Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/127246
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Structured binary neural networks for accurate image classification and semantic segmentation
Author: Zhuang, B.
Shen, C.
Tan, M.
Liu, L.
Reid, I.
Citation: Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019, vol.2019-June, pp.413-422
Publisher: IEEE
Publisher Place: online
Issue Date: 2019
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781728132938
ISSN: 1063-6919
Conference Name: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (15 Jun 2019 - 20 Jun 2019 : Long Beach, USA)
Statement of
Responsibility: 
Bohan Zhuang, Chunhua Shen, Mingkui Tan, Lingqiao Liu, Ian Reid
Abstract: In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically for mobile devices with limited power capacity and computation resources. Previous works on quantizing CNNs seek to approximate the floating-point information using a set of discrete values, which we call value approximation, but typically assume the same architecture as the full-precision networks. However, we take a novel “structure approximation” view for quantization-it is very likely that a different architecture may be better for best performance. In particular, we propose a “network decomposition” strategy, termed Group-Net, in which we divide the network into groups. In this way, each full-precision group can be effectively reconstructed by aggregating a set of homogeneous binary branches. In addition, we learn effective connections among groups to improve the representational capability. Moreover, the proposed Group-Net shows strong generalization to other tasks. For instance, we extend Group-Net for highly accurate semantic segmentation by embedding rich context into the binary structure. Experiments on both classification and semantic segmentation tasks demonstrate the superior performance of the proposed methods over various popular architectures. In particular, we outperform the previous best binary neural networks in terms of accuracy and major computation savings.
Rights: ©2019 IEEE
DOI: 10.1109/CVPR.2019.00050
Grant ID: http://purl.org/au-research/grants/arc/DE170101259
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.