Presentation | 2019-09-05 Active learning based on self-supervised feature learning Shunsuke Tsukatani, Kazuhiko Murasaki, Shingo Andou, jun Shimamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose an active learning algorithm based on self-supervised feature learning. When the domain of the data set used for pre-trained model are different from target domain, the conventional sampling method can not select samples effectively. To avoid this problem, Our approach adopt self-supervised feature learning method in active learning framework. Our algorithm select unlabeled data from feature clusters which does not include labeled data. Our experiments show that the proposed method outperforms existing approaches in imageclassification experiments. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | active learning / self-supervised feature learning / image classification |
Paper # | PRMU2019-28,MI2019-47 |
Date of Issue | 2019-08-28 (PRMU, MI) |
Conference Information | |
Committee | PRMU / MI / IPSJ-CVIM |
---|---|
Conference Date | 2019/9/4(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Yoichi Sato(Univ. of Tokyo) / Yoshiki Kawata(Tokushima Univ.) |
Vice Chair | Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT) / Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
Secretary | Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX) / Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
Assistant | Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.) / Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Medical Imaging / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Active learning based on self-supervised feature learning |
Sub Title (in English) | |
Keyword(1) | active learning |
Keyword(2) | self-supervised feature learning |
Keyword(3) | image classification |
1st Author's Name | Shunsuke Tsukatani |
1st Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
2nd Author's Name | Kazuhiko Murasaki |
2nd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
3rd Author's Name | Shingo Andou |
3rd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
4th Author's Name | jun Shimamura |
4th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT) |
Date | 2019-09-05 |
Paper # | PRMU2019-28,MI2019-47 |
Volume (vol) | vol.119 |
Number (no) | PRMU-192,MI-193 |
Page | pp.pp.115-119(PRMU), pp.115-119(MI), |
#Pages | 5 |
Date of Issue | 2019-08-28 (PRMU, MI) |