论文标题
一个奇怪的技巧，可以改善您的半弱监督语义细分模型
One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model
论文作者
论文摘要
半弱监督的语义细分（SWSSS）旨在训练模型，以基于少数带有像素级标签的图像以及仅具有图像级标签的更多图像来识别图像中的对象。大多数现有的SWSS算法从图像分类器中提取像素级伪标签 - 这是一个非常困难的任务，因此需要复杂的体系结构并在完全监督的验证集上进行大量的超参数调整。我们提出了一种称为预测过滤的方法，该方法并没有提取伪标记，而只是将分类器用作分类器：它忽略了分类器没有信心的类中的任何细分预测。将此简单的后处理方法添加到基准中，与先前的SWSSS算法相比，结果具有竞争力或更好的结果。此外，它与伪标签方法兼容：将预测过滤添加到现有的SWSSS算法中进一步改善了细分性能。
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS algorithms extract pixel-level pseudo-labels from an image classifier - a very difficult task to do well, hence requiring complicated architectures and extensive hyperparameter tuning on fully-supervised validation sets. We propose a method called prediction filtering, which instead of extracting pseudo-labels, just uses the classifier as a classifier: it ignores any segmentation predictions from classes which the classifier is confident are not present. Adding this simple post-processing method to baselines gives results competitive with or better than prior SWSSS algorithms. Moreover, it is compatible with pseudo-label methods: adding prediction filtering to existing SWSSS algorithms further improves segmentation performance.
