论文阅读笔记《Learning to Select Base Classes for Few-shot Classification》
核心思想 本文提出一种通过优化基础类别选择的方式改善小样本学习的算法。许多小样本分类算法都是基于迁移学习的方式，首先在基础数据集上进行预训练，然后在新的小样本数据集上做微调训练。本文并没有研究如何改善特征提取网络或分类器的结构，而是另辟蹊径的考虑如何选择最佳的基础数据集，更具体地说就是选择哪些类别的基础数据集用于预训练。解决这一问题存在两大困难：1.如果对基础数据集中的所有类别组合都进行尝试，
相关文章
- 1. 论文阅读笔记 | (ECCV 2018) Learning to Navigate for Fine-grained Classification
- 2. Machine Learning & Deep Learning 论文阅读笔记
- 3. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 4. 论文阅读笔记《Meta-learning for semi-supervised few-shot classification》
- 5. 论文阅读笔记《SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning》
- 6. 论文阅读笔记《Dense Classification and Implanting for Few-Shot Learning》
- 7. 论文阅读笔记《Meta-SGD: Learning to Learn Quickly for Few-Shot Learning》
- 8. 论文阅读笔记《Learning to Compare: Relation Network for Few-Shot Learning》
- 9. 论文阅读 Prototypical Networks for Few-shot Learning
- 10. 论文阅读笔记：Learning Attribute-to-Feature Mappings for Cold-Start Recommendations
- 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 | (ECCV 2018) Learning to Navigate for Fine-grained Classification
- 2. Machine Learning & Deep Learning 论文阅读笔记
- 3. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 4. 论文阅读笔记《Meta-learning for semi-supervised few-shot classification》
- 5. 论文阅读笔记《SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning》
- 6. 论文阅读笔记《Dense Classification and Implanting for Few-Shot Learning》
- 7. 论文阅读笔记《Meta-SGD: Learning to Learn Quickly for Few-Shot Learning》
- 8. 论文阅读笔记《Learning to Compare: Relation Network for Few-Shot Learning》
- 9. 论文阅读 Prototypical Networks for Few-shot Learning
- 10. 论文阅读笔记：Learning Attribute-to-Feature Mappings for Cold-Start Recommendations