Filters








910,030 Hits in 5.5 sec

Image-free single-pixel segmentation [article]

Haiyan Liu, Liheng Bian, Jun Zhang
<span title="2021-08-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The illumination patterns are optimized together with the subsequent reconstruction neural network, which directly infers segmentation maps from the single-pixel measurements.  ...  The technique combines structured illumination and single-pixel detection together, to efficiently samples and multiplexes scene's segmentation information into compressed one-dimensional measurements.  ...  The second part is a decoder module that infers segmentation information from the non-visual measurements.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10617v1">arXiv:2108.10617v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3fahwfunzfdije2bgeecypvami">fatcat:3fahwfunzfdije2bgeecypvami</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210829184755/https://arxiv.org/pdf/2108.10617v1.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/ea/b3/eab3bae2d97bdb14e4f68022f9802b3aef1c3e9c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10617v1" 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>

Machine Learning Based Precision Orientation and Strain Mapping from 4D Diffraction Datasets

Renliang Yuan, Jiong Zhang, Lingfeng He, Jian-Min Zuo
<span title="2021-07-30">2021</span> <i title="Cambridge University Press (CUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p62srgk5yvb2lpsg64xdrhwdyu" style="color: black;">Microscopy and Microanalysis</a> </i> &nbsp;
The advantage of having a 4D-DD over the traditional 2D imaging techniques comes from the rich information captured in diffraction patterns, which can be related to the sample structure, electric and magnetic  ...  Now, the large data size also brings new challenges to the 4D-DD analysis. Faster and better ways to extract information from 4D-DDs are both needed.  ...  The advantage of having a 4D-DD over the traditional 2D imaging techniques comes from the rich information captured in diffraction patterns, which can be related to the sample structure, electric and magnetic  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1017/s1431927621004785">doi:10.1017/s1431927621004785</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r7bntywmr5flvimegyhzohzkf4">fatcat:r7bntywmr5flvimegyhzohzkf4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210803181423/https://www.cambridge.org/core/services/aop-cambridge-core/content/view/0E883D71D6208F78ED035AD5D5422503/S1431927621004785a.pdf/div-class-title-machine-learning-based-precision-orientation-and-strain-mapping-from-4d-diffraction-datasets-div.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/d2/8c/d28c0d7c9b256c7593efd15e54bb1af33b4b221d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1017/s1431927621004785"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> cambridge.org </button> </a>

Network analysis reveals multiscale controls on streamwater chemistry

K. J. McGuire, C. E. Torgersen, G. E. Likens, D. C. Buso, W. H. Lowe, S. W. Bailey
<span title="2014-04-21">2014</span> <i title="Proceedings of the National Academy of Sciences"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nvtuoas5pbdsllkntnhizy4f4q" style="color: black;">Proceedings of the National Academy of Sciences of the United States of America</a> </i> &nbsp;
Therefore, both Euclidean and flow-unconnected network relationships provide information on how the landscape influences patterns of streamwater chemistry within a single catchment/network, whereas a flow-connected  ...  Quantifying these pattern-process links is largely a problem of scale.  ...  A subset of 664 from the total of 761 samples was selected for network analysis based on an assessment of hydrography and the ability to delineate catchment areas by using a geographical information system  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1073/pnas.1404820111">doi:10.1073/pnas.1404820111</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24753575">pmid:24753575</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4024884/">pmcid:PMC4024884</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vgm4qou7sraixoj23xaqjkpfie">fatcat:vgm4qou7sraixoj23xaqjkpfie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811194448/http://faculty.washington.edu/cet6/pub/McGuire_etal_2014.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/fd/0b/fd0be6f0b2c289fd596c72e95524115405ad050c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1073/pnas.1404820111"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4024884" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Non-imaging single-pixel sensing with optimized binary modulation [article]

Hao Fu, Liheng Bian, Jun Zhang
<span title="2019-09-27">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this letter, we propose single-pixel sensing (SPS) that performs high-level sensing directly from coupled measurements of a single-pixel detector, without the conventional image acquisition and reconstruction  ...  Besides, the binary modulation is trained and optimized together with the sensing network, which ensures least required measurements and optimal sensing accuracy.  ...  Second, the signal-to-noise ratio is largely increased by orders of magnitude, because all the light from target scene is converged to the single detection unit.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.11498v2">arXiv:1909.11498v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jy44xn4ujvccxpc73i3oq42dhq">fatcat:jy44xn4ujvccxpc73i3oq42dhq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823234606/https://arxiv.org/pdf/1909.11498v2.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/d6/76/d67680fe2135ba2bc3f959ff1357298408f1f7e6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.11498v2" 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>

Synchronous locating and imaging behind scattering medium in a large depth based on deep learning [article]

