Chen Huaian, Jin Yi, Jin Guoqiang, Zhu Changan, Chen Enhong
IEEE Trans Neural Netw Learn Syst. 2022 Sep;33(9):4991-5003. doi: 10.1109/TNNLS.2021.3066850. Epub 2022 Aug 31.
Most of the recent image segmentation methods have tried to achieve the utmost segmentation results using large-scale pixel-level annotated data sets. However, obtaining these pixel-level annotated training data is usually tedious and expensive. In this work, we address the task of semisupervised semantic segmentation, which reduces the need for large numbers of pixel-level annotated images. We propose a method for semisupervised semantic segmentation by improving the confidence of the predicted class probability map via two parts. First, we build an adversarial framework that regards the segmentation network as the generator and uses a fully convolutional network as the discriminator. The adversarial learning makes the prediction class probability closer to 1. Second, the information entropy of the predicted class probability map is computed to represent the unpredictability of the segmentation prediction. Then, we infer the label-error map of the segmentation prediction and minimize the uncertainty on misclassified regions for unlabeled images. In contrast to existing semisupervised and weakly supervised semantic segmentation methods, the proposed method results in more confident predictions by focusing on the misclassified regions, especially the boundary regions. Our experimental results on the PASCAL VOC 2012 and PASCAL-CONTEXT data sets show that the proposed method achieves competitive segmentation performance.
最近的大多数图像分割方法都试图使用大规模的像素级标注数据集来实现最佳分割结果。然而，获取这些像素级标注的训练数据通常既繁琐又昂贵。在这项工作中，我们解决半监督语义分割任务，该任务减少了对大量像素级标注图像的需求。我们提出了一种半监督语义分割方法，通过两个部分提高预测类别概率图的置信度。首先，我们构建一个对抗框架，将分割网络视为生成器，并使用全卷积网络作为判别器。对抗学习使预测类别概率更接近1。其次，计算预测类别概率图的信息熵以表示分割预测的不可预测性。然后，我们推断分割预测的标签错误图，并最小化未标记图像误分类区域上的不确定性。与现有的半监督和弱监督语义分割方法相比，所提出的方法通过关注误分类区域，特别是边界区域，产生更具置信度的预测。我们在PASCAL VOC 2012和PASCAL-CONTEXT数据集上的实验结果表明，所提出的方法实现了具有竞争力的分割性能。
