文献の詳細
| 論文の言語 | 日本語 |
|---|---|
| 著者 | Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise |
| 論文名 | ShakeDrop Regularization |
| 論文誌名 | Proc. 6th International Conference on Learning Representation (ICLR) Workshop |
| ページ | pp.1-4 |
| ページ数 | 4 pages |
| 発表場所 | Vancouver, Canada |
| 査読の有無 | 有 |
| 年月 | 2018年4月 |
| 要約 | This paper proposes a powerful regularization method named ShakeDrop regularization. ShakeDrop is inspired by Shake-Shake regularization that decreases error rates by disturbing learning. While Shake-Shake can be applied to only ResNeXt which has multiple branches, ShakeDrop can be applied to not only ResNeXt but also ResNet, Wide ResNet and PyramidNet in a memory efficient way. Important and interesting feature of ShakeDrop is that it strongly disturbs learning by multiplying even a negative factor to the output of a convolutional layer in the forward training pass. The effectiveness of ShakeDrop is confirmed by experiments on CIFAR-10/100 and Tiny ImageNet datasets. |
| URL | https://openreview.net/forum?id=Bymu6tJwz |
- 次のファイルが利用可能です．
- BibTeX用エントリー
@InProceedings{Yoshihiro2018, author = {Yoshihiro Yamada and Masakazu Iwamura and Koichi Kise}, title = {ShakeDrop Regularization}, booktitle = {Proc. 6th International Conference on Learning Representation (ICLR) Workshop}, year = 2018, month = apr, pages = {1--4}, numpages = {4}, URL = {https://openreview.net/forum?id=Bymu6tJwz}, location = {Vancouver, Canada} }