Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (2401.06159v1)

Published 22 Dec 2023 in cs.CV and cs.LG

Abstract: Rotation-equivariance is an essential yet challenging property in oriented object detection. While general object detectors naturally leverage robustness to spatial shifts due to the translation-equivariance of the conventional CNNs, achieving rotation-equivariance remains an elusive goal. Current detectors deploy various alignment techniques to derive rotation-invariant features, but still rely on high capacity models and heavy data augmentation with all possible rotations. In this paper, we introduce a Fully Rotation-Equivariant Oriented Object Detector (FRED), whose entire process from the image to the bounding box prediction is strictly equivariant. Specifically, we decouple the invariant task (object classification) and the equivariant task (object localization) to achieve end-to-end equivariance. We represent the bounding box as a set of rotation-equivariant vectors to implement rotation-equivariant localization. Moreover, we utilized these rotation-equivariant vectors as offsets in the deformable convolution, thereby enhancing the existing advantages of spatial adaptation. Leveraging full rotation-equivariance, our FRED demonstrates higher robustness to image-level rotation compared to existing methods. Furthermore, we show that FRED is one step closer to non-axis aligned learning through our experiments. Compared to state-of-the-art methods, our proposed method delivers comparable performance on DOTA-v1.0 and outperforms by 1.5 mAP on DOTA-v1.5, all while significantly reducing the model parameters to 16%.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. A program to build E (N)-equivariant steerable CNNs. In International Conference on Learning Representations.
  2. Hybrid task cascade for instance segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4974–4983.
  3. Piou loss: Towards accurate oriented object detection in complex environments. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, 195–211. Springer.
  4. Group equivariant convolutional networks. In International conference on machine learning, 2990–2999. PMLR.
  5. Learning RoI transformer for oriented object detection in aerial images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2849–2858.
  6. Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–1.
  7. The pascal visual object classes (voc) challenge. International journal of computer vision, 88: 303–338.
  8. Beyond bounding-box: Convex-hull feature adaptation for oriented and densely packed object detection. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, 8792–8801.
  9. Rotation equivariant siamese networks for tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12362–12371.
  10. Align deep features for oriented object detection. IEEE Transactions on Geoscience and Remote Sensing, 60: 1–11.
  11. Redet: A rotation-equivariant detector for aerial object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2786–2795.
  12. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2961–2969.
  13. Learning Rotation-Equivariant Features for Visual Correspondence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 21887–21897.
  14. Feature-attentioned object detection in remote sensing imagery. In 2019 IEEE international conference on image processing (ICIP), 3886–3890. IEEE.
  15. Oriented reppoints for aerial object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1829–1838.
  16. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, 2980–2988.
  17. Dynamic anchor learning for arbitrary-oriented object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 2355–2363.
  18. Dynamic refinement network for oriented and densely packed object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 11207–11216.
  19. Learning modulated loss for rotated object detection. In Proceedings of the AAAI conference on artificial intelligence, volume 35, 2458–2466.
  20. RSDet++: Point-based modulated loss for more accurate rotated object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(11): 7869–7879.
  21. Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 658–666.
  22. Attentive group equivariant convolutional networks. In International Conference on Machine Learning, 8188–8199. PMLR.
  23. Rotation equivariant CNNs for digital pathology. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11, 210–218. Springer.
  24. Oriented objects as pairs of middle lines. ISPRS Journal of Photogrammetry and Remote Sensing, 169: 268–279.
  25. General e (2)-equivariant steerable cnns. Advances in neural information processing systems, 32.
  26. DOTA: A Large-Scale Dataset for Object Detection in Aerial Images. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  27. Gliding vertex on the horizontal bounding box for multi-oriented object detection. IEEE transactions on pattern analysis and machine intelligence, 43(4): 1452–1459.
  28. R3det: Refined single-stage detector with feature refinement for rotating object. In Proceedings of the AAAI conference on artificial intelligence, volume 35, 3163–3171.
  29. Scrdet: Towards more robust detection for small, cluttered and rotated objects. In Proceedings of the IEEE/CVF international conference on computer vision, 8232–8241.
  30. The KFIoU loss for rotated object detection. arXiv preprint arXiv:2201.12558.
  31. Reppoints: Point set representation for object detection. In Proceedings of the IEEE/CVF international conference on computer vision, 9657–9666.
  32. Mmrotate: A rotated object detection benchmark using pytorch. In Proceedings of the 30th ACM International Conference on Multimedia, 7331–7334.
  33. Deformable convnets v2: More deformable, better results. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 9308–9316.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Chanho Lee (4 papers)
  2. Jinsu Son (1 paper)
  3. Hyounguk Shon (7 papers)
  4. Yunho Jeon (7 papers)
  5. Junmo Kim (90 papers)
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets