2 Search Results for "Zhao, Tian"

Document
DOI: 10.4230/LITES.8.1.3
HW-Flow: A Multi-Abstraction Level HW-CNN Codesign Pruning Methodology

Authors: Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein, Emanuele Valpreda, Manfredi Camalleri, Qi Zhao, Christian Unger, Naveen-Shankar Nagaraja, Maurizio Martina, and Walter Stechele

Published in: LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision. Leibniz Transactions on Embedded Systems, Volume 8, Issue 1

Abstract
Convolutional neural networks (CNNs) have produced unprecedented accuracy for many computer vision problems in the recent past. In power and compute-constrained embedded platforms, deploying modern CNNs can present many challenges. Most CNN architectures do not run in real-time due to the high number of computational operations involved during the inference phase. This emphasizes the role of CNN optimization techniques in early design space exploration. To estimate their efficacy in satisfying the target constraints, existing techniques are either hardware (HW) agnostic, pseudo-HW-aware by considering parameter and operation counts, or HW-aware through inflexible hardware-in-the-loop (HIL) setups. In this work, we introduce HW-Flow, a framework for optimizing and exploring CNN models based on three levels of hardware abstraction: Coarse, Mid and Fine. Through these levels, CNN design and optimization can be iteratively refined towards efficient execution on the target hardware platform. We present HW-Flow in the context of CNN pruning by augmenting a reinforcement learning agent with key metrics to understand the influence of its pruning actions on the inference hardware. With 2× reduction in energy and latency, we prune ResNet56, ResNet50, and DeepLabv3 with minimal accuracy degradation on the CIFAR-10, ImageNet, and CityScapes datasets, respectively.
Cite as

Manoj-Rohit Vemparala, Nael Fasfous, Alexander Frickenstein, Emanuele Valpreda, Manfredi Camalleri, Qi Zhao, Christian Unger, Naveen-Shankar Nagaraja, Maurizio Martina, and Walter Stechele. HW-Flow: A Multi-Abstraction Level HW-CNN Codesign Pruning Methodology. In LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision. Leibniz Transactions on Embedded Systems, Volume 8, Issue 1, pp. 03:1-03:30, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@Article{vemparala_et_al:LITES.8.1.3,
  author =	{Vemparala, Manoj-Rohit and Fasfous, Nael and Frickenstein, Alexander and Valpreda, Emanuele and Camalleri, Manfredi and Zhao, Qi and Unger, Christian and Nagaraja, Naveen-Shankar and Martina, Maurizio and Stechele, Walter},
  title =	{{HW-Flow: A Multi-Abstraction Level HW-CNN Codesign Pruning Methodology}},
  booktitle =	{LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision},
  pages =	{03:1--03:30},
  journal =	{Leibniz Transactions on Embedded Systems},
  ISSN =	{2199-2002},
  year =	{2022},
  volume =	{8},
  number =	{1},
  editor =	{Vemparala, Manoj-Rohit and Fasfous, Nael and Frickenstein, Alexander and Valpreda, Emanuele and Camalleri, Manfredi and Zhao, Qi and Unger, Christian and Nagaraja, Naveen-Shankar and Martina, Maurizio and Stechele, Walter},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LITES.8.1.3},
  doi =		{10.4230/LITES.8.1.3},
  annote =	{Keywords: Convolutional Neural Networks, Optimization, Hardware Modeling, Pruning}
}
Document
Short Paper
DOI: 10.4230/LIPIcs.GISCIENCE.2018.72
Scalable Spatial Join for WFS Clients (Short Paper)

Authors: Tian Zhao, Chuanrong Zhang, and Zhijie Zhang

Published in: LIPIcs, Volume 114, 10th International Conference on Geographic Information Science (GIScience 2018)

Abstract
Web Feature Service (WFS) is a popular Web service for geospatial data, which is represented as sets of features that can be queried using the GetFeature request protocol. However, queries involving spatial joins are not efficiently supported by WFS server implementations such as GeoServer. Performing spatial join at client side is unfortunately expensive and not scalable. In this paper, we propose a simple and yet scalable strategy for performing spatial joins at client side after querying WFS data. Our approach is based on the fact that Web clients of WFS data are often used for query-based visual exploration. In visual exploration, the queried spatial objects can be filtered for a particular zoom level and spatial extent and be simplified before spatial join and still serve their purpose. This way, we can drastically reduce the number of spatial objects retrieved from WFS servers and reduce the computation cost of spatial join, so that even a simple plane-sweep algorithm can yield acceptable performance for interactive applications.
Cite as

Tian Zhao, Chuanrong Zhang, and Zhijie Zhang. Scalable Spatial Join for WFS Clients (Short Paper). In 10th International Conference on Geographic Information Science (GIScience 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 114, pp. 72:1-72:6, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2018)

Copy BibTex To Clipboard

@InProceedings{zhao_et_al:LIPIcs.GISCIENCE.2018.72,
  author =	{Zhao, Tian and Zhang, Chuanrong and Zhang, Zhijie},
  title =	{{Scalable Spatial Join for WFS Clients}},
  booktitle =	{10th International Conference on Geographic Information Science (GIScience 2018)},
  pages =	{72:1--72:6},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-083-5},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{114},
  editor =	{Winter, Stephan and Griffin, Amy and Sester, Monika},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GISCIENCE.2018.72},
  URN =		{urn:nbn:de:0030-drops-94007},
  doi =		{10.4230/LIPIcs.GISCIENCE.2018.72},
  annote =	{Keywords: WFS, SPARQL, Spatial Join}
}
  • Refine by Author
  • 1 Camalleri, Manfredi
  • 1 Fasfous, Nael
  • 1 Frickenstein, Alexander
  • 1 Martina, Maurizio
  • 1 Nagaraja, Naveen-Shankar
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Artificial intelligence
  • 1 Information systems → Geographic information systems

  • Refine by Keyword
  • 1 Convolutional Neural Networks
  • 1 Hardware Modeling
  • 1 Optimization
  • 1 Pruning
  • 1 SPARQL
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 1 2018
  • 1 2022

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
© 2023 Schloss Dagstuhl - LZI GmbH Imprint Privacy Contact