WEKO3
-
RootNode
アイテム
Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition
http://hdl.handle.net/10228/00008727
http://hdl.handle.net/10228/00008727239ecb37-910e-45ce-ac91-52fe48503600
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
10384697.pdf (386.1 kB)
|
|
| Item type | 学術雑誌論文 = Journal Article(1) | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2022-02-18 | |||||||||||||||||||||
| 資源タイプ | ||||||||||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||||||||||
| 資源タイプ | journal article | |||||||||||||||||||||
| タイトル | ||||||||||||||||||||||
| タイトル | Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set Recognition | |||||||||||||||||||||
| 言語 | en | |||||||||||||||||||||
| 言語 | ||||||||||||||||||||||
| 言語 | eng | |||||||||||||||||||||
| 著者 |
Kanaoka, Daiju
× Kanaoka, Daiju× 田中, 悠一朗
WEKO
30537
× 田向, 権
WEKO
6059
|
|||||||||||||||||||||
| 抄録 | ||||||||||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||||||||||
| 内容記述 | With the advent of deep learning, significant improvements in image recognition performance have been achieved. In image recognition, it is generally assumed that all the test data are composed of known classes. This approach is termed as closed-set recognition. In closed-set recognition, when an untrained, unknown class is input, it is recognized as one of the trained classes. The method whereby an unknown image is recognized as unknown when it is input is termed as open-set recognition. Although several open-set recognition methods have been proposed, none of these previous methods excel in terms of all three evaluation items: learning cost, recognition performance, and scalability from closed-set recognition models. To address this, we propose an open-set recognition method using the distance between features in the multidimensional feature space of neural networks. By applying center loss to the feature space, we aim to maintain the classification accuracy of closed-set recognition and improve the unknown detection performance. In our experiments, we achieved state-of-the-art performance on the MNIST, SVHN, and CIFAR-10 datasets. In addition, the proposed approach shows excellent performance in terms of the three evaluation items. | |||||||||||||||||||||
| 言語 | en | |||||||||||||||||||||
| 備考 | ||||||||||||||||||||||
| 内容記述タイプ | Other | |||||||||||||||||||||
| 内容記述 | 17th International Joint Conference on Computer Vision Theory and Applications (VISAPP 2022), February 6-8, 2022, Online Streaming | |||||||||||||||||||||
| 書誌情報 |
Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 巻 5, p. 359-365, 発行日 2022 |
|||||||||||||||||||||
| 出版社 | ||||||||||||||||||||||
| 出版者 | ScitePress | |||||||||||||||||||||
| DOI | ||||||||||||||||||||||
| 関連タイプ | isVersionOf | |||||||||||||||||||||
| 識別子タイプ | DOI | |||||||||||||||||||||
| 関連識別子 | https://doi.org/10.5220/0010816600003124 | |||||||||||||||||||||
| ISBN | ||||||||||||||||||||||
| 識別子タイプ | ISBN | |||||||||||||||||||||
| 関連識別子 | 978-989-758-555-5 | |||||||||||||||||||||
| 日本十進分類法 | ||||||||||||||||||||||
| 主題Scheme | NDC | |||||||||||||||||||||
| 主題 | 548 | |||||||||||||||||||||
| 著作権関連情報 | ||||||||||||||||||||||
| 権利情報Resource | https://creativecommons.org/licenses/by/4.0/ | |||||||||||||||||||||
| 権利情報 | CC BY-NC-ND 4.0 | |||||||||||||||||||||
| キーワード | ||||||||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||||||
| 主題 | Open-Set Recognition | |||||||||||||||||||||
| キーワード | ||||||||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||||||
| 主題 | Neural Networks | |||||||||||||||||||||
| キーワード | ||||||||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||||||
| 主題 | Image Classification | |||||||||||||||||||||
| キーワード | ||||||||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||||||
| 主題 | Unknown Class | |||||||||||||||||||||
| 出版タイプ | ||||||||||||||||||||||
| 出版タイプ | AM | |||||||||||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||||||||||||
| 査読の有無 | ||||||||||||||||||||||
| 値 | yes | |||||||||||||||||||||
| 研究者情報 | ||||||||||||||||||||||
| https://hyokadb02.jimu.kyutech.ac.jp/html/100001426_ja.html | ||||||||||||||||||||||
| 論文ID（連携） | ||||||||||||||||||||||
| 10384697 | ||||||||||||||||||||||
| 連携ID | ||||||||||||||||||||||
| 10153 | ||||||||||||||||||||||
