講演抄録/キーワード |
講演名 |
2023-03-02 17:00
A Semi-Supervised Learning Framework for Handwritten Text Recognition using Mixed Augmentations and Scheduled Pseudo-Label Loss ○Masayuki Honda・Hung Tuan Nguyen・Cuong Tuan Nguyen(TUAT)・Cong Kha Nguyen・Ryosuke Odate・Takashi Kanemaru(Hitachi Ltd.)・Masaki Nakagawa(TUAT) PRMU2022-97 IBISML2022-104 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
We propose Incremental Teacher Model, a semi-supervised learning (SSL) framework for handwriting text recognition. The framework comprises a teacher model and a student model learning through Scheduled Pseudo-Label loss with Mixed Augmentations. First, the student model is pre-trained by labeled samples and used to initiate the teacher model. The student model is further trained on transformed samples provided by Mixed Augmentations. This training process uses pseudo-labels generated by the teacher model. After a training epoch, the teacher model is updated from a well-validated student model. We apply the proposed framework to four architectures of different handwriting recognizers. For almost every architecture, the recognizer trained by Incremental Teacher Model outperforms the recognizers trained by the well-known SSL methods on the IAM handwriting database. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Semi-Supervised Learning / Training framework / Handwriting recognition / / / / / |
文献情報 |
信学技報, vol. 122, no. 404, PRMU2022-97, pp. 199-204, 2023年3月. |
資料番号 |
PRMU2022-97 |
発行日 |
2023-02-23 (PRMU, IBISML) |
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 |
PRMU2022-97 IBISML2022-104 |