IEEE

Training Multi-Object Detector by Estimating Bounding Box Distribution for Input Image

Abstract: In multi-object detection using neural networks, the fundamental problem is, "How should the network learn a variable number of bounding boxes in different input images?". Previous methods ...
GitHub

Bounding-Box Aware Data Augmentation for YOLO Detection Pipelines

bounding-box–aware data augmentation for object detection datasets annotated in YOLO format. Unlike naive image-only augmentation approaches, this tool guarantees that bounding boxes remain ...
GitHub

Annotated object detection dataset with bounding boxes for training YOLO, R-CNN, and other object detection models.

object-detection-dataset/ ├── train/ │ ├── images/ # 800 training images │ │ ├── image_001.jpg │ │ ├── image_002.jpg ...
IEEE

Enhanced Small Object Detection via Attention Mechanism and Improved Bounding Box Regression Loss

Abstract: Small object detection remains a challenging task due to limited feature representation and inaccurate bounding box regression in complex scenes. To address these issues, we propose an ...
The Next Web

New to computer vision and medical imaging? Start with these 10 projects

(AI) and computer science that enables automated systems to see, i.e. to process images and video in a human-like manner to detect and identify objects or regions of importance, predict an outcome or ...