Evidential fully convolutional network for semantic segmentation [PDF]
Applied intelligence (Boston), 2021 We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation. In the so-called evidential FCN (E-FCN), an encoder-decoder architecture first extracts pixel-wise feature maps ...
Zheng Tong, Philippe Xu, T. Denoeux
semanticscholar +2 more sources
Quantitative reconstruction of defects in multi-layered bonded composites using fully convolutional network-based ultrasonic inversion [PDF]
Journal of Sound and Vibration, 2021 Ultrasonic methods have great potential applications to detect and characterize defects in multi-layered bonded composites. However, it remains challenging to quantitatively reconstruct defects, such as disbonds and kissing bonds, that influence the ...
J. Rao +4 more
semanticscholar +3 more sources
Improved Fully Convolutional Network with Conditional Random Fields for Building Extraction
Remote Sensing, 2018 Building extraction from remotely sensed imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications.
Sanjeevan Shrestha, Leonardo Vanneschi
doaj +2 more sources
An Improved Splicing Localization Method by Fully Convolutional Networks
IEEE Access, 2018 Liu and Pun proposed a method based on fully convolutional network (FCN) and conditional random field (CRF) to locate spliced regions in synthesized images from different source images. However, their work has two drawbacks: 1) FCN often smooths detailed
Beijing Chen +5 more
doaj +2 more sources
Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks
Remote Sensing, 2018 Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world.
Ahram Song +3 more
doaj +2 more sources
Multi-Head Self-Attention-Based Fully Convolutional Network for RUL Prediction of Turbofan Engines
AlgorithmsRemaining useful life (RUL) prediction is widely applied in prognostic and health management (PHM) of turbofan engines. Although some of the existing deep learning-based models for RUL prediction of turbofan engines have achieved satisfactory results ...
Zhaofeng Liu +4 more
doaj +2 more sources
Tire Defect Detection Using Fully Convolutional Network
IEEE Access, 2019 A deep convolutional neural network has recently witnessed rapid progress due to the strong feature learning capability. In this paper, we focus on its application in the industrial field and propose a method based on a fully convolutional network (FCN ...
Ren Wang +3 more
doaj +2 more sources
Sensors, 2019 The visual inspection of massive civil infrastructure is a common trend for maintaining its reliability and structural health. However, this procedure, which uses human inspectors, requires long inspection times and relies on the subjective and empirical
M. M. Manjurul Islam, Jong-Myon Kim
doaj +2 more sources
Insights Into LSTM Fully Convolutional Networks for Time Series Classification
IEEE Access, 2019 Long short-term memory fully convolutional neural networks (LSTM-FCNs) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve the state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (
Fazle Karim +2 more
doaj +3 more sources
Detecting global urban expansion over the last three decades using a fully convolutional network
Environmental Research Letters, 2019 The effective detection of global urban expansion is the basis of understanding urban sustainability. We propose a fully convolutional network (FCN) and employ it to detect global urban expansion from 1992–2016.
Chun-Yang He +5 more
semanticscholar +2 more sources