Abstract
Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling efforts. To ease the labeling efforts, we propose a novel weakly supervised human parsing method which only requires simple object keypoint annotations for learning. We develop an iterative learning method to generate pseudo part segmentation masks from keypoint labels. With these pseudo masks, we train an FCN network to output pixel-level human parsing predictions. Furthermore, we develop a correlation network to perform joint prediction of part and object segmentation masks and improve the segmentation performance. The experiment results show that our weakly supervised method is able to achieve very competitive human parsing results. Despite our method only uses simple keypoint annotations for learning, we are able to achieve comparable performance with fully supervised methods which use the expensive pixel-level annotations.
Abstract (translated)
完全卷积网络（FCN）近年来在人类解析方面取得了巨大成功。在传统的人工解析任务中，需要像素级标记来指导训练，这通常涉及巨大的人类标记工作。为了简化标注工作，我们提出了一种新颖的弱监督人类解析方法，该方法只需要简单的对象关键点注释来进行学习。我们开发了一种迭代学习方法，用于从关键点标签生成伪部分分割掩模。利用这些伪掩码，我们训练FCN网络以输出像素级人类解析预测。此外，我们开发了一个相关网络，以执行部件和对象分割掩模的联合预测，并提高分割性能。实验结果表明，我们的弱监督方法能够实现非常有竞争力的人类解析结果。尽管我们的方法仅使用简单的关键点注释进行学习，但我们能够使用昂贵的像素级注释的完全监督方法实现相当的性能。
URL
https://arxiv.org/abs/1809.05285
