论文标题
Nopeopleallowed：弱监督语义细分的三步方法
NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation
论文作者
论文摘要
我们提出了一种新颖的方法，用于弱监督的语义细分，该方法包括连续三个步骤。前两个步骤从图像级注释数据中提取高质量的伪掩模，然后将其用于在第三步上训练分割模型。提出的方法还解决了数据中的两个问题：类不平衡和缺少标签。仅使用图像级注释作为监督，我们的方法能够分割各种类和复杂的对象。它在测试集上达到37.34的意思是，在弱监督的语义细分任务中，在盖子挑战中排名第三。
We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps. The first two steps extract high-quality pseudo masks from image-level annotated data, which are then used to train a segmentation model on the third step. The presented approach also addresses two problems in the data: class imbalance and missing labels. Using only image-level annotations as supervision, our method is capable of segmenting various classes and complex objects. It achieves 37.34 mean IoU on the test set, placing 3rd at the LID Challenge in the task of weakly supervised semantic segmentation.
