Contrastive learning, relying on effective positive and negative sample pairs, is beneficial to learn informative skeleton representations in unsupervised skeleton-based action recognition. To achieve these positive and negative pairs, existing weak/strong data augmentation methods have to randomly change the appearance of skeletons for indirectly pursuing semantic perturbations. However, such approaches have two limitations: i) solely perturbing appearance cannot well capture the intrinsic semantic information of skeletons, and ii) randomly perturbation may change the original positive/negative pairs to soft positive/negative ones. To address the above dilemma, we start the first attempt to explore an attack-based augmentation scheme that additionally brings in direct semantic perturbation, for constructing hard positive pairs and further assisting in constructing hard negative pairs. In particular, we propose a novel Attack-Augmentation Mixing-Contrastive skeletal representation learning (A$^2$MC) to contrast hard positive features and hard negative features for learning more robust skeleton representations. In A$^2$MC, Attack-Augmentation (Att-Aug) is designed to collaboratively perform targeted and untargeted perturbations of skeletons via attack and augmentation respectively, for generating high-quality hard positive features. Meanwhile, Positive-Negative Mixer (PNM) is presented to mix hard positive features and negative features for generating hard negative features, which are adopted for updating the mixed memory banks. Extensive experiments on three public datasets demonstrate that A$^2$MC is competitive with the state-of-the-art methods. The code will be accessible on A$^2$MC (https://github.com/1xbq1/A2MC).

翻译：对比学习依赖于有效的正负样本对，有助于在无监督骨架动作识别中学习信息丰富的骨架表征。为实现这些正负样本对，现有的弱/强数据增强方法需随机改变骨架外观以间接实现语义扰动。然而，此类方法存在两个局限：i) 仅扰动外观无法充分捕捉骨架的内在语义信息；ii) 随机扰动可能将原始正/负对转变为软正/负对。为解决上述困境，我们首次尝试探索基于攻击的增强方案，该方案额外引入直接语义扰动，以构建硬正样本对并进一步辅助构建硬负样本对。具体而言，我们提出一种新颖的攻击增强混合对比骨架表征学习（A$^2$MC）方法，通过对比硬正样本特征与硬负样本特征来学习更鲁棒的骨架表征。在A$^2$MC中，攻击增强模块（Att-Aug）被设计为分别通过攻击和增强协同执行骨架的有目标与无目标扰动，以生成高质量的硬正样本特征。同时，正负混合器（PNM）被提出用于混合硬正样本特征与负样本特征以生成硬负样本特征，这些特征被用于更新混合记忆库。在三个公开数据集上的大量实验表明，A$^2$MC与最先进方法相比具有竞争力。代码将在A$^2$MC（https://github.com/1xbq1/A2MC）上公开。