A Novel Deep Fully Convolutional Network for PolSAR Image Classification
Remote Sensing, 2018 Polarimetric synthetic aperture radar (PolSAR) image classification has become more and more popular in recent years. As we all know, PolSAR image classification is actually a dense prediction problem.
Yangyang Li +3 more
doaj +4 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 +4 more sources
A novel fully convolutional network for visual saliency prediction [PDF]
PeerJ Computer Science, 2020 A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement.
Bashir Muftah Ghariba +2 more
doaj +3 more sources
Parallel Fully Convolutional Network for Semantic Segmentation [PDF]
IEEE Access, 2021 Fully convolutional networks (FCNs) have been widely applied for dense classification tasks such as semantic segmentation. As a large number of works based on FCNs are proposed, various semantic segmentation models have been improved significantly ...
Jian Ji +5 more
doaj +3 more sources
RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation [PDF]
Frontiers in Neuroscience, 2020 We present a fully convolutional neural network (ConvNet), named RatLesNetv2, for segmenting lesions in rodent magnetic resonance (MR) brain images. RatLesNetv2 architecture resembles an autoencoder and it incorporates residual blocks that facilitate its
Juan Miguel Valverde +7 more
doaj +2 more sources
Background Subtraction Using Multiscale Fully Convolutional Network
IEEE Access, 2018 Background modeling and subtraction based on change detection are the first step in many high-level computer vision applications. Many background subtraction methods have been proposed in the recent past and their efforts mainly focus on two aspects ...
Dongdong Zeng, Ming Zhu
doaj +3 more sources
Fully Convolutional Network for the Semantic Segmentation of Medical Images: A Survey. [PDF]
Diagnostics (Basel), 2022 Huang SY, Hsu WL, Hsu RJ, Liu DW.
europepmc +2 more sources
Fully Convolutional Networks for Panoptic Segmentation [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline.
Yanwei Li +6 more
openaire +4 more sources
Mapping and Discriminating Rural Settlements Using Gaofen-2 Images and a Fully Convolutional Network. [PDF]
Sensors (Basel), 2020 Ye Z +6 more
europepmc +2 more sources
Superpixel Segmentation With Fully Convolutional Networks [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 In computer vision, superpixels have been widely used as an effective way to reduce the number of image primitives for subsequent processing. But only a few attempts have been made to incorporate them into deep neural networks. One main reason is that the standard convolution operation is defined on regular grids and becomes inefficient when applied to
Fengting Yang +3 more
openaire +4 more sources