Results 11 to 20 of about 5,768,655 (280)

Scale Equivariant U-Net [PDF]

CoRR, 2022
In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equivariant networks are suited to computer vision tasks where the same classes of objects appear at different scales, like in most semantic segmentation tasks.
Sangalli, Mateus, Blusseau, Samy, Velasco-Forero, Santiago, Angulo, Jesus   +3 more
core   +6 more sources

A Residual-Inception U-Net (RIU-Net) Approach and Comparisons with U-Shaped CNN and Transformer Models for Building Segmentation from High-Resolution Satellite Images

Sensors, 2022
Building segmentation is crucial for applications extending from map production to urban planning. Nowadays, it is still a challenge due to CNNs’ inability to model global context and Transformers’ high memory need.
Batuhan Sariturk, Dursun Zafer Seker
doaj   +2 more sources

UIU-Net: U-Net in U-Net for Infrared Small Object Detection

IEEE Transactions on Image Processing, 2023
Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for ...
Xin Wu 0001, Danfeng Hong, Jocelyn Chanussot   +2 more
openaire   +5 more sources

Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations

CoRR, 2019
Data-driven models for audio source separation such as U-Net or Wave-U-Net are usually models dedicated to and specifically trained for a single task, e.g. a particular instrument isolation. Training them for various tasks at once commonly results in worse performances than training them for a single specialized task.
Meseguer-Brocal, Gabriel, Peeters, Geoffroy   +1 more
openaire   +6 more sources

MSR U-Net: An Improved U-Net Model for Retinal Blood Vessel Segmentation

IEEE Access
For the proper diagnosis and treatment of a variety of retinal conditions, retinal blood vessel segmentation is crucial. Delineation of vessels with varying thicknesses is critical for detecting disease symptoms.
Giri Babu Kande, Logesh Ravi, Nitya Kande, Madhusudana Rao Nalluri, Hossam Kotb, Kareem M. AboRas, Amr Yousef, Yazeed Yasin Ghadi, A. Sasikumar   +8 more
doaj   +2 more sources

U-Net Optimization for Hyperreflective Foci Segmentation in Retinal OCT [PDF]

Diagnostics
Background/Objectives: Hyperreflective foci (HRF) are supportive optical coherence tomography (OCT) imaging biomarkers that have been examined for their association with disease progression and severity in various retinal disorders.
Pavithra Kodiyalbail Chakrapani, Preetham Kumar, Sulatha Venkataraya Bhandary, Geetha Maiya, Shailaja Shenoy, Steven Fernandes, Prakhar Choudhary   +6 more
doaj   +2 more sources

U-Net-Based Models towards Optimal MR Brain Image Segmentation

Diagnostics, 2023
Brain tumor segmentation from MRIs has always been a challenging task for radiologists, therefore, an automatic and generalized system to address this task is needed.
Rammah Yousef, Shakir Khan, Gaurav Gupta, Tamanna Siddiqui, Bader M. Albahlal, Saad Abdullah Alajlan, Mohd Anul Haq   +6 more
doaj   +2 more sources

On the Exploration of Automatic Building Extraction from RGB Satellite Images Using Deep Learning Architectures Based on U-Net

Technologies, 2022
Detecting and localizing buildings is of primary importance in urban planning tasks. Automating the building extraction process, however, has become attractive given the dominance of Convolutional Neural Networks (CNNs) in image classification tasks.
Anastasios Temenos, Nikos Temenos, Anastasios Doulamis, Nikolaos Doulamis   +3 more
doaj   +1 more source

Graph U-Nets

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks ...
Hongyang Gao, Shuiwang Ji
openaire   +6 more sources

Chimeric U-Net – Modifying the standard U-Net towards Explainability

Artificial Intelligence, 2022
Healthcare guided by semantic segmentation has the potential to improve our quality of life through early and accurate disease detection. Convolutional Neural Networks, especially the U-Net-based architectures, are currently the state-of-the-art learningbased segmentation methods and have given unprecedented performances. However, their decision-making
Kenrick Schulze, Felix Peppert, Christof Schütte, Vikram Sunkara   +3 more
openaire   +2 more sources