【论文粗读】Semi-Supervised Semantic Segmentationwith High- and Low-level Consistency

TPAMI2021  具有高、低一致性的半监督语义分割

代码地址:GitHub - sud0301/semisup-semseg

摘要:

使用两个网络分支,将半监督分类与包括自训练在内的半监督分割联系起来。双分支方法减少了使用少量标签进行训练时典型的低水平和高水平伪影。

来自P ASCAL VOC数据集的图像(a)及其groundtruth分割掩码(b)。预测(c)通过5%标记样本的监督训练获得。使用其他95%的未标记图像,我们基于GAN的分支改进了形状估计(d)。第二个分支通过消除误报(e)来增加高级一致性。(f) 显示在100%像素标记样本上训练时的输出。

网络框图

整体思路

利用分类来辅助分割,通过MLMT网络来进行分类,用好的分类网络来挑选分割结果,把不需要的类别赋予较小的权重来解决一开始提到的伪影现象。

s4GAN Branch是一个基于GAN的分割网络,里面还包括一个self-training loss 来平衡D和G的生成,思路就是选取无标签图像的可靠预测,来当做伪标签进行监督训练。因此D有两个输出,一个是用分数来作为预测分割质量的置信图。一个是判断真假的判别输出。

MLMT Branch是一个基于老师学生网络的半监督网络

  • 1
    点赞
  • 2
    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.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
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