ShakeDrop Regularization
| 言語 | 日本語 |
|---|---|
| 種類 | 国際会議等の予稿 |
| 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 |
| 発表場所 | Vancouver, Canada |
| 査読の有無 | 有 |
| 年月 | 2018年4月 |
| 分野 | 物体認識, ディープラーニング |
| URL | https://openreview.net/forum?id=Bymu6tJwz |
| キー | Yamada2018_ICLR (id=1613) |
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.
関連ファイル
- …
この文献を出力
書式の定義
書式の定義の書き方
{authors} のように波括弧でフィールドを挿入します．[ ... ] で囲んだ部分は，その中のフィールドが空のとき丸ごと省略されます．使えるフィールド：
{authors}{authors_and}{authors_ja}{authors_ja_tight}{authors_en}{authors_en_and}{authors_tight}{first_author}{title}{title_ja}{title_en}{journal}{journal_ja}{journal_en}{book_title}{volume}{number}{series}{presen_id}{pages}{pp}{num_pages}{year}{month}{month_en}{month_short}{ym}{date}{date_ja}{date_en}{publisher}{address}{location}{review}{review_ja}{review_en}{reviewed_mark}{presen_type}{type}{type_label}{doi}{url}{key}{awards}