用真实标签提升半监督分割精度，有效缓解伪标签误差问题
Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
- 将有标签图像的真标签区域粘贴到无标签图像上，避免伪标签错误
- 引入特征判别器使无标签图像的特征分布更接近有标签图像
- 在两个医学数据集上平均提升2.07%的mIoU，适合医疗图像分割场景
在语义分割中，生成像素级标签成本高昂。为解决此问题，半监督学习利用少量标注图像与大量未标注图像提升性能。传统方法ClassMix通过将未标注图像的伪标签粘贴到其他图像实现增强，但因依赖不准确的伪标签，存在风险。此外，标注与未标注图像间存在数据质量差异，影响特征表示。本文提出两项改进：首先，将有标签图像的真实类别标签及其对应区域粘贴至未标注图像及其伪标签图像；其次，引入监督-无监督特征判别器，训练模型使未标注图像的预测结果更接近标注图像。在Chase和COVID-19数据集上的实验表明，相比传统半监督方法，平均mIoU提升2.07%。
原文摘要 · Abstract (English)
In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to enhance the performance, has gained attention. A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images. However, since ClassMix performs operations using pseudo-labels obtained from unlabeled images, there is a risk of handling inaccurate labels. Additionally, there is a gap in data quality between labeled and unlabeled images, which can impact the feature maps. This study addresses these two issues. First, we propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images. Second, we introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images. Experiments on the Chase and COVID-19 datasets demonstrated an average improvement of 2.07% in mIoU compared to conventional semi-supervised learning methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。