Shuo Zhu, Enlai Guo, Qianying Cui, Dongliang Zheng, Lianfa Bai, Jing Han
<span title="2020-05-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The constructed DINet can obtain multiple physical information via a single speckle pattern, including both the depth and image.  ...  A multi-task network, named DINet, is constructed to predict the depth and the image of the hidden object from the captured speckle patterns.  ...  In this Letter, a multi-task DINet is designed for simultaneous prediction of depth information and reconstruction of object image from a single speckle pattern.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.12637v2">arXiv:1910.12637v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v4tg36vfkbh27g4t553oelzjki">fatcat:v4tg36vfkbh27g4t553oelzjki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200602012254/https://arxiv.org/ftp/arxiv/papers/1910/1910.12637.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/1910.12637v2" 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>

Coding of Sound-Source Location by Ensembles of Cortical Neurons

Shigeto Furukawa, Li Xu, John C. Middlebrooks
<span title="2000-02-01">2000</span> <i title="Society for Neuroscience"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/s7bticdwizdmhll4taefg57jde" style="color: black;">Journal of Neuroscience</a> </i> &nbsp;
The ANN maintained better-thanchance performance even when input spike patterns were expressed as relative spike counts across units (i.e., no information available from absolute spike counts of individual  ...  The ANN performance improved monotonically as the sizes of ensemble patterns were increased by combining patterns across the entire unit sample.  ...  The possibility of sampling from an insensitive region could account for the particularly large median errors of some points of the simultaneous-sampling configuration shown in Figure 11 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1523/jneurosci.20-03-01216.2000">doi:10.1523/jneurosci.20-03-01216.2000</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/10648726">pmid:10648726</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l7c7ufzmhvbslhzvil2in2u7dy">fatcat:l7c7ufzmhvbslhzvil2in2u7dy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501114637/http://www.jneurosci.org/content/jneuro/20/3/1216.full.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/b8/15/b8156d0b0d5ba3e7a1104cd557bd680c37438372.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1523/jneurosci.20-03-01216.2000"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Page 1219 of The Journal of Neuroscience Vol. 20, Issue 3 [page]

<span title="2000-02-01">2000</span> <i title="Society for Neuroscience"> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_journal-of-neuroscience" style="color: black;">The Journal of Neuroscience</a> </i> &nbsp;
The azimuth was computed from the sine and cosine by forming the arctangent of the two network outputs. patterns effectively.  ...  The stimulus SPL often had large effects on spike patterns, typically increasing spike counts with increasing SPL.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_journal-of-neuroscience_2000-02-01_20_3/page/1219" title="read fulltext microfilm" 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> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_journal-of-neuroscience_2000-02-01_20_3/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

Applying big data based deep learning system to intrusion detection

Wei Zhong, Ning Yu, Chunyu Ai
<span title="">2020</span> <i title="Tsinghua University Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ijf7t5u575awlfr3o2g2yds3ju" style="color: black;">Big Data Mining and Analytics</a> </i> &nbsp;
Particularly, the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of samples.  ...  BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the payload.  ...  Acknowledgment This work was partially supported by Research Initiative for Summer Engagement (RISE) from the Office of the Vice President for Research at University of South Carolina.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.26599/bdma.2020.9020003">doi:10.26599/bdma.2020.9020003</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cqbejohorjcahn34vzhvtpxtta">fatcat:cqbejohorjcahn34vzhvtpxtta</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108145742/https://ieeexplore.ieee.org/ielx7/8254253/9142126/09142151.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/07/98/079811e779f6de7c32a3a38bf9656e66717322dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.26599/bdma.2020.9020003"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Extracting Labeled Topological Patterns from Samples of Networks

Christoph Schmidt, Thomas Weiss, Thomas Lehmann, Herbert Witte, Lutz Leistritz, Stefano Boccaletti
<span title="2013-08-12">2013</span> <i title="Public Library of Science (PLoS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/s3gm7274mfe6fcs7e3jterqlri" style="color: black;">PLoS ONE</a> </i> &nbsp;
These patterns, essentially sample-specific network motifs with vertex labeling, might represent the essence of the intricate topological information contained in all sample element networks and provides  ...  Compared to the analysis of single networks, their investigation promises to yield more detailed information about the represented system.  ...  In Section 2 a general description of our approach to extract topological patterns from network samples is provided.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pone.0070497">doi:10.1371/journal.pone.0070497</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/23950945">pmid:23950945</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3741309/">pmcid:PMC3741309</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6euhcw54kjekjdgfriihhqccwm">fatcat:6euhcw54kjekjdgfriihhqccwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171007231604/http://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0070497&amp;type=printable" 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/41/80/4180d519841bc9fd665db653b8a4c48d6f15536e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pone.0070497"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> plos.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3741309" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Single-shot autofocus microscopy using deep learning [article]

Henry Pinkard, Zachary Phillips, Arman Babakhani, Daniel A. Fletcher, Laura Waller
<span title="2019-03-23">2019</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Defocus distance can be estimated and corrected based on a single image under this LED illumination using a neural network that is small enough to be trained on a desktop CPU in a few hours.  ...  In this work, we detail the procedure for generating data and training such a network, explore practical limits, and describe relevant design principles governing the illumination source and network architecture  ...  truth focal position from an entire stack, and the other for training the network to predict the output of this computation from a single image (Fig. 1a) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/587485">doi:10.1101/587485</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vkcj4zhgize33ebpf32ekvrs7u">fatcat:vkcj4zhgize33ebpf32ekvrs7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190504055853/https://www.biorxiv.org/content/biorxiv/early/2019/03/23/587485.full.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/48/58/48587f4e03fd74074613f4e3882030632e5b65e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/587485"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>

