Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
arxiv链接 前言 有时候, 输入数据加入细微的扰动, 都会让模型结果大相径庭. 因此, 我们总是希望训练结果的分布是光滑的, 这样才能保持稳定. 但在连续分布的空间中, 总是存在过大的间隙, 这些间隙只能靠更多的数据或减小网络复杂度(正则)的方法让它尽可能光滑. VAT同样是为了解决光滑问题, 且解释性更强, 也更直观. 我只读了文章前4页, 做个大概了解. 思路 一个图片是N维中的一个点P,
相关文章
- 1. Regularization method for machine learning
- 2. Adversarial learning for semi-supervised semantic segmentation
- 3. DropBlock： A regularization method for convolutional networks
- 4. 5.Adversarial Training Methods for Semi-Supervised Text Classification
- 5. Pseudo-Label：The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
- 6. 论文共读 | “阳奉阴违”的半监督学习算法 - Virtual Adversarial Training
- 7. 《Adversarial learning for weakly-supervised social network alignment》翻译
- 8. 论文：Adversarial Learning for Semi-Supervised Semantic Segmentation
- 9. 《DropBlock: A regularization method for convolutional networks》笔记
- 10. （原）DropBlock A regularization method for convolutional networks
- 更多相关文章...
- • Scala for循环 - Scala教程
- • Lua for 循环 - Lua 教程
- • RxJava操作符（七）Conditional and Boolean
- • Java Agent入门实战（一）-Instrumentation介绍与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Regularization method for machine learning
- 2. Adversarial learning for semi-supervised semantic segmentation
- 3. DropBlock： A regularization method for convolutional networks
- 4. 5.Adversarial Training Methods for Semi-Supervised Text Classification
- 5. Pseudo-Label：The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks
- 6. 论文共读 | “阳奉阴违”的半监督学习算法 - Virtual Adversarial Training
- 7. 《Adversarial learning for weakly-supervised social network alignment》翻译
- 8. 论文：Adversarial Learning for Semi-Supervised Semantic Segmentation
- 9. 《DropBlock: A regularization method for convolutional networks》笔记
- 10. （原）DropBlock A regularization method for convolutional networks