小样本学习
zhaoyuyu_nudt
这个作者很懒,什么都没留下…
展开
-
Differentiable plasticity: training plastic neural networks withbackpropagation
http://proceedings.mlr.press/v80/miconi18a/miconi18a.pdf文章目录AbstractIntroductionRelated workintroAbstract1、 通过梯度下降 优化可微塑性2、 在测试集合中, 训练集中从未见过的自然图像集合, 能重建。3、 可以解决一般的元学习任务。IntroductionMany of the recent spectacular successes in machine learn-ing invol原创 2020-12-18 22:11:28 · 285 阅读 · 0 评论 -
ReID| Progressive Learning for Person Re-Identification With One Example (已读完)
文章目录读书笔记创新点可能着手的切入点、我的疑问Introduction1、Re-ID 从全监督到半监督2、半监督方法中 从静态采样策略 , 到本文的 动态采样策略3、从 a labeled tracklet 到 only one image labeled for each identity。4、训练数据: 从两种数据、到三种数据5、 exclusive loss 排他性损失 用于优化CNN , 使用unselected index-labeled data6、联合训练方法 joint learnin原创 2020-08-02 22:13:30 · 1004 阅读 · 0 评论 -
Overview of Zero-Shot Learning - 1.3
Controbutions and Article Organization .Controbutions:Although there are surveys on transfer learning , and particularly on heterogeneous transfer learning . they do not cover the topic of zero-sho...原创 2019-03-14 10:48:30 · 215 阅读 · 0 评论 -
Overview of Zero-Shot learning
title: SSL Review -2date: 2019-03-10 10:10:25tags: SSLmathjax: trueOverview of Zero-Shot learningthe seen classesthe classes covered by labeled training instances in the feauture spaceth...原创 2019-03-11 16:43:14 · 356 阅读 · 0 评论 -
Overview of Zero-Shot learning - 1.2
Learning Settings 1.2The goal of Zero-Shot Learning: learn the Classifierfu(⋅)f^u(\cdot)fu(⋅).Model learning : if Information about testing instances is involved , the learned model is transductive...原创 2019-03-11 17:16:01 · 156 阅读 · 0 评论