《Semi-Supervised Semantic Segmentation with Cross-Consistency Training》 2020CVPR 论文阅读

在这项工作中,作者首先观察到,对于语义分割,低密度区域在隐藏表示中比在输入中更明显。

作者提出了交叉一致性训练,其中预测的不变性是施加不同的扰动在编码器输出上

 

Cross-Consistency Training

该模型包含一个共享的encoder,一个main decoder和K个辅助decoder

对于有标签的数据,使用Cross-Entropy (CE)来进行训练

对于无标签的数据,使用共享的encoder得到中间特征

使用扰动函数pr对encoder的输出进行扰动,每一个扰动可以用于多个辅助decoder,

将K个扰动版本的输出 输入到辅助decoder中

使用mean squared error (MSE)作为距离衡量,旨在缩小main decoder和辅助decoder之间的差异

为了避免使用主编码器的初始噪声预测,Wu沿着高斯曲线从零开始上升到一个固定的权重λu。具体地,在每次训练中,有无标签的样本数量是相同的

Note:无标签的loss不反向更新main-decoder,只有有标签的才会用来训练main-decoder

Prediction based perturbations.

Feature based perturbations

F-Noise:

F-Drop:

Prediction based perturbations.

Guided Masking:

使用掩码将检测到的object或者上下文mask掉

Guided Cutout (G-Cutout):

Intermediate VAT (I-VAT):

注入对抗扰动

Random perturbations.

 

Practical considerations

在每次迭代训练中,label 和 unlabel 采样数量相同,并且在label的数据上迭代的次数更多,因此过拟合的风险更大

Avoiding Overfitting.

作者发现在训练中逐渐释放监督信号有助于性能提升

将output表示为在像素上的分布概率

作者仅使用分布概率小于某一阈值的,

在训练期间逐渐增大阈值

Exploiting weak-labels

使用一些弱标签样本,比如image-level label,来进一步增强特征编码器H

引入了一个分类分支,使用一个pooling层,然后接一个分类器,使用binary CE loss在分类任务上预训练encoder

预训练的encoder和分类分支可用于生成pixel-level 伪标签

 

Cross-Consistency Training on Multiple Domains

 


 

 

 

 

 

  • 0
    点赞
  • 9
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Semi-supervised classification with graph convolutional networks (GCNs) is a method for predicting labels for nodes in a graph. GCNs are a type of neural network that operates on graph-structured data, where each node in the graph represents an entity (such as a person, a product, or a webpage) and edges represent relationships between entities. The semi-supervised classification problem arises when we have a graph where only a small subset of nodes have labels, and we want to predict the labels of the remaining nodes. GCNs can be used to solve this problem by learning to propagate information through the graph, using the labeled nodes as anchors. The key idea behind GCNs is to use a graph convolution operation to aggregate information from a node's neighbors, and then use this aggregated information to update the node's representation. This operation is then repeated over multiple layers, allowing the network to capture increasingly complex relationships between nodes. To train a GCN for semi-supervised classification, we use a combination of labeled and unlabeled nodes as input, and optimize a loss function that encourages the network to correctly predict the labels of the labeled nodes while also encouraging the network to produce smooth predictions across the graph. Overall, semi-supervised classification with GCNs is a powerful and flexible method for predicting labels on graph-structured data, and has been successfully applied to a wide range of applications including social network analysis, drug discovery, and recommendation systems.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值