本文是计算机视觉领域顶级会议ICCV2021入选论文《An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation(半监督二维人体姿态估计中的模型坍塌问题研究)》的解读。该论文由北京大学王亦洲课题组与微软亚洲研究院合作完成,研究了一致性学习算法在二维人体姿态估计中的模型坍塌问题,并提出了构建预测难度存在差异的样本对来解决该问题。本文提出的算法可以有效地利用无标记数据中的信息,显著提高了姿态估计模型的泛化能力。
[1] Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. Fixmatch: Simplifying semisupervised learning with consistency and confidence. In Advances in Neural Information Processing Systems, 2020.
[2] David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. Mixmatch: A holistic approach to semi-supervised learning. In Advances in Neural Information Processing Systems, pages 5049–5059, 2019.