Tutorial: Knowledge Distillation

时间 2020-12-26

标签 Knowledge Distillation 繁體版

原文原文链接

概述 Knowledge Distillation(KD)一般指利用一个大的teacher网络作为监督，帮助一个小的student网络进行学习，主要用于模型压缩。其方法主要分为两大类 Output Distillation Feature Distillation Output Distillation Motivation 主要拉近teacher和student最终输出的距离，参考论文：Dis

>>阅读原文<<

1. Tutorial: Knowledge Distillation
2. Knowledge Distillation
3. Knowledge Distillation 笔记
4. Awesome Knowledge-Distillation
5. Similarity-Preserving Knowledge Distillation
6. 论文Relational Knowledge Distillation
7. Correlation Congruence for Knowledge Distillation
8. knowledge distillation 论文阅读之：ResKD: Residual-Guided Knowledge Distillation
9. knowledge distillation 论文阅读之：Triplet Loss for Knowledge Distillation
10. Knowledge Distillation论文阅读（2）：Learning Efficient Object Detection Models with Knowledge Distillation
更多相关文章...
• C# 结构体（Struct） - C#教程
• Lua 数组 - Lua 教程
• Git五分钟教程
• Flink 数据传输及反压详解

最新文章

1. [最佳实践]了解 Eolinker 如何助力远程办公
2. katalon studio 安装教程
3. 精通hibernate（harness hibernate oreilly）中的一个”错误“
4. ECharts立体圆柱型
5. 零拷贝总结
6. 6 传输层
7. Github协作图想
8. Cannot load 32-bit SWT libraries on 64-bit JVM
9. IntelliJ IDEA 找其历史版本
10. Unity3D(二)游戏对象及组件

本站公众号

欢迎关注本站公众号,获取更多信息

1. Tutorial: Knowledge Distillation
2. Knowledge Distillation
3. Knowledge Distillation 笔记
4. Awesome Knowledge-Distillation
5. Similarity-Preserving Knowledge Distillation
6. 论文Relational Knowledge Distillation
7. Correlation Congruence for Knowledge Distillation
8. knowledge distillation 论文阅读之：ResKD: Residual-Guided Knowledge Distillation
9. knowledge distillation 论文阅读之：Triplet Loss for Knowledge Distillation
10. Knowledge Distillation论文阅读（2）：Learning Efficient Object Detection Models with Knowledge Distillation

>>更多相关文章<<