Merged Multi-CNN with Parameter Reduction for Face Attribute Estimation

Hiroya Kawai Koichi Ito, Takafumi Aoki

研究成果: Conference contribution

抄録

This paper proposes a face attribute estimation method using Merged Multi-CNN (MM-CNN). The proposed method merges single-task CNNs into one CNN by adding merging points and reduces the number of parameters by removing the fully-connected layers. We also propose a new idea of reducing parameters of CNN called Convolutionalization for Parameter Reduction (CPR), which estimates attributes using only convolution layers, in other words, does not need any fully-connected layers to estimate attributes from extracted features. Through a set of experiments using the Celeb A and LFW-a datasets, we demonstrated that MM- CNN with CPR exhibits higher efficiency of face attribute estimation than conventional methods.

本文言語English
ホスト出版物のタイトル2019 International Conference on Biometrics, ICB 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781728136400
DOI
出版ステータスPublished - 2019 6
イベント2019 International Conference on Biometrics, ICB 2019 - Crete, Greece
継続期間: 2019 6 42019 6 7

出版物シリーズ

名前2019 International Conference on Biometrics, ICB 2019

Conference

Conference2019 International Conference on Biometrics, ICB 2019
国/地域Greece
CityCrete
Period19/6/419/6/7

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理
  • 統計学、確率および不確実性
  • 人口統計学

フィンガープリント

「Merged Multi-CNN with Parameter Reduction for Face Attribute Estimation」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