An Empirical Study of the Collapsing Problem in Semi-Supervised 222D Human Pose Estimation
Rongchang Xie1, Chunyu Wang2, Wenjun Zeng2, Yizhou Wang3 1Center for Data Science, Peking University 2Microsoft Research Asia 3 Center on Frontiers of Computing Studies, CS Dept., Peking University {rongchangxie, {chnuwa,
Abstract
Most semi-supervised learning models are consistency-based, which leverage unlabeled images by maximizing the similarity between different augmentations of an image. But when we apply them to human pose estimation that has extremely imbalanced class distribution, they often collapse and predict every pixel in unlabeled images as background. We find this is because the decision boundary passes the high-density areas of the minor class so more and more pixels are gradually mis-classified as background. In this work, we present a surprisingly simple approach to drive the model to learn in the correct direction. For each image, it composes a pair of easy-hard augmentations and uses the more accurate predictions on the easy image to teach the network to learn pose information of the hard one. The accuracy superiority of teaching signals allows the network to be “monotonically” improved which effectively avoids collapsing. We apply our method to the state-of-the-art pose estimators and it further improves their performance on three public datasets. The source code and pretrained models have been released at https://github.com/xierc/Semi_Human_Pose.
中文速览
半监督学习用于2D人体姿态估计时，常因前景关节点像素远少于背景而发生“坍塌”，把未标注图像几乎所有像素都预测成背景。为此，方法为每张未标注图像构造一对难度不同的增强，用较容易增强得到的更可靠姿态热图作为教师信号，只指导较难增强的预测，并停止教师分支的梯度传播。实验表明，该策略能稳定训练、避免坍塌，在少量标注数据下将平均精度从31.5%提升到44.6%，并在COCO、MPII和H36M等数据集及现有强姿态模型上持续带来收益。它说明一致性半监督学习不能忽视类别极度不均衡的问题，也提供了一种简单、通用的办法来利用海量未标注人体图像提升模型泛化能力。
原文 arXiv:2011.12498;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2011.12498v4