3 Search Results for "Deng, Yuxin"


Document
Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling

Authors: Xueqing Deng, Yuxin Tian, and Shawn Newsam

Published in: LIPIcs, Volume 177, 11th International Conference on Geographic Information Science (GIScience 2021) - Part I (2020)


Abstract
That most deep learning models are purely data driven is both a strength and a weakness. Given sufficient training data, the optimal model for a particular problem can be learned. However, this is usually not the case and so instead the model is either learned from scratch from a limited amount of training data or pre-trained on a different problem and then fine-tuned. Both of these situations are potentially suboptimal and limit the generalizability of the model. Inspired by this, we investigate methods to inform or guide deep learning models for geospatial image analysis to increase their performance when a limited amount of training data is available or when they are applied to scenarios other than which they were trained on. In particular, we exploit the fact that there are certain fundamental rules as to how things are distributed on the surface of the Earth and these rules do not vary substantially between locations. Based on this, we develop a novel feature pooling method for convolutional neural networks using Getis-Ord Gi* analysis from geostatistics. Experimental results show our proposed pooling function has significantly better generalization performance compared to a standard data-driven approach when applied to overhead image segmentation.

Cite as

Xueqing Deng, Yuxin Tian, and Shawn Newsam. Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling. In 11th International Conference on Geographic Information Science (GIScience 2021) - Part I. Leibniz International Proceedings in Informatics (LIPIcs), Volume 177, pp. 3:1-3:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)


Copy BibTex To Clipboard

@InProceedings{deng_et_al:LIPIcs.GIScience.2021.I.3,
  author =	{Deng, Xueqing and Tian, Yuxin and Newsam, Shawn},
  title =	{{Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling}},
  booktitle =	{11th International Conference on Geographic Information Science (GIScience 2021) - Part I},
  pages =	{3:1--3:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-166-5},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{177},
  editor =	{Janowicz, Krzysztof and Verstegen, Judith A.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2021.I.3},
  URN =		{urn:nbn:de:0030-drops-130387},
  doi =		{10.4230/LIPIcs.GIScience.2021.I.3},
  annote =	{Keywords: Remote sensing, convolutional neural networks, pooling function, semantic segmentation, generalization}
}
Document
Invited Paper
Bisimulations for Probabilistic and Quantum Processes (Invited Paper)

Authors: Yuxin Deng

Published in: LIPIcs, Volume 118, 29th International Conference on Concurrency Theory (CONCUR 2018)


Abstract
Bisimulation is a fundamental concept in the classical concurrency theory for comparing the behaviour of nondeterministic processes. It admits elegant characterisations from various perspectives such as fixed point theory, modal logics, game theory, coalgebras etc. In this paper, we review some key ideas used in the formulations and characterisations of reasonable notions of bisimulations for both probabilistic and quantum processes. To some extent the transition from probabilistic to quantum concurrency theory is smooth and natural. However, new ideas need also to be introduced. We have not yet reached the stage of formally verifying quantum communication protocols and quantum algorithms using bisimulations implemented by automatic tools. We discuss some recent efforts in this direction.

Cite as

Yuxin Deng. Bisimulations for Probabilistic and Quantum Processes (Invited Paper). In 29th International Conference on Concurrency Theory (CONCUR 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 118, pp. 2:1-2:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@InProceedings{deng:LIPIcs.CONCUR.2018.2,
  author =	{Deng, Yuxin},
  title =	{{Bisimulations for Probabilistic and Quantum Processes}},
  booktitle =	{29th International Conference on Concurrency Theory (CONCUR 2018)},
  pages =	{2:1--2:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-087-3},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{118},
  editor =	{Schewe, Sven and Zhang, Lijun},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CONCUR.2018.2},
  URN =		{urn:nbn:de:0030-drops-95406},
  doi =		{10.4230/LIPIcs.CONCUR.2018.2},
  annote =	{Keywords: Bisimulations, probabilistic processes, quantum processes}
}
Document
On Coinduction and Quantum Lambda Calculi

Authors: Yuxin Deng, Yuan Feng, and Ugo Dal Lago

Published in: LIPIcs, Volume 42, 26th International Conference on Concurrency Theory (CONCUR 2015)


Abstract
In the ubiquitous presence of linear resources in quantum computation, program equivalence in linear contexts, where programs are used or executed once, is more important than in the classical setting. We introduce a linear contextual equivalence and two notions of bisimilarity, a state-based and a distribution-based, as proof techniques for reasoning about higher-order quantum programs. Both notions of bisimilarity are sound with respect to the linear contextual equivalence, but only the distribution-based one turns out to be complete. The completeness proof relies on a characterisation of the bisimilarity as a testing equivalence.

Cite as

Yuxin Deng, Yuan Feng, and Ugo Dal Lago. On Coinduction and Quantum Lambda Calculi. In 26th International Conference on Concurrency Theory (CONCUR 2015). Leibniz International Proceedings in Informatics (LIPIcs), Volume 42, pp. 427-440, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)


Copy BibTex To Clipboard

@InProceedings{deng_et_al:LIPIcs.CONCUR.2015.427,
  author =	{Deng, Yuxin and Feng, Yuan and Dal Lago, Ugo},
  title =	{{On Coinduction and Quantum Lambda Calculi}},
  booktitle =	{26th International Conference on Concurrency Theory (CONCUR 2015)},
  pages =	{427--440},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-91-0},
  ISSN =	{1868-8969},
  year =	{2015},
  volume =	{42},
  editor =	{Aceto, Luca and de Frutos Escrig, David},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CONCUR.2015.427},
  URN =		{urn:nbn:de:0030-drops-53883},
  doi =		{10.4230/LIPIcs.CONCUR.2015.427},
  annote =	{Keywords: Quantum lambda calculi, contextual equivalence, bisimulation}
}
  • Refine by Author
  • 2 Deng, Yuxin
  • 1 Dal Lago, Ugo
  • 1 Deng, Xueqing
  • 1 Feng, Yuan
  • 1 Newsam, Shawn
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Neural networks
  • 1 Theory of computation → Modal and temporal logics
  • 1 Theory of computation → Operational semantics
  • 1 Theory of computation → Process calculi

  • Refine by Keyword
  • 1 Bisimulations
  • 1 Quantum lambda calculi
  • 1 Remote sensing
  • 1 bisimulation
  • 1 contextual equivalence
  • Show More...

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 1 2015
  • 1 2018
  • 1 2020

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail