mlsanityData to 7 Oct 2026

CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images

arXiv 2303.14639 ↗First posted 26 Mar 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern object detectors take advantage of rectangular bounding boxes as a conventional way to represent objects. When it comes to fisheye images, rectangular boxes involve more background noise rather than semantic information. Although multi-point representation has been proposed, both the regression accuracy and convergence still perform inferior to the widely used rectangular boxes. In order to further exploit the advantages of multi-point representation for distorted images, Concentric Rectangles Regression Strategy(CRRS) is proposed in this work. We adopt smoother mean loss to allocate weights and discuss the effect of hyper-parameter to prediction results. Moreover, an accurate pixel-level method is designed to obtain irregular IoU for estimating detector performance. Compared with the previous work for muti-point representation, the experiments show that CRRS can improve the training performance both in accurate and stability. We also prove that multi-task weighting strategy facilitates regression process in this design.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 26 Mar 2023.

Builds on

26 of 37 references.

References · 26

  1. 2015Fast R-CNNcited by 2,930
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  3. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  7. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  8. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  9. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  10. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  11. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  12. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
14 more
  1. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  2. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  3. 2018TextBoxes++: A Single-Shot Oriented Scene Text Detectorcited by 119
  4. 2018Adapting Auxiliary Losses Using Gradient Similaritycited by 98
  5. 2021Focal and Efficient IOU Loss for Accurate Bounding Box Regressioncited by 57
  6. 2020Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baselinecited by 41
  7. 2020Multi-Loss Weighting with Coefficient of Variationscited by 36
  8. 2020CircleNet: Anchor-free Detection with Circle Representationcited by 19
  9. 2020RAPiD: Rotation-Aware People Detection in Overhead Fisheye Imagescited by 17
  10. 2021Circle Representation for Medical Object Detectioncited by 15
  11. 2020Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusioncited by 13
  12. 2020HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Taskscited by 3
  13. 2021SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learningcited by 3
  14. 2022Field-of-View IoU for Object Detection in 360deg Imagescited by 2

Built on by

Not cited yet.