论文标题
密集的FixMatch：一种简单的半监督学习方法，用于像素的预测任务
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
论文作者
论文摘要
我们提出了密集的FixMatch，这是一种简单的方法，用于在线半监督学习密集和结构化的预测任务，结合了伪标记和一致性正规化，通过强大的数据增强。我们可以通过在伪标签上添加匹配操作，使FixMatch在半监督的学习问题中应用超出图像分类。这使我们仍然可以使用数据增强管道的全部强度，包括几何变换。我们将其评估在半监督的语义细分方面，对城市景观和Pascal VOC，具有不同百分比的标记数据和消融设计选择和超参数。与仅使用标记的数据进行监督学习相比，密集的FixMatch显着改善了结果，并使用标记的样品的1/4接近其性能。
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled data and ablate design choices and hyper-parameters. Dense FixMatch significantly improves results compared to supervised learning using only labeled data, approaching its performance with 1/4 of the labeled samples.
