论文阅读笔记《Attentive Weights Generation for Few Shot Learning via Information Maximization》
核心思想 本文提出一种基于权重生成的小样本学习算法（AWGIM），这种类型的方法之前在小样本目标检测算法中见到过，就是直接用一个生成器生成分类器的权重参数。本文与其他相关算法（LEO）的区别在于在生成分类器权重时，不仅考虑支持集图像，而且考虑查询集图像。为了实现这一目的，本文引入了互信息（Mutual Information，MI）和注意力机制。整个网络的流程如下图所示 首先，介绍一下什么
相关文章
- 1. 论文阅读笔记-CVPR 2020: Attentive Weights Generation for Few Shot Learning via Information Maximization
- 2. 论文阅读笔记《Learning Embedding Adaptation for Few-Shot Learning》
- 3. 论文阅读 Prototypical Networks for Few-shot Learning
- 4. 论文阅读笔记《Few-Shot Learning Through an Information Retrieval Lens》
- 5. 论文阅读笔记《Few-shot Learning via Saliency-guided Hallucination of Samples》
- 6. 论文阅读笔记《Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders》
- 7. 论文阅读-Prototype Rectification for Few-Shot Learning
- 8. 论文阅读Adaptive Subspaces for Few-Shot Learning
- 9. 论文阅读笔记《Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning》
- 10. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
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. 论文阅读笔记-CVPR 2020: Attentive Weights Generation for Few Shot Learning via Information Maximization
- 2. 论文阅读笔记《Learning Embedding Adaptation for Few-Shot Learning》
- 3. 论文阅读 Prototypical Networks for Few-shot Learning
- 4. 论文阅读笔记《Few-Shot Learning Through an Information Retrieval Lens》
- 5. 论文阅读笔记《Few-shot Learning via Saliency-guided Hallucination of Samples》
- 6. 论文阅读笔记《Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders》
- 7. 论文阅读-Prototype Rectification for Few-Shot Learning
- 8. 论文阅读Adaptive Subspaces for Few-Shot Learning
- 9. 论文阅读笔记《Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning》
- 10. 论文阅读笔记《Meta-Learning of Neural Architectures for Few-Shot Learning》