Internet Archive Scholar
Filters
























3 Hits in 5.3 sec

Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection [article]

Dennis Ulmer, Giovanni Cinà
<span title="2021-06-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (8.6 MB)
https://web.archive.org/web/20210302061507/https://arxiv.org/pdf/2012.05329v3.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/2012.05329v3.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="2021-02-26">2021</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05329v3">arXiv:2012.05329v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vxsk2fhsdfcz5j6isre7yabgpe">fatcat:vxsk2fhsdfcz5j6isre7yabgpe</a> </span>

Other Versions

<span title="2020-12-11">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05329v2">arXiv:2012.05329v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h3uqeaq3fbcynav2as6djrwzqi">fatcat:h3uqeaq3fbcynav2as6djrwzqi</a> </span>
<span title="2020-12-09">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05329v1">arXiv:2012.05329v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n44l6hm5jjfmpecekxf3va2syy">fatcat:n44l6hm5jjfmpecekxf3va2syy</a> </span>
data and on which a model might underperform.  ...  This paper gives a theoretical explanation for said experimental findings and illustrates it on synthetic data.  ...  ACKNOWLEDGEMENTS We would like to thank Mareike Hartmann, Adam Izdebski, Natalie Schluter, Emese Thamó and Christina Winkler for their tremendously helpful feedback on this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05329v4">arXiv:2012.05329v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2o6wmk3hg5h67bcynmlvffcdhq">fatcat:2o6wmk3hg5h67bcynmlvffcdhq</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210302061507/https://arxiv.org/pdf/2012.05329v3.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/34/c6/34c68268957e26ecc10b1c09cb4cf2283a50300f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05329v4" 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

Dennis Ulmer, Giovanni Cinà. "Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection." arXiv (2021)

What classifiers know what they don't? [article]

Mohamed Ishmael Belghazi, David Lopez-Paz
<span title="2021-07-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (243.6 kB)
https://web.archive.org/web/20210719204438/https://arxiv.org/pdf/2107.06217v1.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/2107.06217v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

data.  ...  Despite the importance of equipping classifiers with uncertainty estimates ready for the real world, prior work has focused on small datasets and little or no class discrepancy between training and testing  ...  Know your limits: Monotonicity & softmax make neural classifiers overconfident on ood data. arXiv, 2020. References David Alvarez-Melis and Tommi S Jaakkola.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06217v1">arXiv:2107.06217v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/45mbms4tz5hqbac5al7m6ngwm4">fatcat:45mbms4tz5hqbac5al7m6ngwm4</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/20210719204438/https://arxiv.org/pdf/2107.06217v1.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/f6/28/f6289657f58e2e13a3ccf11a029a15e913ea5d5b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.06217v1" 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

Mohamed Ishmael Belghazi, David Lopez-Paz. "What classifiers know what they don't?." arXiv (2021)

Well-calibrated predictive uncertainty in medical imaging with Bayesian Deep Learning [article]

Max-Heinrich Viktor Laves, University, My
<span title="2021-12-20">2021</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.2 MB)
https://web.archive.org/web/20211225052436/https://www.repo.uni-hannover.de/bitstream/handle/123456789/11679/Laves_Max-Heinrich_Viktor_2021.pdf;jsessionid=8F251A743E655B4FCBC28BE105026F94?sequence=3

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://www.repo.uni-hannover.de/bitstream/handle/123456789/11679/Laves_Max-Heinrich_Viktor_2021.pdf;jsessionid=8F251A743E655B4FCBC28BE105026F94?sequence=3">the original URL</a>. The file type is <code>application/pdf</code>.

These concerns are reinforced by the core problem that this dissertation addresses: the overconfidence of deep models in incorrect predictions. How do we know if we do not know?  ...  The approach achieves state-of-the-art performance on both medical and non-medical classification data sets. Many medic [...]  ...  Introduction Your overconfidence is your weakness.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15488/11588">doi:10.15488/11588</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hkyyhvzumrecxeuar2m6mjyosi">fatcat:hkyyhvzumrecxeuar2m6mjyosi</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic black small" title="ISO Language Code">lang:de</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211225052436/https://www.repo.uni-hannover.de/bitstream/handle/123456789/11679/Laves_Max-Heinrich_Viktor_2021.pdf;jsessionid=8F251A743E655B4FCBC28BE105026F94?sequence=3" 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/d9/80d9463965ae01c630c75adf420fff51330422b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15488/11588"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>
Citation

Max-Heinrich Viktor Laves, University, My. "Well-calibrated predictive uncertainty in medical imaging with Bayesian Deep Learning." (2021)