WEKO3
アイテム
Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples
https://repository.lib.tottori-u.ac.jp/records/7210
https://repository.lib.tottori-u.ac.jp/records/72105617a32e-f0df-4872-9cd6-3652f1d85773
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
ieicetise105-d(2)_415.pdf (2.0 MB)
|
|
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2022-07-13 | |||||
| タイトル | ||||||
| タイトル | Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| キーワード | ||||||
| 主題 | gaze distribution | |||||
| キーワード | ||||||
| 主題 | attention mechanism | |||||
| キーワード | ||||||
| 主題 | convolutional neural network | |||||
| キーワード | ||||||
| 主題 | gender recognition | |||||
| キーワード | ||||||
| 主題 | self-attention | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題 | gaze distribution | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題 | attention mechanism | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題 | convolutional neural network | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題 | gender recognition | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題 | self-attention | |||||
| 資源タイプ | ||||||
| 資源タイプ | journal article | |||||
| 著者 |
西山, 正志
× 西山, 正志× 岩井, 儀雄× Inoue, Michiko |
|||||
| 著者所属（英） | ||||||
| 言語 | en | |||||
| 値 | Graduate School of Engineering, Tottori University | |||||
| 著者所属（英） | ||||||
| 言語 | en | |||||
| 値 | Graduate School of Engineering, Tottori University | |||||
| 著者所属（英） | ||||||
| 言語 | en | |||||
| 値 | Graduate School of Engineering, Tottori University | |||||
| 抄録 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | We propose an attention mechanism in deep learning networks for gender recognition using the gaze distribution of human observers when they judge the gender of people in pedestrian images. Prevalent attention mechanisms spatially compute the correlation among values of all cells in an input feature map to calculate attention weights. If a large bias in the background of pedestrian images (e.g., test samples and training samples containing different backgrounds) is present, the attention weights learned using the prevalent attention mechanisms are affected by the bias, which in turn reduces the accuracy of gender recognition. To avoid this problem, we incorporate an attention mechanism called gaze-guided self-attention (GSA) that is inspired by human visual attention. Our method assigns spatially suitable attention weights to each input feature map using the gaze distribution of human observers. In particular, GSA yields promising results even when using training samples with the background bias. The results of experiments on publicly available datasets confirm that our GSA, using the gaze distribution, is more accurate in gender recognition than currently available attention-based methods in the case of background bias between training and test samples. | |||||
| 書誌情報 |
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS en : IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 巻 E105-D, 号 2, p. 415-426, 発行日 2022-02 |
|||||
| 出版者 | ||||||
| 出版者 | IEICE | |||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 17451361 | |||||
| DOI | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | 10.1587/transinf.2021edp7117 | |||||
| 権利 | ||||||
| 権利情報 | (C) 2022 The Institute of Electronics, Information and Communication Engineers | |||||
| 情報源 | ||||||
| 関連名称 | Nishiyama Masashi, Inoue Michiko, Iwai Yoshio, et al. Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS. 2022. E105D(2). 415-426. doi:10.1587/t | |||||
| 関連サイト | ||||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | https://doi.org/10.1587/transinf.2021EDP7117 | |||||
| 関連名称 | https://doi.org/10.1587/transinf.2021EDP7117 | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
