Truncating Wide Networks Using Binary Tree Architectures

Yan Zhangy, Mete Ozayy, Shuohao Li, Takayuki Okatani

研究成果: Conference contribution

抄録

In this paper, we propose a binary tree architecture to truncate architecture of wide networks by reducing the width of the networks. More precisely, in the proposed architecture, the width is incrementally reduced from lower layers to higher layers in order to increase the expressive capacity of networks with a less increase on parameter size. Also, in order to ease the gradient vanishing problem, features obtained at different layers are concatenated to form the output of our architecture. By employing the proposed architecture on a baseline wide network, we can construct and train a new network with same depth but considerably less number of parameters. In our experimental analyses, we observe that the proposed architecture enables us to obtain better parameter size and accuracy trade-off compared to baseline networks using various benchmark image classification datasets. The results show that our model can decrease the classification error of a baseline from 20:43% to 19:22% on Cifar-100 using only 28% of parameters that the baseline has. Code is available at https://github.com/ZhangVision/bitnet.

本文言語English
ホスト出版物のタイトルProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ2116-2124
ページ数9
ISBN(電子版)9781538610329
DOI
出版ステータスPublished - 2017 12 22
イベント16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
継続期間: 2017 10 222017 10 29

出版物シリーズ

名前Proceedings of the IEEE International Conference on Computer Vision
2017-October
ISSN(印刷版)1550-5499

Other

Other16th IEEE International Conference on Computer Vision, ICCV 2017
国/地域Italy
CityVenice
Period17/10/2217/10/29

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Truncating Wide Networks Using Binary Tree Architectures」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル