Few-shot Learning with Meta Metric Learners
一、介绍 现有的基于元学习、度量学习的小样本学习方法在处理diverse domains和various classes上存在局限。元学习训练一个meta learner预测具有相同结构，但针对不同任务网络的权重。度量学习针对不同任务学习一个不随任务改变，适应所有任务的度量。当任务间差异较大时，度量学习将会失败，学不到这样的度量。作者提出了一个元度量学习的方法，利用度量学习的匹配网络作为base
相关文章
- 1. 论文阅读笔记《Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace》
- 2. (Fewshot detection)Review:RepMet: Representative-based metric learning for few-shot detection
- 3. 【2017_ICCV】Deep Metric Learning with Angular Loss
- 4. Large-scale Distance Metric Learning with Uncertainty
- 5. [Machine Learning]--Improving classification with the AdaBoost meta-algorithm
- 6. Learning a Similarity Metric Discriminatively, with Application to Face Verification.
- 7. What’s New in Deep Learning Research: Understanding Meta-Learning
- 8. Learning a Similarity Metric Discriminatively, with Application to Face Verification
- 9. M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning
- 10. The Rise of Meta Learning
- 更多相关文章...
- • XSLT
- • ASP ServerVariables 集合 - ASP 教程
- • Java Agent入门实战（三）-JVM Attach原理与使用
- • Java Agent入门实战（一）-Instrumentation介绍与使用
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《Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace》
- 2. (Fewshot detection)Review:RepMet: Representative-based metric learning for few-shot detection
- 3. 【2017_ICCV】Deep Metric Learning with Angular Loss
- 4. Large-scale Distance Metric Learning with Uncertainty
- 5. [Machine Learning]--Improving classification with the AdaBoost meta-algorithm
- 6. Learning a Similarity Metric Discriminatively, with Application to Face Verification.
- 7. What’s New in Deep Learning Research: Understanding Meta-Learning
- 8. Learning a Similarity Metric Discriminatively, with Application to Face Verification
- 9. M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning
- 10. The Rise of Meta Learning