Filters








2,872 Hits in 3.6 sec

Superpixel Segmentation with Fully Convolutional Networks [article]

Fengting Yang, Qian Sun, Hailin Jin, Zihan Zhou
<span title="2020-03-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Inspired by an initialization strategy commonly adopted by traditional superpixel algorithms, we present a novel method that employs a simple fully convolutional network to predict superpixels on a regular  ...  Based on the predicted superpixels, we further develop a downsampling/upsampling scheme for deep networks with the goal of generating high-resolution outputs for dense prediction tasks.  ...  Conclusion This paper has presented a simple fully convolutional network for superpixel segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12929v1">arXiv:2003.12929v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/muqjv2as3bb3togsae4kowcm4q">fatcat:muqjv2as3bb3togsae4kowcm4q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200407064739/https://arxiv.org/pdf/2003.12929v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12929v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Face Parsing via a Fully-Convolutional Continuous CRF Neural Network [article]

Lei Zhou, Zhi Liu, Xiangjian He
<span title="2017-08-12">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FC-CNN is fully convolutional with high segmentation accuracy.  ...  In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture.  ...  We compare the proposed FC-CNN with a number of recent fully convolutional semantic segmentation methods with competitive performance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.03736v1">arXiv:1708.03736v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mwrcdmwtijcnzmc4mqswzvby2m">fatcat:mwrcdmwtijcnzmc4mqswzvby2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829070003/https://arxiv.org/pdf/1708.03736v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1a/6b/1a6be54aa60f6e348e75b13d4d3335f1faaf6536.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.03736v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Superpixel-based Road Segmentation for Real-time Systems using CNN

Farnoush Zohourian, Borislav Antic, Jan Siegemund, Mirko Meuter, Josef Pauli
<span title="">2018</span> <i title="SCITEPRESS - Science and Technology Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tyl5kfigejfehnouax7r3tii24" style="color: black;">Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications</a> </i> &nbsp;
Convolutional Neural Networks (CNN) contributed considerable improvements for image segmentation tasks in the field of computer vision.  ...  To enable the necessary convolutional operations on the irregular arranged superpixels, we introduce a lattice projection scheme as part of the superpixel creation method, which composes neighbourhood  ...  Our proposed network structure consists of two convolutional layers, two fully connected layers and one drop-out layer with non-linear activation function after each convolutional and fully connected layer  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0006612002570265">doi:10.5220/0006612002570265</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/visapp/ZohourianASMP18.html">dblp:conf/visapp/ZohourianASMP18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xxt4vld7fvcdtk7i2qlq5hcys4">fatcat:xxt4vld7fvcdtk7i2qlq5hcys4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190223162929/http://pdfs.semanticscholar.org/47f8/ba44fde1f8a3a621b20cabb7e84515fb8313.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/47/f8/47f8ba44fde1f8a3a621b20cabb7e84515fb8313.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0006612002570265"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning [article]

Cem Sazara, Mecit Cetin, Khan M. Iftekharuddin
<span title="2019-08-31">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For the flood area segmentation task, we investigated superpixel based methods and Fully Convolutional Neural Network (FCN).  ...  Pre-trained VGG-16 network with logistic regression classifier outperformed all other methods.  ...  We studied superpixel and Fully Convolutional Neural Networks (FCNs) based semantic segmentation methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.00125v1">arXiv:1909.00125v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mj7ilx2m4vbjjc6xx6opfkryz4">fatcat:mj7ilx2m4vbjjc6xx6opfkryz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930195931/https://arxiv.org/ftp/arxiv/papers/1909/1909.00125.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/05/13/05132381df9cf3ce6bc1bac214e9c2e370413ca7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.00125v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Efficient Convolutional Neural Network with Binary Quantization Layer [article]

Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi, Lucio Marcenaro, Carlo Regazzoni
<span title="2016-11-21">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN).  ...  These binary encoding can be embedded into the CNN as an extra layer at the end of the network. This results in real-time segmentation.  ...  Segmentation Network Details: The designed deep-net consist of two major parts; 1) Fully convolutional network: at first we used a pre-trained AlexNet model on ImageNet [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.06764v1">arXiv:1611.06764v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fzpcftcn35hvtit7d4rp5jqhye">fatcat:fzpcftcn35hvtit7d4rp5jqhye</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904011241/https://arxiv.org/pdf/1611.06764v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ad/96/ad969a415f126c8ca6597038c4c1ed8ffff01029.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.06764v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

CNN-aware Binary Map for General Semantic Segmentation [article]

Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi, Mohammad Rastegari, Carlo Regazzoni
<span title="2016-09-29">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper we introduce a novel method for general semantic segmentation that can benefit from general semantics of Convolutional Neural Network (CNN).  ...  These binary encoding can be embedded into the CNN as an extra layer at the end of the network. This results in real-time segmentation.  ...  Segmentation Network Details: The designed deep-net consist of two major parts; 1) Fully convolutional network: As reviewed in 3.1 at first we utilized a pre-trained AlexNet model on ImageNet.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.09220v1">arXiv:1609.09220v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ldskhhnefbypgofiqwuhcjdny">fatcat:6ldskhhnefbypgofiqwuhcjdny</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908223326/https://arxiv.org/pdf/1609.09220v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/b8/4fb82dbd81627f8bafec1f23994c28dc6d100979.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.09220v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Feedforward semantic segmentation with zoom-out features

Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Concatenating these features gives us a 12,416-dim. feature representation per superpixel, which is classified by a neural network with three fully connected layers.  ...  We define a zoom-out level associated with the output of every convolutional layer in the recently proposed 16 layer network, pre-trained on ImageNet classification task [5] .  ...  Concatenating these features gives us a 12,416-dim. feature representation per superpixel, which is classified by a neural network with three fully connected layers.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7298959">doi:10.1109/cvpr.2015.7298959</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/MostajabiYS15.html">dblp:conf/cvpr/MostajabiYS15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4p3dpufshrhixcvug3lu27znfe">fatcat:4p3dpufshrhixcvug3lu27znfe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830044538/http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_005_ext.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3f/16/3f169aa7863a8a6d8367176697bc62ae222e6ac6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7298959"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Two-Branch Convolutional Neural Network Based on Multi-Spectral Entropy Rate Superpixel Segmentation for Hyperspectral Image Classification

Caihong Mu, Zhidong Dong, Yi Liu
<span title="2022-03-24">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
In this paper, a two-branch convolutional neural network based on multi-spectral entropy rate superpixel segmentation (TBN-MERS) is designed for HSI classification.  ...  Convolutional neural networks (CNNs) can extract advanced features of joint spectral–spatial information, which are useful for hyperspectral image (HSI) classification.  ...  We use 2D convolutional layers, 3D convolutional layers, and fully connected layers to build neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs14071569">doi:10.3390/rs14071569</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3wm6qupzmjbqnm7u7h7lnjkmqq">fatcat:3wm6qupzmjbqnm7u7h7lnjkmqq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220620025448/https://mdpi-res.com/d_attachment/remotesensing/remotesensing-14-01569/article_deploy/remotesensing-14-01569-v2.pdf?version=1648172599" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e7/34/e7345c49e524ead08741eb30e5cc94e1eaaf444b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs14071569"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

CRF learning with CNN features for hyperspectral image segmentation

Fahim Irfan Alam, Jun Zhou, Alan Wee-Chung Liew, Xiuping Jia
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6i67v2zuujhfvocqaapmnsoifm" style="color: black;">2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)</a> </i> &nbsp;
After a hyperspectral image is over-segmented into superpixels, a deep Convolutional Neural Network (CNN) is used to perform superpixel-level labelling.  ...  A mean-field approximation algorithm for CRF inference is used and formulated with Gaussian pairwise potentials as Recurrent Neural Network.  ...  In our work, the CNN contains eight layers with weights; the first five are convolutional and the remaining three are fully-connected.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/igarss.2016.7730798">doi:10.1109/igarss.2016.7730798</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/igarss/AlamZLJ16.html">dblp:conf/igarss/AlamZLJ16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ga5vzryxcrch5drbdr27ktseqy">fatcat:ga5vzryxcrch5drbdr27ktseqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20181104094943/https://research-repository.griffith.edu.au/bitstream/handle/10072/339311/AlamPUB1959.pdf;jsessionid=4AD3096D1B256915F2E015FFF6A14E2A?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/80/1f/801f33a6c58b30800e8d8382efacba10bd9487d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/igarss.2016.7730798"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields

Fayao Liu, Chunhua Shen, Guosheng Lin, Ian Reid
<span title="2016-10-01">2016</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
We then further propose an equally effective model based on fully convolutional networks and a novel superpixel pooling method, which is ∼ 10 times faster, to speedup the patch-wise convolutions in the  ...  With this more efficient model, we are able to design deeper networks to pursue better performance.  ...  Therefore, we here propose an improved model, which we term as DCNF-FCSP (DCNF with Fully Convolutional networks and Superpixel Pooling), based on fully convolutional networks and a novel superpixel pooling  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2015.2505283">doi:10.1109/tpami.2015.2505283</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26660697">pmid:26660697</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iyrvuo5lazaorbgbfsyzfpx4zm">fatcat:iyrvuo5lazaorbgbfsyzfpx4zm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930071227/https://arxiv.org/pdf/1502.07411v5.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4f/34/4f3454965d0b3b68bdde285f618dfd66af6a3369.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2015.2505283"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Deep convolutional networks for pancreas segmentation in CT imaging

