Although existing domain-adaptive person re-identification (re-ID) methods have achieved competitive per- formance, most of them highly rely on the reliability of pseudo-label prediction, which seriously limits their applicability as noisy labels cannot be avoided. This paper designs a Transformer framework based on body part-level domain alignment to solve the above-mentioned issues in domain-adaptive person re-ID. Different parts of the human body (such as head, torso, and legs) have different structures and shapes. Therefore, they usually exhibit different characteristics. The proposed method makes full use of the dissimilarity between different human body parts. Specifically, the local features from the same body part are aggregated by the Transformer to obtain the corresponding class token, which is used as the global representation of this body part. Additionally, a Transformer layer-embedded adversarial learning strategy is designed. This strategy can simultaneously achieve domain alignment and classification of the class token for each human body part in both target and source domains by an integrated discriminator, thereby realizing domain alignment at human body part level. Compared with existing domain-level and identity-level alignment methods, the proposed method has a stronger fine-grained domain alignment capability. Therefore, the information loss or distortion that may occur in the feature alignment process can be effectively alleviated. The proposed method does not need to predict pseudo labels of any target sample, so the negative impact caused by unreliable pseudo labels on re-ID performance can be effectively avoided. Compared with state-of-the-art methods, the proposed method achieves better performance on the datasets that are in line with real-world scene settings.

中文翻译：

---

使用 Transformer 框架进行域自适应人员重新识别的身体部位级域对齐


尽管现有的领域自适应行人重识别（re-ID）方法已经取得了有竞争力的性能，但它们大多数都高度依赖伪标签预测的可靠性，这严重限制了它们的适用性，因为噪声标签无法避免。本文设计了一种基于身体部位级域对齐的Transformer框架来解决域自适应行人重识别中的上述问题。人体的不同部位（如头部、躯干和腿部）具有不同的结构和形状。因此，它们通常表现出不同的特征。该方法充分利用了人体不同部位之间的差异。具体来说，来自同一身体部位的局部特征由 Transformer 聚合以获得相应的类标记，该类标记用作该身体部位的全局表示。此外，还设计了 Transformer 层嵌入的对抗性学习策略。该策略可以通过集成鉴别器同时实现目标域和源域中每个人体部位的类标记的域对齐和分类，从而实现人体部位级别的域对齐。与现有的域级和身份级对齐方法相比，该方法具有更强的细粒度域对齐能力。因此，可以有效地减轻特征对齐过程中可能出现的信息丢失或失真。该方法不需要预测任何目标样本的伪标签，因此可以有效避免不可靠的伪标签对re-ID性能造成的负面影响。 与最先进的方法相比，所提出的方法在符合真实场景设置的数据集上取得了更好的性能。