Results 21 to 30 of about 369,316 (285)

Learning Rigid Image Registration - Utilizing Convolutional Neural Networks for Medical Image Registration [PDF]

, 2018
Many traditional computer vision tasks, such as segmentation, have seen large step-changes in accuracy and/or speed with the application of Convolutional Neural Networks (CNNs).
Goatman, K.A., Siebert, J.P., Sloan, J.M.   +2 more
core   +1 more source

Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces [PDF]

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
We formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions. The energy is formulated by integrating a continuum of scales from a scale space computed from the heat equation within regions.
Naeemullah Khan, Byung-Woo Hong, Anthony J. Yezzi, Ganesh Sundaramoorthi   +3 more
openaire   +1 more source

MGVSS-UNet: A Novel U-Net Architecture Integrating Multi-Scale Global Visual State Space for Medical Image Segmentation

IEEE Access
Medical image segmentation plays an essential role in computer-aided diagnosis, supports physicians with fast and accurate information to make timely treatment decisions.
Yu Liu, Yanping Chen, Yang Yu
doaj   +1 more source

An Alarm System For Segmentation Algorithm Based On Shape Model

, 2019
It is usually hard for a learning system to predict correctly on rare events that never occur in the training data, and there is no exception for segmentation algorithms. Meanwhile, manual inspection of each case to locate the failures becomes infeasible
Liu, Fengze, Xia, Yingda, Xu, Daguang, Yang, Dong, Yuille, Alan   +4 more
core   +1 more source

NCLG-UNet: A Lightweight U-Net Based on Non-Causal State Space Duality and Laplacian Guidance for Medical Image Segmentation

IEEE Access
Medical image segmentation requires accurate lesion boundary delineation under complex structural variations and interference conditions. However, lightweight models are constrained by their limited parameter capacity and computational budgets, making it
Siyi Li, Gaocai Wang, Yiwen Li
doaj   +1 more source

Attention Guided Encoder-Decoder Network With Multi-Scale Context Aggregation for Land Cover Segmentation

IEEE Access, 2020
Land cover segmentation is an important and challenging task in the field of remote sensing. Even though convolutional neural networks (CNNs) provide great support for semantic segmentation, standard models are still difficult to capture global ...
Shuyang Wang, Xiaodong Mu, Dongfang Yang, Hao He, Peng Zhao   +4 more
doaj   +1 more source

The Empirical Watershed Wavelet

Journal of Imaging, 2020
The empirical wavelet transform is an adaptive multi-resolution analysis tool based on the idea of building filters on a data-driven partition of the Fourier domain.
Basile Hurat, Zariluz Alvarado, Jérôme Gilles   +2 more
doaj   +1 more source

SASO: Joint 3D semantic‐instance segmentation via multi‐scale semantic association and salient point clustering optimization

IET Computer Vision, 2021
Jointly performing semantic and instance segmentation of 3D point cloud remains a challenging task. In this work, a novel framework called joint 3D semantic‐instance segmentation via multi‐scale Semantic Association and Salient point clustering ...
Jingang Tan, Lili Chen, Kangru Wang, Jiamao Li, Xiaolin Zhang   +4 more
doaj   +1 more source

SBNet: Sparse Blocks Network for Fast Inference

, 2018
Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications.
Pokrovsky, Andrei, Ren, Mengye, Urtasun, Raquel, Yang, Bin   +3 more
core   +1 more source

Coarse-to-Fine Segmentation With Shape-Tailored Scale Spaces

CoRR, 2016
We formulate a general energy and method for segmentation that is designed to have preference for segmenting the coarse structure over the fine structure of the data, without smoothing across boundaries of regions. The energy is formulated by considering data terms at a continuum of scales from the scale space computed from the Heat Equation within ...
Ganesh Sundaramoorthi, Naeemullah Khan, Byung-Woo Hong   +2 more
openaire   +2 more sources