skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A mixed-scale dense convolutional neural network for image analysis

Journal Article · · Proceedings of the National Academy of Sciences of the United States of America
 [1];  [2]
  1. Center for Applied Mathematics for Energy Research Applications, Lawrence Berkeley National Laboratory, Berkeley, CA 94720,
  2. Center for Applied Mathematics for Energy Research Applications, Lawrence Berkeley National Laboratory, Berkeley, CA 94720,, Department of Mathematics, University of California, Berkeley, CA 94720
+ Show Author Affiliations

We report that deep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results in practice, a large number of trainable parameters are often required. Here, we introduce a network architecture based on using dilated convolutions to capture features at different image scales and densely connecting all feature maps with each other. The resulting architecture is able to achieve accurate results with relatively few parameters and consists of a single set of operations, making it easier to implement, train, and apply in practice, and automatically adapts to different problems. Lastly, we compare results of the proposed network architecture with popular existing architectures for several segmentation problems, showing that the proposed architecture is able to achieve accurate results with fewer parameters, with a reduced risk of overfitting the training data.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), Biological and Environmental Research (BER)
Grant/Contract Number:
AC03-76SF00098; AC02-05CH11231
OSTI ID:
1414877
Alternate ID(s):
OSTI ID: 1485062
Journal Information:
Proceedings of the National Academy of Sciences of the United States of America, Journal Name: Proceedings of the National Academy of Sciences of the United States of America Vol. 115 Journal Issue: 2; ISSN 0027-8424
Publisher:
Proceedings of the National Academy of SciencesCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 146 works
Citation information provided by
Web of Science

References (11)

Superparsing: Scalable Nonparametric Image Parsing with Superpixels journal October 2012
PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation journal March 2012
ImageNet: A large-scale hierarchical image database
  • Deng, Jia; Dong, Wei; Socher, Richard
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2009.5206848
conference June 2009
Deep learning journal May 2015
Fully Convolutional Networks for Semantic Segmentation journal April 2017
Semantic object classes in video: A high-definition ground truth database journal January 2009
Generalizing the Hough transform to detect arbitrary shapes journal January 1981
Radio frequency interference mitigation using deep convolutional neural networks journal January 2017
Image-to-Image Translation with Conditional Adversarial Networks conference July 2017
Caffe: Convolutional Architecture for Fast Feature Embedding conference January 2014
Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique journal July 2001

Figures / Tables (9)

Fig. 1(p. 3)figure Fig. 1
Fig. 2(p. 3)figure Fig. 2
Fig. 3(p. 4)figure Fig. 3
Fig. 4(p. 4)figure Fig. 4
Fig. 5(p. 5)figure Fig. 5
Table 1(p. 5)table Table 1
Fig. 6(p. 6)figure Fig. 6
Fig. 7(p. 6)figure Fig. 7
Fig. 8(p. 6)figure Fig. 8

Similar Records

Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices
Dataset · Thu May 21 00:00:00 EDT 2020 · OSTI ID:1414877
Application of convolutional neural networks for stellar spectral classification
Journal Article · Wed Nov 06 00:00:00 EST 2019 · Monthly Notices of the Royal Astronomical Society · OSTI ID:1414877
+3 more
A data-driven CO2 leakage detection using seismic data and spatial–temporal densely connected convolutional neural networks
Journal Article · Sat Aug 24 00:00:00 EDT 2019 · International Journal of Greenhouse Gas Control · OSTI ID:1414877
+4 more

Related Subjects

97 MATHEMATICS AND COMPUTING
image segmentation
machine learning
convolution neural networks