论文标题
基于骨架的动作识别的分层一致的对比度学习，增长不断增长
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
论文作者
论文摘要
对比度学习已被证明有益于基于骨骼的自我监督的动作识别。大多数对比的学习方法都利用精心设计的增强来为同一语义生成不同的骨骼运动模式。但是，应用强大的增强量仍然是一个待定的问题，这会扭曲图像/骨骼的结构并导致语义损失，这是由于它们的不稳定训练。在本文中，我们研究了采用强大增强的潜力，并提出了基于骨骼的动作识别的一般层次一致的对比学习框架（HICLR）。具体而言，我们首先设计了逐渐增长的增强政策，以产生多个有序的积极对，该对指导从不同的观点实现了学说的代表性的一致性。然后，提出了不对称的损失，以通过特征空间中的方向聚类操作来强制执行层次结构的一致性，从而使表示形式从强烈的增强视图中拉出更接近弱增强视图的观点，以获得更好的推广性。同时，我们建议并评估3D骨骼的三种强大增强，以证明我们方法的有效性。广泛的实验表明，在三个大规模数据集（即NTU60，NTU120和PKUMMD）上，HICLR的表现均优于最先进的方法。
Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of skeletons for the same semantics. However, it is still a pending issue to apply strong augmentations, which distort the images/skeletons' structures and cause semantic loss, due to their resulting unstable training. In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition. Specifically, we first design a gradual growing augmentation policy to generate multiple ordered positive pairs, which guide to achieve the consistency of the learned representation from different views. Then, an asymmetric loss is proposed to enforce the hierarchical consistency via a directional clustering operation in the feature space, pulling the representations from strongly augmented views closer to those from weakly augmented views for better generalizability. Meanwhile, we propose and evaluate three kinds of strong augmentations for 3D skeletons to demonstrate the effectiveness of our method. Extensive experiments show that HiCLR outperforms the state-of-the-art methods notably on three large-scale datasets, i.e., NTU60, NTU120, and PKUMMD.
