Filters








9,921 Hits in 4.4 sec

Semantic Binary Segmentation using Convolutional Networks without Decoders [article]

Shubhra Aich, William van der Kamp, Ian Stavness
2018 arXiv   pre-print
In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation.  ...  Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half.  ...  FCN [23] is the earliest example of an encoder-decoder style semantic segmentation network.  ... 
arXiv:1805.00138v2 fatcat:t2kb6yp6dnht5f2r3rffiitkwq

Semantic Binary Segmentation Using Convolutional Networks without Decoders

Shubhra Aich, William van der Kamp, Ian Stavness
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation.  ...  Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half.  ...  FCN [23] is the earliest example of an encoder-decoder style semantic segmentation network.  ... 
doi:10.1109/cvprw.2018.00032 dblp:conf/cvpr/AichKS18 fatcat:45csxdxvgrb4vade2txpaqjiua

Multi-Supervised Encoder-Decoder for Image Forgery Localization

Chunfang Yu, Jizhe Zhou, Qin Li
2021 Electronics  
Unlike many existing solutions, we employ a semantic segmentation network, named Multi-Supervised Encoder–Decoder (MSED), for the detection and localization of forgery images with arbitrary sizes and multiple  ...  types of manipulations without extra pre-training.  ...  CNN-Based Image Semantic Segmentation The Convolutional Neural Network (CNN) is one of the standard algorithms of deep learning.  ... 
doi:10.3390/electronics10182255 fatcat:6wwiaphbcnexrh7hjjwrcqy6nq

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation [article]

Hasib Zunair, A. Ben Hamza
2021 arXiv   pre-print
To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical  ...  The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation.  ...  Then, we introduce an end-to-end depthwise encoder-decoder convolutional network architecture for both binary and multi-class biomedical image segmentation.  ... 
arXiv:2107.12461v1 fatcat:na3jvmftcnb5ph4o35y6v7cr24

Densely Connected Large Kernel Convolutional Network for Semantic Membrane Segmentation in Microscopy Images

Dongnan Liu, Donghao Zhang, Siqi Liu, Yang Song, Haozhe Jia, Dagan Feng, Yong Xia, Weidong Cai
2018 2018 25th IEEE International Conference on Image Processing (ICIP)  
Semantic segmentation of neurons thus becomes an important technique in bioinformatics. Deep learning approaches have shown promising performance in various semantic segmentation problems.  ...  In our work, we propose a network with a ResNet encoder and densely connected decoder with large kernels, and then refinement with simple morphological post-possessing.  ...  Recently, several methods based on deep convolutional neural networks (CNN) have been proposed for semantic segmentation in general imaging.  ... 
doi:10.1109/icip.2018.8451775 dblp:conf/icip/LiuZLSJFXC18 fatcat:y6kl6wcumrf4fapztpgd7ocffe

TernausNetV2: Fully Convolutional Network for Instance Segmentation [article]

Vladimir I. Iglovikov, Selim Seferbekov, Alexander V. Buslaev and Alexey Shvets
2018 arXiv   pre-print
The network has popular encoder-decoder type of architecture with skip connections but has a few essential modifications that allows using for semantic as well as for instance segmentation tasks.  ...  This approach is universal and allows to extend any network that has been successfully applied for semantic segmentation to perform instance segmentation task.  ...  We used a fully convolutional neural network that is traditionally used for semantic segmentation and added additional output that adds instance segmentation functionality.  ... 
arXiv:1806.00844v2 fatcat:qicuxba7irejzlsjwtmn2hgnl4

Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving [article]

Alexander Frickenstein and Manoj Rohit Vemparala and Jakob Mayr and Naveen Shankar Nagaraja and Christian Unger and Federico Tombari and Walter Stechele
2020 arXiv   pre-print
This paper proposes a novel binarized driveable area detection network (binary DAD-Net), which uses only binary weights and activations in the encoder, the bottleneck, and the decoder part.  ...  Along with automatically generated training data, the binary DAD-Net outperforms state-of-the-art semantic segmentation networks on public datasets.  ...  One of the first prominent semantic segmentation models proposed was the Fully Convolutional Network (FCN), is successfully adopted by Shelhamer et al. [7] .  ... 
arXiv:2006.08178v1 fatcat:sb6pmvj6nvd2zdkv32wddxxyb4

D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction

Lichen Zhou, Chuang Zhang, Ming Wu
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
In this paper, we propose a semantic segmentation neural network, named D-LinkNet, which adopts encoderdecoder structure, dilated convolution and pretrained encoder for road extraction task.  ...  Dilation convolution is a powerful tool that can enlarge the receptive field of feature points without reducing the resolution of the feature maps.  ...  Using ImageNet [23] pretrained model to be the encoder of the network is a method widely used in semantic segmentation field [16, 24] .  ... 
doi:10.1109/cvprw.2018.00034 dblp:conf/cvpr/ZhouZW18 fatcat:e5ogzwbtiza37blh4wa5p7akx4

