Search Results for author:
Found 4 papers, 0 papers with code
PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation
First, the class-wise gradient magnitude homogenization helps alleviate the imbalance among label masks by ensuring equal consideration of the class-wise impact on model updates.
Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems
In remedy, we use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data, and to prune the training dataset in a manner that maximizes distribution overlap.
An Automated Real-Time Approach for Image Processing and Segmentation of Fluoroscopic Images and Videos Using a Single Deep Learning Network
Image segmentation in total knee arthroplasty is crucial for precise preoperative planning and accurate implant positioning, leading to improved surgical outcomes and patient satisfaction.
ARPD: Anchor-free Rotation-aware People Detection using Topview Fisheye Camera
To capture the various orientation of people in fish-eye cameras, in addition to the center and size, ARPD also predicts the angle of each bounding box.
