Residual UNet

Residual UNets are a class of convolutional neural networks used for image segmentation tasks, primarily aiming to improve accuracy and efficiency by incorporating residual connections within the U-Net architecture. Current research focuses on enhancing performance through modifications like incorporating attention mechanisms, specialized loss functions (e.g., Generalized Dice Focal Loss), and hybrid approaches combining UNets with other architectures (e.g., 3DResNet). These advancements are significantly impacting various fields, including medical image analysis (e.g., brain tumor and lesion segmentation in PET/CT scans, retinal vessel segmentation) and remote sensing (e.g., marine debris detection, precipitation nowcasting), by enabling more accurate and automated image analysis.

Papers

October 24, 2024

Multi-Stage Airway Segmentation in Lung CT Based on Multi-scale Nested Residual UNet
Bingyu Yang, Huai Liao, Xinyan Huang, Qingyao Tian, Jinlin Wu, Jingdi Hu, Hongbin Liu
Medical Image Segmentation Multi Scale Airway Segmentation Lung CT Segmentation Pipeline Residual Information Residual U Net Residual UNet

September 16, 2024

AutoPET Challenge III: Testing the Robustness of Generalized Dice Focal Loss trained 3D Residual UNet for FDG and PSMA Lesion Segmentation from Whole-Body PET/CT Images
Shadab Ahamed
CT Image Focal Loss Lesion Localization Residual UNet

May 22, 2024

Hybrid Multihead Attentive Unet-3D for Brain Tumor Segmentation
Muhammad Ansab Butt, Absaar Ul Jabbar
U Net Brain Tumor Segmentation Brain Tumor Region Segmentation Residual UNet

September 24, 2023

Generalized Dice Focal Loss trained 3D Residual UNet for Automated Lesion Segmentation in Whole-Body FDG PET/CT Images
Shadab Ahamed, Arman Rahmim
CT Image Lesion Segmentation Whole Body Focal Loss Deep Learning Based Segmentation Residual UNet

April 13, 2023

Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser
Astha Verma, Siddhesh Bangar, A V Subramanyam, Naman Lal, Rajiv Ratn Shah, Shin'ichi Satoh
Adversarial Perturbation Black Box Model Black Box Defense Residual UNet

March 12, 2023

SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Tasks
Mathieu Renault, Siamak Mehrkanoon
UNet Based Data Driven Nowcasting Precipitation Nowcasting Attention UNet Residual UNet Precipitation Map

October 16, 2022

ResAttUNet: Detecting Marine Debris using an Attention activated Residual UNet
Azhan Mohammed
Deep Learning Human Attention Spatial Encoder Marine Debris Residual UNet Debris Detection

September 1, 2022

Physics-informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites
Zeyu Cao, Wen Yao, Wei Peng, Xiaoya Zhang, Kairui Bao
Human Prediction Multi Task Learning Deformation Behavior Physic Informed Learning Multiple Satellite Human Stress Residual UNet Deformation Prediction

November 10, 2021

Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet
Bo Wang, Reza Mohajerpoor, Chen Cai, Inhi Kim, Hai L. Vu
Traffic Forecasting Traffic Pattern Traffic4cast Competition Real Time Traffic Residual UNet

November 8, 2021

DR-VNet: Retinal Vessel Segmentation via Dense Residual UNet
Ali Karaali, Rozenn Dahyot, Donal J. Sexton
Deep Learning Vessel Segmentation Retinal Vessel Segmentation Residual Block Poor Segmentation Residual UNet