Holger R. Roth, Amal Farag, Le Lu, Evrim B. Turkbey, Ronald M. Summers, Sébastien Ourselin, Martin A. Styner
<span title="2015-03-20">2015</span> <i title="SPIE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ha25cznnjncxtjoykhsg6fz5ly" style="color: black;">Medical Imaging 2015: Image Processing</a> </i> &nbsp;
We present a fully-automated bottom-up method for pancreas segmentation in computed tomography (CT) images of the abdomen.  ...  networks (ConvNets) to succeed in image classification tasks.  ...  Superpixels with high pancreas probability after random forest (RF) classification (b) are retained at cost of over-segmentation to serve as input to a convolutional network (ConvNet) classification (c  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.2081420">doi:10.1117/12.2081420</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/miip/RothFLTS15.html">dblp:conf/miip/RothFLTS15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3lmtbq67cvhtzf5wdx3wfliy7i">fatcat:3lmtbq67cvhtzf5wdx3wfliy7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201126195744/https://arxiv.org/pdf/1504.03967v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/54/11/54114a83436ecf953f7bf9f27277aa982a2c8e35.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.2081420"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

DEL: Deep Embedding Learning for Efficient Image Segmentation

Yun Liu, Peng-Tao Jiang, Vahan Petrosyan, Shi-Jie Li, Jiawang Bian, Le Zhang, Ming-Ming Cheng
<span title="">2018</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
Starting with the SLIC superpixels, we train a fully convolutional network to learn the feature embedding space for each superpixel.  ...  With the deep similarities, we can directly merge the superpixels into large segments.  ...  Since deep features can represent much richer information than hand-crafted features, we train a fully convolutional network to learn the deep feature embedding space that encodes the deep representation  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/120">doi:10.24963/ijcai.2018/120</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/LiuJPLBZC18.html">dblp:conf/ijcai/LiuJPLBZC18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pkzqrla3i5gvlgw7mdhonzrblu">fatcat:pkzqrla3i5gvlgw7mdhonzrblu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190427124437/https://www.ijcai.org/proceedings/2018/0120.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/aa/dcaa524f5b7575b50bcf7c6a3c3ce52e74ab65cd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/120"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Attention Graph Convolution Network for Image Segmentation in Big SAR Imagery Data

Fei Ma, Fei Gao, Jinping Sun, Huiyu Zhou, Amir Hussain
<span title="2019-11-04">2019</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
Here, we propose a novel Attention Graph Convolution Network (AGCN) to perform superpixel-wise segmentation in big SAR imagery data.  ...  However, the over-segmented images become non-Euclidean structure data that traditional deep Convolutional Neural Networks (CNN) cannot directly process.  ...  The CNN network consists of several convolutional layers, fully connected layers, and a SoftMax layer, which are updated with a random gradient descent method.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs11212586">doi:10.3390/rs11212586</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mrxz6cl7wvefjep5a4l4zioiw4">fatcat:mrxz6cl7wvefjep5a4l4zioiw4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200208160604/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-11-02586/article_deploy/remotesensing-11-02586.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4e/9f/4e9f708cc9908ae419a6ba24994fd7be85ec1db2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs11212586"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

A Correlation Context-Driven Method for Sea Fog Detection in Meteorological Satellite Imagery

Yixiang Huang, Ming Wu, Jun Guo, Chuang Zhang, Mengqiu Xu
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q2cxanfrsvclzbz73u2mnqrxru" style="color: black;">IEEE Geoscience and Remote Sensing Letters</a> </i> &nbsp;
of a two-stage superpixel-based fully convolutional network (SFCNet), named SFCNet.  ...  A fully connected Conditional Random Field (CRF) is utilized to model the dependencies between pixels.  ...  In Section II-B, we introduce the second part, its goal is to achieve superpixel-based sea fog detection by superpixelbased fully convolutional network (SFCNet), and utilize a fully connected CRF to get  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/lgrs.2021.3095731">doi:10.1109/lgrs.2021.3095731</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tx5yup7ajrfxdau277tedyojhq">fatcat:tx5yup7ajrfxdau277tedyojhq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210728022240/https://ieeexplore.ieee.org/ielx7/8859/4357975/09494720.pdf?tp=&amp;arnumber=9494720&amp;isnumber=4357975&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3e/59/3e5989bc4768fd546a4729f259de8581c0ed2e19.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/lgrs.2021.3095731"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Non-flat Ground Detection Based on A Local Descriptor [article]

Kangru Wang, Lei Qu, Lili Chen, Yuzhang Gu, DongChen zhu, Xiaolin Zhang
<span title="2018-06-06">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
And we also present a complete framework to detect the ground plane regions base on the disparity texture image with convolutional neural network architecture.  ...  In this paper, we propose a framework of the ground plane detection with stereo vision.  ...  Convolutional Network (FCNs) by converting the fully connected layers into convolutional layers.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.08436v9">arXiv:1609.08436v9</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hznxjgirdjbejf2hq5uis5ttee">fatcat:hznxjgirdjbejf2hq5uis5ttee</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200925045240/https://arxiv.org/pdf/1609.08436v9.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c2/e8/c2e8899f80516aa2ea42d615b1a29d274ace318a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.08436v9" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,872 results