Internet Archive Scholar
Filters
























8,631 Hits in 6.2 sec

Evaluating Bayesian Deep Learning Methods for Semantic Segmentation [article]

Jishnu Mukhoti, Yarin Gal
<span title="2019-03-23">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (5.1 MB)
https://web.archive.org/web/20191017192913/https://arxiv.org/pdf/1811.12709v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1811.12709v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2018-11-30">2018</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12709v1">arXiv:1811.12709v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2wjugpomczgqxjzpzlamw2pboy">fatcat:2wjugpomczgqxjzpzlamw2pboy</a> </span>
Deep learning has been revolutionary for computer vision and semantic segmentation in particular, with Bayesian Deep Learning (BDL) used to obtain uncertainty maps from deep models when predicting semantic  ...  This information is critical when using semantic segmentation for autonomous driving for example. Standard semantic segmentation systems have well-established evaluation metrics.  ...  Related Work In this section, we discuss some of the recent works on semantic segmentation as well as those on approximate inference in Bayesian Deep Learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12709v2">arXiv:1811.12709v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lqtc6w3n6jehtcma4m3athavwu">fatcat:lqtc6w3n6jehtcma4m3athavwu</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017192913/https://arxiv.org/pdf/1811.12709v1.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/52/87/5287f4698ab988231b46de2fb009127a613debed.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12709v2" 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>
Citation

Jishnu Mukhoti, Yarin Gal. "Evaluating Bayesian Deep Learning Methods for Semantic Segmentation." arXiv (2019)

Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images

Clément Dechesne, Pierre Lassalle, Sébastien Lefèvre
<span title="2021-09-25">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (61.7 MB)
https://web.archive.org/web/20210929132519/https://mdpi-res.com/d_attachment/remotesensing/remotesensing-13-03836/article_deploy/remotesensing-13-03836-v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://mdpi-res.com/d_attachment/remotesensing/remotesensing-13-03836/article_deploy/remotesensing-13-03836-v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To do this, we relied on a Bayesian deep learning method, based on Monte Carlo Dropout, which allows us to derive uncertainty metrics along with the semantic segmentation.  ...  In recent years, numerous deep learning techniques have been proposed to tackle the semantic segmentation of aerial and satellite images, increase trust in the leaderboards of main scientific contests  ...  Method Traditional Deep Learning methods are very efficient for semantic segmentation [7] [8] [9] [10] [11] . However, such methods are prone to produce over-confident decisions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13193836">doi:10.3390/rs13193836</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z5qicf43abd6zda5oiesgfql4i">fatcat:z5qicf43abd6zda5oiesgfql4i</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span> <span class="ui label basic orange small" title="Szcezepanski OA Journal List">Szczepanski</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210929132519/https://mdpi-res.com/d_attachment/remotesensing/remotesensing-13-03836/article_deploy/remotesensing-13-03836-v2.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/f9/c9/f9c97754e6203bb6406a2af376f4ce3d37a507eb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13193836"> <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>
Citation

Clément Dechesne, Pierre Lassalle, Sébastien Lefèvre. "Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images." Remote Sensing 13.19 (2021) 3836

Calibrated Bagging Deep Learning for Image Semantic Segmentation: A Case Study on COVID-19 Chest X-ray Image [article]

Lucy Nwosu, Xiangfang Li, Lijun Qian, Seungchan Kim, Xishuang Dong
<span title="2022-05-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20220605173359/https://arxiv.org/pdf/2206.00002v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2206.00002v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty  ...  However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated  ...  RELATED WORK This paper aims to build a novel bagging learning method to implement COVID-19 semantic segmentation through combining bagging deep learning and model calibration.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00002v1">arXiv:2206.00002v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4rsjpmosxfgelngkpkkxdnvwde">fatcat:4rsjpmosxfgelngkpkkxdnvwde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220605173359/https://arxiv.org/pdf/2206.00002v1.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/f9/0d/f90d6424aa7ee1323f546053251e60aa44c9a5a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.00002v1" 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>
Citation

Lucy Nwosu, Xiangfang Li, Lijun Qian, Seungchan Kim, Xishuang Dong. "Calibrated Bagging Deep Learning for Image Semantic Segmentation: A Case Study on COVID-19 Chest X-ray Image." arXiv (2022)

Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras [article]

Lingni Ma and Jörg Stückler and Christian Kerl and Daniel Cremers
<span title="2017-12-04">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.7 MB)
https://web.archive.org/web/20200827043042/https://arxiv.org/pdf/1703.08866v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1703.08866v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2017-03-26">2017</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.08866v1">arXiv:1703.08866v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ic6n6phmpfcdbph6f36x2nkyqu">fatcat:ic6n6phmpfcdbph6f36x2nkyqu</a> </span>
We base our network architecture on a recent single-view deep learning approach to RGB and depth fusion for semantic object-class segmentation and enhance it with multi-scale loss minimization.  ...  In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning.  ...  In this paper, we propose a novel deep learning approach for semantic segmentation of RGB-D images with multi-view context.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.08866v2">arXiv:1703.08866v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ymfotnytyfacfaxzifd2xnaoce">fatcat:ymfotnytyfacfaxzifd2xnaoce</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827043042/https://arxiv.org/pdf/1703.08866v2.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/49/b6/49b65df7c7fbd0ab44b0c96881b8a9f03f751e79.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.08866v2" 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>
Citation

Lingni Ma and Jörg Stückler and Christian Kerl and Daniel Cremers. "Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras." arXiv (2017)

Semantic Grid Estimation with a Hybrid Bayesian and Deep Neural Network Approach

Ozgur Erkent, Christian Wolf, Christian Laugier, David Sierra Gonzalez, Victor Romero Cano
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dmucnarmarh2fj6syg5jyqs7ny" style="color: black;">2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.6 MB)
https://web.archive.org/web/20200509114708/https://hal.inria.fr/hal-01881377/file/Erkent-2018-IROS.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://hal.inria.fr/hal-01881377/file/Erkent-2018-IROS.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We propose a hybrid approach, which combines the advantages of two different methodologies: we use Deep Learning to perform semantic segmentation on monocular RGB images with supervised learning from labeled  ...  We combine these segmentations with occupancy grids calculated from LIDAR data using a generative Bayesian particle filter.  ...  ACKNOWLEDGEMENT We thank Nicolas Vignard, Jean-Alix David and Jérôme Lussereau for their assistance with the experimental vehicle during the data collection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iros.2018.8593434">doi:10.1109/iros.2018.8593434</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iros/Erkent0LGR18.html">dblp:conf/iros/Erkent0LGR18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kyiqvdp63rhcppje5nifxs2vj4">fatcat:kyiqvdp63rhcppje5nifxs2vj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200509114708/https://hal.inria.fr/hal-01881377/file/Erkent-2018-IROS.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/61/c7/61c7b460d7477d15a7becf09d4aeacdb0d66c34d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iros.2018.8593434"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
Citation

Ozgur Erkent, Christian Wolf, Christian Laugier, David Sierra Gonzalez, Victor Romero Cano. "Semantic Grid Estimation with a Hybrid Bayesian and Deep Neural Network Approach." 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2018) 888-895

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding [article]

Alex Kendall and Vijay Badrinarayanan and Roberto Cipolla
<span title="2016-10-10">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.0 MB)
https://web.archive.org/web/20200929203704/https://arxiv.org/pdf/1511.02680v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1511.02680v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2015-11-09">2015</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.02680v1">arXiv:1511.02680v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dpnoxekxejdf3nlcwqhwluou7a">fatcat:dpnoxekxejdf3nlcwqhwluou7a</a> </span>
We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet.  ...  Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.  ...  Real Time Performance Conclusions We have presented Bayesian SegNet, the first probabilistic framework for semantic segmentation using deep learning, which outputs a measure of model uncertainty for  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.02680v2">arXiv:1511.02680v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2rc2pxlzm5ddlkksy7cmyhfoam">fatcat:2rc2pxlzm5ddlkksy7cmyhfoam</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929203704/https://arxiv.org/pdf/1511.02680v2.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/21/53/2153fb8ba5b10961da93ba5ece69114862e0fe56.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.02680v2" 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>
Citation

Alex Kendall and Vijay Badrinarayanan and Roberto Cipolla. "Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding." arXiv (2016)

Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds [article]

Swaroop Bhandary K and Nico Hochgeschwender and Paul Plöger and Frank Kirchner and Matias Valdenegro-Toro
<span title="2020-07-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (8.6 MB)
https://web.archive.org/web/20200710064011/https://arxiv.org/pdf/2007.01787v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2007.01787v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Bayesian methods for UQ have been extensively studied for Deep Learning models applied on images but have been less explored for 3D modalities such as point clouds often used for Robots and Autonomous  ...  In this work, we evaluate three uncertainty quantification methods namely Deep Ensembles, MC-Dropout and MC-DropConnect on the DarkNet21Seg 3D semantic segmentation model and comprehensively analyze the  ...  To the best of our knowledge, most methods for semantic segmentation of 3D point clouds do not consider uncertainty, which is particularly important for the safe use of learned models, in particular regarding  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01787v1">arXiv:2007.01787v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d3mcwhrkabhflelgq5a4d54s5y">fatcat:d3mcwhrkabhflelgq5a4d54s5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710064011/https://arxiv.org/pdf/2007.01787v1.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/2007.01787v1" 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>
Citation

Swaroop Bhandary K and Nico Hochgeschwender and Paul Plöger and Frank Kirchner and Matias Valdenegro-Toro. "Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds." arXiv (2020)

Informative Path Planning for Active Learning in Aerial Semantic Mapping [article]

Julius Rückin, Liren Jin, Federico Magistri, Cyrill Stachniss, Marija Popović
<span title="2022-03-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (11.4 MB)
https://web.archive.org/web/20220307190117/https://arxiv.org/pdf/2203.01652v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2203.01652v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

However, supervised deep learning models for segmentation rely on large amounts of high-quality labelled data, which is labour-intensive and time-consuming to generate.  ...  We exploit a Bayesian approach to estimate model uncertainty in semantic segmentation. During a mission, the semantic predictions and model uncertainty are used as input for terrain mapping.  ...  ACKNOWLEDGEMENT We would like to thank Matteo Sodano and Tiziano Guadagnino for help with our experiments and proofreading.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.01652v1">arXiv:2203.01652v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7cfx3v4dazhydbaz2rhcx62eqm">fatcat:7cfx3v4dazhydbaz2rhcx62eqm</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220307190117/https://arxiv.org/pdf/2203.01652v1.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/f6/5e/f65ebea0fefe794cc31f05e1c191cb8a33c2a449.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.01652v1" 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>
Citation

Julius Rückin, Liren Jin, Federico Magistri, Cyrill Stachniss, Marija Popović. "Informative Path Planning for Active Learning in Aerial Semantic Mapping." arXiv (2022)

Semantic Grid Estimation with Occupancy Grids and Semantic Segmentation Networks

Ozgur Erkent, Christian Wolf, Christian Laugier
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ivv5w2wonvgzdfvpd7q7w4wksm" style="color: black;">2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200509083911/https://hal.inria.fr/hal-01933939/file/manuscript.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://hal.inria.fr/hal-01933939/file/manuscript.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We propose a method to estimate the semantic grid for an autonomous vehicle.  ...  Finally, we test our method on two datasets and compare different architecture types for semantic segmentation. We perform the experiments on KITTI dataset and Inria-Chroma dataset.  ...  We thank Jean-Alix David and Jérôme Lussereau for their assistance with data collection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icarcv.2018.8581180">doi:10.1109/icarcv.2018.8581180</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icarcv/ErkentWL18.html">dblp:conf/icarcv/ErkentWL18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qfborz5g35ewlemfiswszwl474">fatcat:qfborz5g35ewlemfiswszwl474</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200509083911/https://hal.inria.fr/hal-01933939/file/manuscript.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/80/3a/803ae8372de779c328cfbc93d862ef58d67e33c1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icarcv.2018.8581180"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
Citation

Ozgur Erkent, Christian Wolf, Christian Laugier. "Semantic Grid Estimation with Occupancy Grids and Semantic Segmentation Networks." 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) (2018) 1051-1056

Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning [article]

