Arbitrary-Oriented Object Detection with Circular Smooth Label

By Xue Yang, Junchi Yan. European Conference on Computer Vision, 2020

590 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/feb6f9d7082d29dbf4d6c1bb70b404f7237298b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Junchi Yan
2. Xue Yang
3. Guisong Xia
4. Jian Ding
5. Wentao Wang
6. Qi Ming
7. Nan Xue
8. Qi Tian

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Junchi Yan
4. Guisong Xia
5. Xue Yang
6. Qi Tian
7. Xiwen Yao
8. Jian Ding

Citations in the corpus

• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, methodology): “Angle prediction based on regression often introduces boundary discontinuity [51, 30, 48, 49], mainly including periodicity of angle (PoA) and exchangeability of edges (EoE).”
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (2021, methodology): “Recent advances in rotation detection [3, 4, 12, 14, 27] are mainly driven by adapting the horizontal object detectors with rotated bounding boxes to represent multi-oriented objects.”
• Poly Kernel Inception Network for Remote Sensing Detection (2024, background): “Consequently, numerous prior efforts have been dedicated to developing various oriented bounding box (OBB) detectors [10, 20, 31, 65, 67, 71] and improving the angle prediction accuracy for OBBs [68, 70, 72–74].”
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing (2020, background): “five-parameter regression [18], [23], [24], [25] suffer from the issue of discontinuous boundaries, which is inherently caused by the periodicity of angular (PoA) and exchangeability of edges (EoE) [26] (see details in Sec.”
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss (2021, methodology): “In contrast, the design of most peer works [66, 64] are coupled with the parameterization of bounding box.”
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection (2021, methodology): “CSL [38] regards angular prediction as a classification task to avoid discontinuous boundaries problem.”
• MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, background): “Aerial image detection plays a vital role in the military and attracts more and more attention in civilian field [3, 33, 34, 37].”
• Oriented R-CNN for Object Detection (2021, background): “In addition, some works [12, 28, 39, 27, 43, 16, 40, 47, 15] have explored one-stage or anchor-free oriented object detection frameworks: outputting object classes and oriented bounding boxes without region proposal generation and RoI alignment operation.”