Multi Task UNet

Multi-task UNet architectures are convolutional neural networks designed to simultaneously perform multiple related tasks on image data, improving efficiency and performance compared to training separate models for each task. Current research focuses on adapting these networks for diverse applications, including image fusion, domain adaptation, and medical image analysis, often employing variations like asymmetric UNets or incorporating modules like atrous convolutions and attention mechanisms to enhance performance. This approach is proving valuable in various fields, offering improvements in accuracy and efficiency for tasks ranging from autonomous driving to medical image segmentation and analysis. The ability to jointly learn multiple tasks from a single model is driving significant advancements in computer vision and related areas.

Papers

April 27, 2024

MMA-UNet: A Multi-Modal Asymmetric UNet Architecture for Infrared and Visible Image Fusion
Jingxue Huang, Xilai Li, Tianshu Tan, Xiaosong Li, Tao Ye
Image Fusion Richer RGB Infrared Feature Visible Image Fusion Multi Modal Image Scale Fusion Multi Task UNet

April 16, 2024

Exploring selective image matching methods for zero-shot and few-sample unsupervised domain adaptation of urban canopy prediction
John Francis, Stephen Law
Domain Adaptation Unsupervised Domain Adaptation Image to Image Image Matching Pixel Wise Adaptive Urban Prediction Multi Task UNet

November 24, 2022

Mediastinal Lymph Node Detection and Segmentation Using Deep Learning
Al-Akhir Nayan, Boonserm Kijsirikul, Yuji Iwahori
Deep Learning Deep Convolutional Neural Network Segmentation Based Approach Lymph Node Mediastinal Lymph Node Multi Task UNet

May 6, 2022

Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection
Ziteng Cui, Guo-Jun Qi, Lin Gu, Shaodi You, Zenghui Zhang, Tatsuya Harada
Object Detection Model Detection Task Illumination Estimation Auto Encoders Orthogonality Regularization Dark Object Detection Multi Task UNet

April 7, 2022

MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation
Ting Zhang, Jun Li, Yi Zhao, Nan Chen, Han Zhou, Hongtao Xu, Zihao Guan, Changcai Yang, Lanyan Xue, Riqing Chen, Lifang Wei
Vessel Segmentation U Shaped Network Retinal Image Datasets Retinal Blood Vessel Segmentation Atrous Convolution Multi Task UNet

February 15, 2022

Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images
Hongzhi Zhu, Robert Rohling, Septimiu Salcudean
Multi Task Learning Visual Attention Chest X Ray Image Disease Classification Saliency Prediction Multi Task UNet

December 16, 2021

Multi-task UNet architecture for end-to-end autonomous driving
Der-Hau Lee, Jinn-Liang Liu
Autonomous Driving Reinforcement Learning Model Multi Task UNet Path Prediction

Multi Task UNet

Papers

MMA-UNet: A Multi-Modal Asymmetric UNet Architecture for Infrared and Visible Image Fusion

Exploring selective image matching methods for zero-shot and few-sample unsupervised domain adaptation of urban canopy prediction

Mediastinal Lymph Node Detection and Segmentation Using Deep Learning

Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection

MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation

Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images

Multi-task UNet architecture for end-to-end autonomous driving