Sora Iwamoto, Bisser Raytchev, Toru Tamaki, Kazufumi Kaneda
<span title="2021-08-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (29.4 MB)
https://web.archive.org/web/20210831013104/https://arxiv.org/pdf/2108.11693v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2108.11693v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper we propose a novel method which leverages the uncertainty measures provided by Bayesian deep networks through curriculum learning so that the uncertainty estimates are fed back to the system  ...  We show in the concrete setting of a semantic segmentation task (iPS cell colony segmentation) that the proposed system is able to increase significantly the reliability of the model.  ...  We extract sub-images of size d × d pixels from the large image, and these are sent to a Bayesian U-Net for learning the segmentation end-to-end, using ground truth segmentation map images provided by  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.11693v1">arXiv:2108.11693v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wlgbzi57xjafhhh7rocwgqilsi">fatcat:wlgbzi57xjafhhh7rocwgqilsi</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210831013104/https://arxiv.org/pdf/2108.11693v1.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/b3/be/b3be8984fafd442260891bd9eb8bdafd644393d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.11693v1" 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>
Citation

Sora Iwamoto, Bisser Raytchev, Toru Tamaki, Kazufumi Kaneda. "Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning." arXiv (2021)

End-to-End Learning of Semantic Grid Estimation Deep Neural Network with Occupancy Grids

Ozgur Erkent, Christian Wolf, Christian Laugier
<span title="2019-05-03">2019</span> <i title="World Scientific Pub Co Pte Lt"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4rjrqivihvdrrpd7k3pnt72amy" style="color: black;">Unmanned Systems</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.1 MB)
https://web.archive.org/web/20200313071954/https://hal.archives-ouvertes.fr/hal-02302533/document

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://hal.archives-ouvertes.fr/hal-02302533/document">the original URL</a>. The file type is <code>application/pdf</code>.

It consists of an integration of an occupancy grid, which computes the grid states with a Bayesian filter approach, and semantic segmentation information from monocular RGB images, which is obtained with  ...  The proposed method is tested in various datasets (KITTI dataset, Inria-Chroma dataset and SYNTHIA) and different deep neural network architectures are compared.  ...  We thank Jean-Alix David and Jérôme Lussereau for their assistance with data collection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1142/s2301385019410036">doi:10.1142/s2301385019410036</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/egfnhvlqgfh7dddxtfydtvsnxy">fatcat:egfnhvlqgfh7dddxtfydtvsnxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200313071954/https://hal.archives-ouvertes.fr/hal-02302533/document" 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/02/62/026232792100191ed2ada3e4df35394a7dc89880.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1142/s2301385019410036"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> worldscientific.com </button> </a>
Citation

Ozgur Erkent, Christian Wolf, Christian Laugier. "End-to-End Learning of Semantic Grid Estimation Deep Neural Network with Occupancy Grids." Unmanned Systems 07.03 (2019)

Multi-Task Learning for Scalable and Dense Multi-Layer Bayesian Map Inference [article]

Lu Gan, Youngji Kim, Jessy W. Grizzle, Jeffrey M. Walls, Ayoung Kim, Ryan M. Eustice, Maani Ghaffari
<span title="2021-06-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (35.4 MB)
https://web.archive.org/web/20210701075215/https://arxiv.org/pdf/2106.14986v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2106.14986v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To this end, we design a multi-task deep neural network with attention mechanisms as our front-end to provide multiple observations for multiple map layers simultaneously.  ...  The proposed framework goes beyond modern metric-semantic maps to provide even richer environmental information for robots in a single mapping formalism while exploiting existing inter-layer correlations  ...  TABLE I ABLATION I STUDY OF DEEP MULTI-TASK LEARNING NETWORK FOR SEMANTIC AND TRAVERSABILITY SEGMENTATION.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14986v1">arXiv:2106.14986v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/46cq2tsyvfgy7drac2aqi2awwq">fatcat:46cq2tsyvfgy7drac2aqi2awwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210701075215/https://arxiv.org/pdf/2106.14986v1.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/c8/1e/c81e57a0e233c14f290d27e45865b46435e73739.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14986v1" 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>
Citation

Lu Gan, Youngji Kim, Jessy W. Grizzle, Jeffrey M. Walls, Ayoung Kim, Ryan M. Eustice, Maani Ghaffari. "Multi-Task Learning for Scalable and Dense Multi-Layer Bayesian Map Inference." arXiv (2021)

Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning [article]

Suman Sedai, Bhavna Antony, Dwarikanath Mahapatra, Rahil Garnavi
<span title="2018-09-12">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.4 MB)
https://web.archive.org/web/20191022064509/https://arxiv.org/pdf/1809.04282v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1809.04282v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper, we propose a method for retinal layer segmentation and quantification of uncertainty based on Bayesian deep learning.  ...  Our method not only performs end-to-end segmentation of retinal layers, but also gives the pixel wise uncertainty measure of the segmentation output.  ...  Conclusion In this paper, we proposed a Bayesian deep learning based method for retinal layer segmentation in OCT images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.04282v1">arXiv:1809.04282v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yem46egk7bbgtf7bv23xanbzxi">fatcat:yem46egk7bbgtf7bv23xanbzxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022064509/https://arxiv.org/pdf/1809.04282v1.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/ed/db/eddbe71269fedb25f731810c8a19d6412528e8c8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.04282v1" 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>
Citation

Suman Sedai, Bhavna Antony, Dwarikanath Mahapatra, Rahil Garnavi. "Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning." arXiv (2018)

Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning

Rowan McAllister, Yarin Gal, Alex Kendall, Mark van der Wilk, Amar Shah, Roberto Cipolla, Adrian Weller
<span title="">2017</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-Sixth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.4 MB)
https://web.archive.org/web/20190228121723/http://pdfs.semanticscholar.org/91d3/28311d63f7ad64abf03101f3b47c376581d5.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="http://pdfs.semanticscholar.org/91d3/28311d63f7ad64abf03101f3b47c376581d5.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We highlight the need for concrete evaluation metrics, propose example problems, and highlight possible solutions.  ...  Compliance refers to maintaining some control for the passenger. We discuss open challenges for research within these themes.  ...  Figure 2 :Figure 3 : 23 Bayesian deep learning for semantic segmentation. Typically, deep learning models make predictions (b) without considering the uncertainty (c).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2017/661">doi:10.24963/ijcai.2017/661</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/McAllisterGKWSC17.html">dblp:conf/ijcai/McAllisterGKWSC17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c3rj5ikybbgvrea6zl4niklxcq">fatcat:c3rj5ikybbgvrea6zl4niklxcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190228121723/http://pdfs.semanticscholar.org/91d3/28311d63f7ad64abf03101f3b47c376581d5.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/91/d3/91d328311d63f7ad64abf03101f3b47c376581d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2017/661"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Rowan McAllister, Yarin Gal, Alex Kendall, Mark van der Wilk, Amar Shah, Roberto Cipolla, Adrian Weller. "Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning." Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (2017) 4745-4753

Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing [article]

Kento Tomita and Katherine A. Skinner and Koki Ho
<span title="2022-03-18">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.1 MB)
https://web.archive.org/web/20220519092455/https://arxiv.org/pdf/2102.10545v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2102.10545v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-02-21">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.10545v1">arXiv:2102.10545v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tptcvutrknas5pt4grrlwrueme">fatcat:tptcvutrknas5pt4grrlwrueme</a> </span>
In response to these limitations, this paper proposes an application of the Bayesian deep-learning segmentation method for hazard detection.  ...  The developed approach enables reliable, safe landing site detection by: (i) generating simultaneously a safety prediction map and its uncertainty map via Bayesian deep learning and semantic segmentation  ...  Bayesian Deep Learning for Semantic Segmentation Figure 2 shows the network architecture used for the semantic segmentation stage, which is based on Bayesian SegNet [34] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.10545v2">arXiv:2102.10545v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fbgg4zwn5jduvlxwsdlzbxyroa">fatcat:fbgg4zwn5jduvlxwsdlzbxyroa</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220519092455/https://arxiv.org/pdf/2102.10545v2.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/5f/fd/5ffd926f42e49969aba17c9803d2229f88d84f11.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.10545v2" 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>
Citation

Kento Tomita and Katherine A. Skinner and Koki Ho. "Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing." arXiv (2022)

&laquo; Previous Showing results 1 &mdash; 15 out of 8,631 results