Weighted Encoding Optimization for Dynamic Single-pixel Imaging and Sensing [article]

Xinrui Zhan, Liheng Bian, Chunli Zhu, Jun Zhang
<span title="2022-01-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, for varied sampling rates, the large-scale network requires retraining that is laboursome and computation-consuming.  ...  While the network is training at a high sampling rate, the modulation patterns and corresponding weights are updated iteratively, which produces optimal ranked encoding series when converged.  ...  with the highest weight as the modulating ones at each sampling rate from 0.01 to 0.1.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.02833v1">arXiv:2201.02833v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fzftjlfdpjeb3ivsy3uvsio2j4">fatcat:fzftjlfdpjeb3ivsy3uvsio2j4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112005219/https://arxiv.org/pdf/2201.02833v1.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/86/4c/864c27d3022654929417556d18ff97827611be53.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.02833v1" 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>

Multi-Modal Prototype Learning for Interpretable Multivariable Time Series Classification [article]

Gaurav R. Ghosal, Reza Abbasi-Asl
<span title="2021-06-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The next stage of our framework represents the multivariable time series sample points in terms of their similarity to these single-variable prototypes.  ...  In the first stage of our framework, encoders extract features from each variable independently. Prototype layers identify single-variable prototypes in the resulting feature spaces.  ...  these informative patterns.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.09636v1">arXiv:2106.09636v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ir4ojjl7gbakzikyrz6waaq434">fatcat:ir4ojjl7gbakzikyrz6waaq434</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210620020224/https://arxiv.org/pdf/2106.09636v1.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/95/61/9561d3a1f575900037bf9a3831f447dd641d55c9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.09636v1" 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>

Recognizing three-dimensional phase images with deep learning [article]

Weiru Fan, Tianrun Chen, Xingqi Xu, Ziyang Chen, Huizhu Hu, Delong Zhang, Da-Wei Wang, Jixiong Pu, Shi-Yao Zhu
<span title="2021-07-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
From the single-shot, reference-free and scanning-free speckle pattern input, STRN distinguishes depth-resolving quantitative phase information with high fidelity.  ...  Optical phase contains key information for biomedical and astronomical imaging.  ...  In conclusion, we demonstrated a novel imaging scheme for retrieving 3D phase information from 2D speckle patterns. A deep learning network, STRN, is designed to enable the 3D phase imaging scheme.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.10584v1">arXiv:2107.10584v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zwbzte677rcqnjl3v5rtmd4fqy">fatcat:zwbzte677rcqnjl3v5rtmd4fqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210724085625/https://arxiv.org/ftp/arxiv/papers/2107/2107.10584.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/1e/27/1e27efa5cc00ab01afedbf24db31d693b9253a72.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.10584v1" 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 detection from cluttered images using a polynomial neural network

Lin-Lin Huang, Akinobu Shimizu, Yoshihiro Hagihara, Hidefumi Kobatake
<span title="">2003</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bby322qx6ndsje4ypr56c7nnly" style="color: black;">Neurocomputing</a> </i> &nbsp;
The PNN is shown to be powerful to discriminate between face and non-face patterns when trained with large number of samples.  ...  We use a polynomial neural network (PNN) for separation of face and non-face patterns while the complexity of the PNN is reduced b y principal component analysis (PCA).  ...  It is expected that the object patterns have small distance from feature space and non-object patterns have large distance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0925-2312(02)00616-1">doi:10.1016/s0925-2312(02)00616-1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fopgxde44jhu3e5zugp3snpno4">fatcat:fopgxde44jhu3e5zugp3snpno4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20041121012055/http://www.tuat.ac.jp:80/~khbase/members/huang/ICIP01.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/94/f9/94f981794d7a836a7ed81399f2a83c85597ab3f4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0925-2312(02)00616-1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability [article]

Vojtěch Krajňanský, Matej Gallo, Rudolf Nenutil, Michal Němeček, Petr Holub, Tomáš Brázdil
<span title="2022-04-01">2022</span> <i title="Cold Spring Harbor Laboratory"> bioRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, we investigated various methods to extract the key features used by the neural network for classification.  ...  Reassuringly, the heatmaps identified several prevailing histomorphological features characterizing carcinoma, e.g. single-layered epithelium, presence of small lumina, and hyperchromatic nuclei with halos  ...  We also limited the maximum number of samples from a single WSI to 20.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2022.03.31.486599">doi:10.1101/2022.03.31.486599</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bxl4zskbhfc4ji6u5c6oxfn6fq">fatcat:bxl4zskbhfc4ji6u5c6oxfn6fq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220517104254/https://www.biorxiv.org/content/biorxiv/early/2022/04/01/2022.03.31.486599.full.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/29/01/29012fb3deeb4f5e41e7b4605b14fec5bfc82aab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2022.03.31.486599"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> biorxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 910,030 results