To address this problem, we propose a new 3D Cross-Pseudo Supervision (3D-CPS) method, a semi-supervised network architecture based on nnU-Net with the Cross-Pseudo Supervision method. We design a new nnU-Net based preprocessing. In addition, we set the semi-supervised loss weights to ...
CVPR 2021|June 2021 In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on...
两个网络的结构相同,但使用不同的初始化(作为不同的扰动),具体而言,2个网络backbone部分使用同样的ImageNet预训练权重,Segmentation Head部分使用不同的随机初始化权重。 上图中的Y1和Y2分别表示2个网络输出的one hot标签,⟶ 表示前向计算,− − → 表示监督信息的传播,//表示不进行梯度计算。 对于无标签数...
We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network,...
We proposed a novel multi-task semi-supervised method based on multi-branch cross pseudo supervision, called MS2MPS, which can efficiently utilize unlabeled data for semi-supervised medical image segmentation. The proposed method consists of two multi-task backbone networks with multiple output branches...
[CVPR 2021] Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision by Xiaokang Chen1, Yuhui Yuan2, Gang Zeng1, Jingdong Wang2. 1 Key Laboratory of Machine Perception (MOE), Peking University 2 Microsoft Research Asia. [Poster] [Video (YouTube)] Simpler Is Better ! News [July ...
A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision in training. Typically in recent work, the pseudo-labels are obtained by training a model on the labeled data, and then using confident predictions fr...
2.2 Pseudo Label 伪标签 互补标签:防止模型对噪声数据过拟合,加速模型训练 2.4 Cross Labeling Supervision 前文介绍过使用分类器自身生成的人工标签会有信息偏差,所以在CLS中提出了两种策略 2.4.1 Weighted Labeling 第一种方法是使用样本重加权处理错误的人工标签。 因为softmax后输出的最大概率分布更可能是准确的人...
强制两个分支中的两个上采样模块产生彼此接近的结果,即使它们处于不同的监督之下(source GT HR supervision 和target pseudo SR supervision)。 通过这种方式,对target branch实施间接的和对抗性的监督。 4、其他一些小策略 以上三个部分,是该方法的主要内容。其他还包括一些常见的策略,如下所示: (1)cycle image ...
Images with weak labels are then used to help obtain a reliable class activation mapping (CAM) at the class activation branch, and the dense conditional random fields (DenseCRFs) are used to generate high-quality pseudo labels. Finally, the strong label images and the weak label images that ...