Presentation 2021-03-05
Improving Accuracy on Biased Datasets via Explanations of Deep Neural Networks
Kazuki Adachi, Shin'ya Yamaguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Although it is desirable that training datasets for deep learning have diverse features, datasets that have biased features irrelevant to target tasks are likely to be created actually. Deep learning models trained on such biased datasets degrade its accuracy toward input distribution shift. To tackle this problem, we propose Independent Feature Focusing (IFF), the method to detect features on which models should focus and regularize its attribution to improve accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep learning / Explanation / Dataset bias
Paper # PRMU2020-93
Date of Issue 2021-02-25 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2021/3/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Computer Vision and Pattern Recognition for specific environment
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.)
Secretary Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.)
Assistant Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / 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) Improving Accuracy on Biased Datasets via Explanations of Deep Neural Networks
Sub Title (in English)
Keyword(1) Deep learning
Keyword(2) Explanation
Keyword(3) Dataset bias
1st Author's Name Kazuki Adachi
1st Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
2nd Author's Name Shin'ya Yamaguchi
2nd Author's Affiliation Nippon Telegraph and Telephone Corporation(NTT)
Date 2021-03-05
Paper # PRMU2020-93
Volume (vol) vol.120
Number (no) PRMU-409
Page pp.pp.139-144(PRMU),
#Pages 6
Date of Issue 2021-02-25 (PRMU)