论文信息

论文标题:Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples
论文作者:Mahmoud AssranMathilde CaronIshan MisraPiotr BojanowskiArmand JoulinNicolas Ballas
论文来源:NeurIPS 2021
论文地址:download 
论文代码:download
视屏讲解:click

1 介绍

  提出问题:充分利用无标注目标;

  解决办法:对无标注数据使用一种可信的伪标签策略;

2 方法

2.1 整体框架

  

2.2 问题定义

  We consider a large dataset of unlabeled images  $\mathcal{D}=   \left(\mathrm{x}_{i}\right)_{i \in[1, N]}$  and a small support dataset of annotated images  $\mathcal{S}=\left(\mathbf{x}_{s i}, y_{i}\right)_{i \in[1, M]}$ , with  $M \ll N  $.Our goal is to learn image representations by leveraging both  $\mathcal{D}$  and  $\mathcal{S}$  during pretraining. After pre-training with  $\mathcal{D}$  and  $\mathcal{S}$ , we fine-tune the learned representations using only the labeled set  $\mathcal{S}$ .

2.3 相似度分类器

  公式:

    $\pi_{d}\left(z_{i}, \mathbf{z}_{\mathcal{S}}\right)=\sum_{\left(z_{s_{j}}, y_{j}\right) \in \mathbf{z}_{\mathcal{S}}}\left(\frac{d\left(z_{i}, z_{s j}\right)}{\sum_{z_{s k} \in \mathbf{z}_{\mathcal{S}}} d\left(z_{i}, z_{s k}\right)}\right) y_{j}$

  Note:Soft Nearest Neighbours strategy

  其中:

    $d(a, b) =\exp \left( \frac{a^{T} b}{\|a\|\|b\| \tau} \right)$

  简化:

    $p_{i}:=\pi_{d}\left(z_{i}, \mathbf{z}_{\mathcal{S}}\right)=\sigma_{\tau}\left(z_{i} \mathbf{z}_{\mathcal{S}}^{\top}\right) \mathbf{y}_{\mathcal{S}}$

  Note:$p_{i} \in[0,1]^{K}$

  锐化:

    $\left[\rho\left(p_{i}\right)\right]_{k}:=\frac{\left[p_{i}\right]_{k}^{1 / T}}{\sum_{j=1}^{K}\left[p_{i}\right]_{j}^{1 / T}}, \quad k=1, \ldots, K$

  Note:锐化目标会鼓励网络产生自信的预测,避免模型崩溃问题。

2.4 训练目标

  总目标:

    $\frac{1}{2 n} \sum_{i=1}^{n}\left(H\left(\rho\left(p_{i}^{+}\right), p_{i}\right)+H\left(\rho\left(p_{i}\right), p_{i}^{+}\right)\right)-H(\bar{p})$

  ME-MAX 正则化项:$H(\bar{p})$

  其中:

    $\bar{p}:=\frac{1}{2 n} \sum_{i=1}^{n}\left(\rho\left(p_{i}\right)+\right.   \left.\rho\left(p_{i}^{+}\right)\right) $ 表示所有未标记表示的锐化预测的平均值;

  该正则化项在鼓励个体预测有信心的同时,鼓励平均预测接近均匀分布。ME-MAX 正则化项之前已在判别式无监督聚类社区中用于平衡学习的聚类大小[35]。

  Note:交叉熵

# Example of target with class indices
loss = nn.CrossEntropyLoss()
input = torch.randn(3, 5, requires_grad=True)
target = torch.empty(3, dtype=torch.long).random_(5)
output = loss(input, target)
output.backward()
# Example of target with class probabilities
input = torch.randn(3, 5, requires_grad=True)
target = torch.randn(3, 5).softmax(dim=1)
output = loss(input, target)
output.backward()

3 总结

  略

论文解读(PAWS)《Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples》的更多相关文章

  1. 【论文阅读】Deep Clustering for Unsupervised Learning of Visual Features

    文章:Deep Clustering for Unsupervised Learning of Visual Features 作者:Mathilde Caron, Piotr Bojanowski, ...

