolution of Velocity Fields in Two-Dimensional Fluids Using Convolutional Neural Networkscited by 3
  24. 2023Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detectioncited by 3
  25. 2021The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutionscited by 2
  26. 2023TpopT: Efficient Trainable Template Optimization on Low-Dimensional Manifoldscited by 2
  27. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  28. 2025SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classificationcited by 2
  29. 2021Rotation invariant CNN using scattering transform for image classificationcited by 1
  30. 2021FILTRA: Rethinking Steerable CNN by Filter Transformcited by 1
  31. 2021Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributionscited by 1
  32. 2022RRL:Regional Rotation Layer in Convolutional Neural Networkscited by 1
  33. 2022Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluationcited by 1
  34. 2024Achieving Rotation-Invariant Convolution via Non-Learnable Orientation Alignment Operatorscited by 1
  35. 2025GMR-Conv: An Efficient Rotation and Reflection Equivariant Convolution Kernel Using Gaussian Mixture Ringscited by 1
  36. 2025Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detectioncited by 1
  37. 2026Rotation Equivariant Mamba for Vision Taskscited by 1
  38. 2026Image-to-Image Translation Framework Embedded with Rotation Symmetry Priorscited by 1

50 most cited of 67 All 67 (JSON)