TernausNetV2: Fully Convolutional Network for Instance Segmentation

Vladimir Iglovikov, Selim Seferbekov, Alexander Buslaev, Alexey Shvets
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The network has popular encoderdecoder type of architecture with skip connections but has a few essential modifications that allows using for semantic as well as for instance segmentation tasks.  ...  This approach is universal and allows to extend any network that has been successfully applied for semantic segmentation to perform instance segmentation task.  ...  We used a fully convolutional neural network that is traditionally used for semantic segmentation and added additional output that adds instance segmentation functionality.  ... 
doi:10.1109/cvprw.2018.00042 dblp:conf/cvpr/IglovikovS0S18 fatcat:cnh7qh6mnzfsfleka43ijgxglu

Rethinking Convolutional Semantic Segmentation Learning [article]

Mrinal Haloi
2017 arXiv   pre-print
Deep convolutional semantic segmentation (DCSS) learning doesn't converge to an optimal local minimum with random parameters initializations; a pre-trained model on the same domain becomes necessary to  ...  It addresses many drawbacks with existing deep semantic segmentation learning; the proposed approach simultaneously learn both segmentation and classification; taking away the essential need of the pre-trained  ...  ACKNOWLEDGMENT We would like to thank the data team leads RajaRajalakshmi Kodhandapani and Ophthalmologists of Artelus; who have helped to prepare the segmentation dataset.  ... 
arXiv:1710.07991v1 fatcat:cuseidmqmrbgldy5t2slbldgyy

PaI‐Net: A modified U‐Net of reducing semantic gap for surgical instrument segmentation

Xiaoyan Wang, Luyao Wang, Xingyu Zhong, Cong Bai, Xiaojie Huang, Ruiyi Zhao, Ming Xia
2021 IET Image Processing  
Specially, APM utilizes multi-scale convolution kernels and global average pooling operations to extract semantic information and global context information of different scales, while OFM combines the  ...  feature maps of the decoder part to aggregate the abundant boundary information of shallow layers and the rich semantic information of deep layers together, which achieve a significant improvement in generating  ...  The structure uses a network of convolutional layers entirely to perform the task of semantic segmentation.  ... 
doi:10.1049/ipr2.12283 fatcat:ehoziikcqrgylkba237yh4vbmm

PPANet: Point-Wise Pyramid Attention Network for Semantic Segmentation

Mohammed A. M. Elhassan, YuXuan Chen, Yunyi Chen, Chenxi Huang, Jane Yang, Xingcong Yao, Chenhui Yang, Yinuo Cheng
2021 Wireless Communications and Mobile Computing  
This paper presents a point-wise pyramid attention network, namely, PPANet, which employs an encoder-decoder approach for semantic segmentation.  ...  In recent years, convolutional neural networks (CNNs) have been at the centre of the advances and progress of advanced driver assistance systems and autonomous driving.  ...  Semantic segmentation has been at the centre of this development. There is a significant amount of research using convolution neural network-based segmentation.  ... 
doi:10.1155/2021/5563875 doaj:6555263df5c84f7f988d4053ae8f5c75 fatcat:hsq2tef2mrbllo4o2geksm6ufe

DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation

Hatem Ibrahem, Ahmed Salem, Hyun-Soo Kang
2022 Sensors  
We propose Depth-to-Space Net (DTS-Net), an effective technique for semantic segmentation using the efficient sub-pixel convolutional neural network.  ...  We propose both a deep network, that is, DTS-Net, and a lightweight network, DTS-Net-Lite, for real-time semantic segmentation; these networks employ Xception and MobileNetV2 architectures as the feature  ...  Data Availability Statement: The datasests used in this paper are public datasets.  ... 
doi:10.3390/s22010337 pmid:35009879 pmcid:PMC8749585 fatcat:mvxugub4anbmbcpoybyrmm7dxa

PedNet: A Spatio-Temporal Deep Convolutional Neural Network for Pedestrian Segmentation

Mohib Ullah, Ahmed Mohammed, Faouzi Alaya Cheikh
2018 Journal of Imaging  
Moreover, to combine the low-level features with the high-level semantic information learned by the deeper layers, we used long-skip connections from the encoder to decoder network and concatenate the  ...  The input to the network is a set of three frames and the output is a binary mask of the segmented regions in the middle frame.  ...  [31] introduced a fully convolutional neural network for semantic segmentation.  ... 
doi:10.3390/jimaging4090107 fatcat:mijr5cag25anhefxkthsizeiem

Decoding the Partial Pretrained Networks for Sea-Ice Segmentation of 2021 Gaofen Challenge

Jian Kang, Fengyu Tong, Xiang Ding, Sijiang Li, Ruoxin Zhu, Yan Huang, Yusheng Xu, Ruben Fernandez-Beltran
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this article, we briefly introduce our three strategies of the achievement including: 1) decoding the partial pretrained networks which can simultaneously capture the complex boundaries of sea ices  ...  The main contributions are twofold: 1) an efficient and effective sea-ice segmentation method is proposed and 2) the gradient vanishing problem of binary Dice loss is investigated under some scenarios  ...  Binary Segmentation in RS Differently to semantic segmentation, binary segmentation aims at discriminating one specific land-use or land-cover class from RS images, such as buildings and roads.  ... 
doi:10.1109/jstars.2022.3180558 fatcat:7rrhamig3vcq5ne3q7j7j53aya
« Previous Showing results 1 — 15 out of 9,921 results