Abstract
The goal of gait recognition is to extract identity-invariant features of an individual under various gait conditions, e.g., cross-view and cross-clothing. Most gait models strive to implicitly learn the common traits across different gait conditions in a data-driven manner to pull different gait conditions closer for recognition. However, relatively few studies have explicitly explored the inherent relations between different gait conditions. For this purpose, we attempt to establish connections among different gait conditions and propose a new perspective to achieve gait recognition: variations in different gait conditions can be approximately viewed as a combination of geometric transformations. In this case, all we need is to determine the types of geometric transformations and achieve geometric invariance, then identity invariance naturally follows. As an initial attempt, we explore three common geometric transformations (i.e., Reflect, Rotate, and Scale) and design a $\mathcal{R}$eflect-$\mathcal{R}$otate-$\mathcal{S}$cale invariance learning framework, named ${\mathcal{RRS}}$-Gait. Specifically, it first flexibly adjusts the convolution kernel based on the specific geometric transformations to achieve approximate feature equivariance. Then these three equivariant-aware features are respectively fed into a global pooling operation for final invariance-aware learning. Extensive experiments on four popular gait datasets (Gait3D, GREW, CCPG, SUSTech1K) show superior performance across various gait conditions.
Abstract (translated)
步态识别的目标是从不同步态条件下提取个体的身份不变特征，例如跨视角和跨服装条件。大多数步态模型致力于通过数据驱动的方式隐式学习不同步态条件下的共同特性，以使不同的步态条件在识别时更加接近。然而，相对较少的研究明确探讨了不同步态条件之间的内在关系。为此，我们试图建立不同步态条件之间的联系，并提出了一种新的实现步态识别的视角：不同步态条件的变化可以近似视为几何变换的组合。在这种情况下，我们需要确定各种几何变换类型并实现几何不变性，则身份不变性自然随之而来。 作为初步尝试，我们探索了三种常见的几何变换（即反射、旋转和缩放），并设计了一个名为$\mathcal{RRS}$-Gait的反射-$\mathcal{R}$otate-$\mathcal{S}$cale不变性学习框架。具体来说，它首先根据特定的几何变换灵活调整卷积核以实现近似的特征等变性（equivariance）。然后将这三种具有等变性的特征分别输入全局池化操作进行最终的不变性感知学习。 在四个流行的步态数据集（Gait3D、GREW、CCPG和SUSTech1K）上进行了广泛的实验，结果表明该方法在各种步态条件下均表现出优异性能。
URL
https://arxiv.org/abs/2601.05604
