Shape-IoU: More Accurate Metric considering Bounding Box Shape and Scale
Explore this paper's citation graph
Summary
This article analyzed the regression characteristics of the bounding boxes and found that the shape and scale factors of the bounding boxes themselves will have an impact on the regression results, which will make the bounding box regression more accurate.
- Type
- preprint
- Published
- 2023-12-29
- Cited by
- 245
- References
- 14
- Access
- Open access
- OpenAlex
- https://openalex.org/W4390524233
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:266690801
Keywords
Minimum bounding box, Bounding overwatch, Computer science, Scale (ratio), Regression
References
- You Only Look Once: Unified, Real-Time Object Detection
- UnitBox: An Advanced Object Detection Network
- CornerNet: Detecting Objects as Paired Keypoints
- CenterNet: Keypoint Triplets for Object Detection
- Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
- Focal Loss for Dense Object Detection
- FCOS: Fully Convolutional One-Stage Object Detection
- Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
- Focal and Efficient IOU Loss for Accurate Bounding Box Regression
- Dot Distance for Tiny Object Detection in Aerial Images
- SIoU Loss: More Powerful Learning for Bounding Box Regression
- Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
- SSD: Single Shot MultiBox Detector
- Fast R-CNN
Cited by
- HR-YOLOv8: A Crop Growth Status Object Detection Method Based on YOLOv8
- Infrared Thermography-based Temperature Detection of Key Components in Switchgear
- YOLO-DLHS-P: A Lightweight Behavior Recognition Algorithm for Captive Pigs
- SRFAD-Net: Scale-Robust Feature Aggregation and Diffusion Network for Object Detection in Remote Sensing Images
- Enhanced YOLOv7 for Improved Underwater Target Detection
- Lightweight tomato ripeness detection algorithm based on the improved RT-DETR
- MW-YOLO: Improved YOLOv8n for Lightweight Dense Vehicle Object Detection Algorithm
- SC-YOLO: An Improved Yolo Network for PCB Defect Detection
- Real-time medical lesion screening: accurate and rapid detectors
- YOLO-RMS: A Lightweight and Efficient Detector for Object Detection in Remote Sensing
- An algorithmic model for recognizing healthy wheat seeds based on YOLOv8
- Research on Face Detection Algorithm Based on Improved YOLOv5
- HP-YOLOv8: High-Precision Small Object Detection Algorithm for Remote Sensing Images
- Efficient Real-time Detection of Complex Tire Cord Defects on Airjet Loom
- SONet: A Small Object Detection Network for Power Line Inspection Based on YOLOv8
- LDSI-YOLOv8: Real-Time Detection Method for Multiple Targets in Coal Mine Excavation Scenes
- DMFF-YOLO: YOLOv8 Based on Dynamic Multiscale Feature Fusion for Object Detection on UAV Aerial Photography
- Lightweight Motorcycle Helmet Detection Based on Improved YOLOv7-Tiny
- An improved YOLOv5s method of vehicle target detection in remote sensing images
- Infrared Ship Object Detection Utilizing Deformable Large Kernel Convolution and a Highly Sensitive Intersection over Union Loss
Related papers
- Bounding-box Centralization for Improving SiamFC++
- Syncretic-NMS: A Merging Non-Maximum Suppression Algorithm for Instance Segmentation
- Medical image segmentation with imperfect 3D bounding boxes
- A Method to Generate the Minimum Bounding Boxes for Shape-Arbitrary Objects
- Fully Functional Image Manipulation Using Scene Graphs in A Bounding-Box Free Way
- Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint