Learning the relationship between weak and strong perturbations has been considered a major part of semi-supervised semantic segmentation. We observed two problems with a publicly used perturbation method, which randomly generates a mask with a single large bounding box. The large single bounding box that entirely covers the important object components in an image, hindering the model from capturing partial object information. Furthermore, training the model with a single large bounding box as an image-level perturbation causes the model to be biased towards the shape of the large squared box, rather than the deformable object component shapes. In this paper, we propose Subdivided Mask Dispersion Framework (SMDF) to solve these problems. Our framework disperses the large squared box into small multi-scale boxes, capturing the crucial multi-scaled object components in the image. SMDF achieves state-of-the-art performance on five data partitions of PASCAL dataset and three partitions of Extended SBD dataset. Our extensive ablation studies show the effectiveness of dispersed small multi-scale bounding boxes in semi-supervised semantic segmentation.

中文翻译：

---

用于半监督语义分割的细分掩模分散框架

学习弱扰动和强扰动之间的关系被认为是半监督语义分割的主要部分。我们观察到公开使用的扰动方法存在两个问题，该方法随机生成具有单个大边界框的掩模。大的单一边界框完全覆盖了图像中的重要对象组件，阻碍了模型捕获部分对象信息。此外，使用单个大边界框作为图像级扰动来训练模型会导致模型偏向于大方框的形状，而不是可变形对象组件的形状。在本文中，我们提出了细分掩模色散框架（SMDF）来解决这些问题。我们的框架将大方形框分散成小的多尺度框，捕获图像中关键的多尺度对象组件。SMDF 在 PASCAL 数据集的五个数据分区和扩展 SBD 数据集的三个分区上实现了最先进的性能。我们广泛的消融研究表明了分散的小型多尺度边界框在半监督语义分割中的有效性。