Abstract
Domain generalizable person re-identification (DG re-ID) aims to learn discriminative representations that are robust to distributional shifts. While data augmentation is a straightforward solution to improve generalization, certain augmentations exhibit a polarized effect in this task, enhancing in-distribution performance while deteriorating out-of-distribution performance. In this paper, we investigate this phenomenon and reveal that it leads to sparse representation spaces with reduced uniformity. To address this issue, we propose a novel framework, Balancing Alignment and Uniformity (BAU), which effectively mitigates this effect by maintaining a balance between alignment and uniformity. Specifically, BAU incorporates alignment and uniformity losses applied to both original and augmented images and integrates a weighting strategy to assess the reliability of augmented samples, further improving the alignment loss. Additionally, we introduce a domain-specific uniformity loss that promotes uniformity within each source domain, thereby enhancing the learning of domain-invariant features. Extensive experimental results demonstrate that BAU effectively exploits the advantages of data augmentation, which previous studies could not fully utilize, and achieves state-of-the-art performance without requiring complex training procedures. The code is available at \url{this https URL}.
Abstract (translated)
领域通用的人体重新识别（DG re-ID）旨在学习能够抵御分布变化的判别表示。虽然数据增强是提高泛化能力的一种直接解决方案，但在某些情况下，这些增强方法表现出了一种两极分化的效果，在提升模型在训练集上的表现的同时却损害了其在未见数据集上的表现。在这篇论文中，我们研究了这一现象并揭示它导致了不均匀的稀疏表示空间。为了解决这个问题，我们提出了一种新的框架——平衡对齐和一致性的方法（BAU），通过维持对齐与一致性之间的平衡来有效地缓解这种效果。具体来说，BAU结合了应用于原始图像和增强图像上的对齐损失和一致性损失，并集成了一种权重策略以评估增强样本的可靠性，进一步提高了对齐损失的效果。此外，我们还引入了一种领域特定的一致性损失，它在每个源域内促进一致性，从而增强了学习领域的不变特征的能力。大量的实验结果表明，BAU有效地利用了数据增强的优势，这是以往研究未能充分挖掘出来的，并且实现了最先进的性能，而无需复杂的训练过程。代码可在\url{this https URL}获取。
URL
https://arxiv.org/abs/2411.11471
