講演抄録/キーワード |
講演名 |
2020-03-16 17:00
Continuous Variables Estimation Through Classification Networks Ensembles ○Qianyuan Liu(Nagoya Univ.)・Yu Wang・Jien Kato(Ritsumeikan Univ.) PRMU2019-87 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
With the development of deep learning, CNNs have shown outstanding performance on various tasks. Previous approaches find that CNNs perform better on classification tasks than regression tasks, because regression task is a highly challenging task that approximates a mapping function from input variables to a continuous output variable. In the computer vision and mul-timedia communities, researchers address continuous variables estimation by deep convolutional neural regression networks. In this paper we make estimation of the continuous attributes of images by using classification networks ensembling. To the best of our knowledge, this is the first attempt to address regression problems through classification networks ensembles and our proposed method shows great versatility in different datasets. Experiment results show that our proposed method outper-forms the regression method and single classification network. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Regression task / Classification task / Networks Ensembling / CNNs / / / / |
文献情報 |
信学技報, vol. 119, no. 481, PRMU2019-87, pp. 109-114, 2020年3月. |
資料番号 |
PRMU2019-87 |
発行日 |
2020-03-09 (PRMU) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2019-87 |