Low-shot Visual Recognition by Shrinking and Hallucinating Features
3个组成
It employs a learner, two training phases, and one testing phase.
1. learner
The learner is assumed to be composed of a feature extractor and a multi-class classifier.
2. traing phased one （representation learning）
During representation learning (training phase one), the
learner receives a fixed set of base categories CbaseC_{base}Cbase, and a dataset D containing a large number of examples for each category in Cbase. The learner uses D to set the parameters of its feature extractor.
产生新的类别
Any two examples z1 and z2 belonging to the same category represent a plausible transformation. Then, given a novel category example x, we want to apply to x the transformation that sent z1 to z2. That is, we want to complete the transformation “analogy” z1 : z2 :: x : ?.
We do this by training a function G that takes as input the concatenated feature vectors of the three examples [φ(x), φ(z1), φ(z2)].G是MLP
3. second phase （low-shot learning）
the learner is given a set of categories ClC_lCl that it must learn to distinguish. ClC_lCl = CbaseC_{base}Cbase ∪\cup∪ CnovelC_{novel}Cnovel is a mix of base categories Cbase, and unseen novel categories Cnovel.
对于CnovelC_{novel}Cnovel，仅仅有k-shot
4.testing phase
the learnt model predicts labels from the combined label space ClC_lCl = CbaseC_{base}Cbase ∪\cup∪ CnovelC_{novel}Cnovel on a set of previously unseen test images.
模型（Learning to generate new examples）
核心：
，通过z1:z2,类比x:?.
利用D训练G， 为用于类比的2组双胞胎。预测结果为：。损失函数。与上文中的特征表达误差与分类误差对应。
Low-shot Visual Recognition by Shrinking and Hallucinating Features相关推荐
- 【Paper】CNN-LSTM：Long-term Recurrent Convolutional Networks for Visual Recognition and Description
论文期刊:CVPR 2015 (oral) 论文被引:3673 (04/24/20) 论文原文:点击此处 该论文是 CNN-LSTM 的开山鼻祖,主要用于生成图像描述.初稿发布于2014年,拿到了 C ...
- Paper8：Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition 还未读
- 《BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition》笔记
Paper:<BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition& ...
- [SPP-NET]Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
基于空间金字塔池化的卷积神经网络物体检测 原文地址:http://blog.csdn.net/hjimce/article/details/50187655 作者:hjimce 一.相关理论 本篇博文 ...
- 目标检测--Spatial pyramid pooling in deep convolutional networks for visual recognition(PAMI, 2015)
Spatial pyramid pooling in deep convolutional networks for visual recognition 作者: Kaiming He, Xiangy ...
- Convolutional Neural Networks for Visual Recognition 1
Introduction 这是斯坦福计算机视觉大牛李菲菲最新开设的一门关于deep learning在计算机视觉领域的相关应用的课程.这个课程重点介绍了deep learning里的一种比较流行的模型 ...
- CVPR2018 Tutorial 之 Visual Recognition and Beyond
这一tutorials主要带来了目前视觉识别的前沿研究以及在高级任务中的应用.其中前三个演讲将会覆盖视觉识别背后支撑的方法和原理,包括图像分类.目标检测以及实例分割和语义分割等.而后两个演讲将主要集中 ...
- 【CS231n_2017】1-Introduction to CNN for Visual Recognition
本专栏根据斯坦福大学2017年公开课CS231n的视频教程整理学习资料,做学习笔记. 首先简单介绍CS231n,又称Convolutional Neural Networks for Visu ...
- BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
文章目录 概 主要内容 采样方式 权重 α \alpha α Inference phase 代码 Zhu B., Cui Q., Wei X. and Chen Z. BBN: Bilateral- ...
- Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition
(ICCV 2011 CODE)Discriminative Learning of Relaxed Hierarchy for Large-scale Visual Recognition 本文的二 ...
最新文章
- 有关RDS上只读实例延时分析-同适用于自建MySQL主从延时分析判断
- 数据备份软件,BackBone,NetVault,网络存储备份,系统集成
- mysql修改最后一条记录删除第一条记录
- Jenkins TFS配置
- 什么是分布式计算系统？—Vecloud微云
- Sqlite使用技巧集锦
- QGraphicsWidget收不到鼠标、键盘消息解决
- Netty4.x中文教程系列(二) Hello World !
- 使用乱序标签来控制HTML的输出效果
- 小甲鱼java视频_b站有哪些好的java视频?
- pscad仿真数据提取方法
- fritzing元件太少_Arduino电路设计软件Fritzing
- 四大行业晋身今秋求贤大户 游戏人才缺口奇大
- word 2019 方框中打勾
- 浅谈SEO（搜索引擎优化）
- node nvm 安装及使用
- 修改电脑C:\User\用户名文件夹的名字
- Placement service – placement安装（wallaby-allinone）
- Xilinx Zynq UltraScale+ MPSoC 介绍
- 【实战篇】执行计划3种看法，2种操作，4个误区