Abstract
Gait recognition is a biometric technology that distinguishes individuals by their walking patterns. However, previous methods face challenges when accurately extracting identity features because they often become entangled with non-identity clues. To address this challenge, we propose CLTD, a causality-inspired discriminative feature learning module designed to effectively eliminate the influence of confounders in triple domains, \ie, spatial, temporal, and spectral. Specifically, we utilize the Cross Pixel-wise Attention Generator (CPAG) to generate attention distributions for factual and counterfactual features in spatial and temporal domains. Then, we introduce the Fourier Projection Head (FPH) to project spatial features into the spectral space, which preserves essential information while reducing computational costs. Additionally, we employ an optimization method with contrastive learning to enforce semantic consistency constraints across sequences from the same subject. Our approach has demonstrated significant performance improvements on challenging datasets, proving its effectiveness. Moreover, it can be seamlessly integrated into existing gait recognition methods.
Abstract (translated)
步伐识别是一种生物识别技术,它通过区分个体的行走模式来识别个体。然而, previous 方法在准确提取身份特征时面临挑战,因为它们通常会纠缠于非个体特征。为解决这个挑战,我们提出了 CLTD,一种以因果关系为导向的判别特征学习模块,旨在有效消除在三个领域(即空间、时间和频域)中混淆因素的影响。具体来说,我们利用 Cross Pixel-wise Attention Generator (CPAG) 生成空间和时间域中的事实和反事实特征的注意力分布。然后,我们引入了 Fourier Projection Head (FPH),将空间特征投影到频域中,保留关键信息的同时降低计算成本。此外,我们还使用一种具有对比学习优化的方法来强制确保同一主题序列之间的语义一致性约束。我们的方法在具有挑战性的数据集上取得了显著的性能提升,证明了其有效性。此外,它可以轻松地集成到现有的步伐识别方法中。
URL
https://arxiv.org/abs/2407.12519