  2. 论文解读《Momentum Contrast for Unsupervised Visual Representation Learning》俗称 MoCo

    论文题目:<Momentum Contrast for Unsupervised Visual Representation Learning> 论文作者: Kaiming He.Haoq ...

  3. 论文解读《Deep Resdual Learning for Image Recognition》

    总的来说这篇论文提出了ResNet架构,让训练非常深的神经网络(NN)成为了可能. 什么是残差? "残差在数理统计中是指实际观察值与估计值(拟合值)之间的差."如果回归模型正确的话 ...

  4. 【公式详解】【优秀论文解读】EDPLVO: Efficient Direct Point-Line Visual Odometry

    前言 多的不说哈 2022最佳优秀论文 来自美团无人机团队 作者提出了一种使用点和线的高效的直接视觉里程计(visual odometry,VO)算法-- EDPLVO .他们证明了,2D 线上的 3 ...

  5. 论文解读(SimCLR)《A Simple Framework for Contrastive Learning of Visual Representations》

    1 题目 <A Simple Framework for Contrastive Learning of Visual Representations> 作者: Ting Chen, Si ...

  6. 自监督学习(Self-Supervised Learning)多篇论文解读(下)

    自监督学习(Self-Supervised Learning)多篇论文解读(下) 之前的研究思路主要是设计各种各样的pretext任务,比如patch相对位置预测.旋转预测.灰度图片上色.视频帧排序等 ...

  7. 自监督学习(Self-Supervised Learning)多篇论文解读(上)

    自监督学习(Self-Supervised Learning)多篇论文解读(上) 前言 Supervised deep learning由于需要大量标注信息,同时之前大量的研究已经解决了许多问题.所以 ...

  8. 论文解读(BYOL)《Bootstrap Your Own Latent A New Approach to Self-Supervised Learning》

    论文标题:Bootstrap Your Own Latent A New Approach to Self-Supervised Learning 论文方向:图像领域 论文来源:NIPS2020 论文 ...

  9. 论文笔记之:Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

    论文笔记之:Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning  2017-06-06  21: ...

  10. Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记

    Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记 arXiv 摘要:本文提出了一种 DRL 算法进行单目标跟踪 ...

随机推荐

  1. drf视图类

    1 2个视图基类 # django 内置的View# drf 的APIView ,继承自View# GenericAPIView -两个重要的类属性:    queryset = Book.objec ...

  2. vite + vue安装 注意事项

    一.要求node版本必须>12.0.0 1.node 如何升级 · 执行npm cache clean -f 清除缓冲 · npm install -g n 安装 n 模块  n模块用于管理 n ...

  3. Docker部署Nginx报错 WARNING: IPv4 forwarding is disabled. Networking will not work.

    Docker 部署 Nginx 报错 WARNING: IPv4 forwarding is disabled. Networking will not work. [root@localhost ~ ...

  4. [C#]索引指示器

    参考代码: using System; namespace IndexerDemo { class StuInfo { public string Name; public string[] CouN ...

  5. pymysql安装后使用报错处理

    1.django启动报错: Error loading MySQLdb module. Did you install mysqlclient? 原因:初次安装配置pymysql时需要在__init_ ...

  6. idea开发使用外置tomcat配置

    1. 添加依赖 <dependency> <groupId>org.apache.tomcat.embed</groupId> <artifactId> ...

  7. windows下查找端口、PID、查找进程、杀死进程

    查找端口 netstat -ano|findstr "1099" TCP 0.0.0.0:1099 0.0.0.0:0 LISTENING 10120 TCP [::]:1099 ...

  8. MYSQL DUAL(伪表)

    #DUAL是一个伪表,不存在的表. SELECT 8*9 FROM DUAL #输出72

  9. lnmp重新安装mysql

    安装mysql好长时间,一直没去管,后来一直频繁重启,各种网上找方案去解决,最后问题太异常,一顿操作猛如虎之后把mysql彻底搞垮,无奈只能进行重装. whereis mysql mysql: /us ...

  10. DBeaver的使用

    1.下载安装: https://dbeaver.io/download/ 2.下载后解压到指定目录,双击安装包: 然后 进行连接,在连接数据库的时候,会提示下载文件,下载的时候老是出错,选择强制下载就 ...