Regularizing Class-wise Predictions via Self-knowledge Distillation
解决的问题是图像分类模型的过拟合，做法利用类class-wise 正则化项。思想是比如上图，这个思想简单的作为KL散度中不动的一方，下面这个背景复杂的作为动的一方，在类别预测的概率分布上进行蒸馏，过滤掉黑暗知识。一个模型，两个不同的样本但是类别是一致的，带有标签。
相关文章
- 1. Knowledge Distillation via Route Constrained Optimization
- 2. Awesome Knowledge-Distillation
- 3. Understanding black-box predictions via influence functions_1703.04730_icml_best论文理解
- 4. （2017ICML Bestpaper）Understanding Black-box Predictions via Influence Functions 笔记
- 5. 论文笔记understanding black-box predictions via influence functions
- 6. 论文浅尝 | Understanding Black-box Predictions via Influence Func
- 7. Knowledge Distillation
- 8. Fast and Accurate Single Image Super-Resolution via Information Distillation Network
- 9. PaperNote-Fast and Accurate Single Image Super-Resolution via Information Distillation Network
- 10. 【distill.&transfer】Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
- 更多相关文章...
- • PHP is_uploaded_file() 函数 - PHP参考手册
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. Knowledge Distillation via Route Constrained Optimization
- 2. Awesome Knowledge-Distillation
- 3. Understanding black-box predictions via influence functions_1703.04730_icml_best论文理解
- 4. （2017ICML Bestpaper）Understanding Black-box Predictions via Influence Functions 笔记
- 5. 论文笔记understanding black-box predictions via influence functions
- 6. 论文浅尝 | Understanding Black-box Predictions via Influence Func
- 7. Knowledge Distillation
- 8. Fast and Accurate Single Image Super-Resolution via Information Distillation Network
- 9. PaperNote-Fast and Accurate Single Image Super-Resolution via Information Distillation Network
- 10. 【distill.&transfer】Deep Face Recognition Model Compression via Knowledge Transfer and Distillation