type
status
date
slug
summary
tags
category
icon
password
论文网站：
arXiv.orgDataset Distillation by Matching Training Trajectories
arXiv.org
arXiv.orgDataset Distillation by Matching Training TrajectoriesDataset Distillation by Matching Training Trajectories
Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full dataset. In this...
arXiv.org代码网站：
知乎介绍：![]()
zhuanlan.zhihu.com![zhuanlan.zhihu.com]()
![]()
zhuanlan.zhihu.com
我们的方法通过直接优化假图像来提炼合成数据集，以诱导与完整的真实数据集相似的网络训练动态。我们训练“学生”网络对合成数据进行多次迭代，测量在真实数据上训练的“学生”和“专家”网络之间的参数空间误差，并通过所有学生网络更新进行反向传播以优化合成像素。
算法框架：
- Author:Coding
- URL:http://preview.tangly1024.com/article/2adad491-793a-81e6-a7a4-d456701987b6
- Copyright:All articles in this blog, except for special statements, adopt BY-NC-SA agreement. Please indicate the source!
Relate Posts
