Presentation | 2022-02-22 Noise-Resistant Learning for Object Detection Jiafeng Mao, Qing Yu, Yoko Yamakata, Kiyoharu Aizawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Supervised training of object detectors requires well-annotated large-scale datasets, whose production is extremely expensive. Therefore, some efforts have been made to obtain annotations in economical ways such as cloud sourcing. However, datasets obtained by these methods tend to contain noisy annotations such as inaccurate bounding boxes and incorrect class labels. Our research thus focuses on training object detectors on datasets with entangled classification noise and localization annotation noise. In this study, we propose a framework to distinguish and correct the noisy annotations and subsequently train the detector using the corrected annotations. We verified the effectiveness of our proposed method and compared it with state-of-the-art methods on noisy datasets with different noise levels. The experimental results show that our proposed method significantly outperforms state-of-the-art methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | noise-resistantrobust learningobject detectionannotation refinement |
Paper # | ITS2021-52,IE2021-61 |
Date of Issue | 2022-02-14 (ITS, IE) |
Conference Information | |
Committee | IE / ITS / ITE-AIT / ITE-ME / ITE-MMS |
---|---|
Conference Date | 2022/2/21(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image Processing, etc. |
Chair | Kazuya Kodama(NII) / Masahiro Fujii(Utsunomiya Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.) / Kenji Machida(NHK) |
Vice Chair | Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST) / / Shogo Muramatsu(Niigata Univ.) |
Secretary | Hiroyuki Bandoh(KDDI Research) / Toshihiko Yamazaki(Nagoya Inst. of Tech.) / Kohei Ohno(Akita Prefectural Univ.) / Naohisa Hashimoto(NIT, Tsuruoka College) / / Shogo Muramatsu(NHK) / (Hokkaido Univ.) |
Assistant | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) |
Paper Information | |
Registration To | Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Artistic Image Technology / Technical Group on Media Engineering / Technical Group on Multi-media Storage |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Noise-Resistant Learning for Object Detection |
Sub Title (in English) | |
Keyword(1) | noise-resistantrobust learningobject detectionannotation refinement |
1st Author's Name | Jiafeng Mao |
1st Author's Affiliation | The University of Tokyo(UTokyo) |
2nd Author's Name | Qing Yu |
2nd Author's Affiliation | The University of Tokyo(UTokyo) |
3rd Author's Name | Yoko Yamakata |
3rd Author's Affiliation | The University of Tokyo(UTokyo) |
4th Author's Name | Kiyoharu Aizawa |
4th Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2022-02-22 |
Paper # | ITS2021-52,IE2021-61 |
Volume (vol) | vol.121 |
Number (no) | ITS-373,IE-374 |
Page | pp.pp.163-166(ITS), pp.163-166(IE), |
#Pages | 4 |
Date of Issue | 2022-02-14 (ITS, IE) |