Domain generalization (DG) for person re-identification (ReID) is a challenging problem, as access to target domain data is not permitted during the training process. Most existing DG ReID methods update the feature extractor and classifier parameters based on the same features. This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains. To solve this problem, we propose a novel style interleaved learning (IL) framework. Unlike conventional learning strategies, IL incorporates two forward propagations and one backward propagation for each iteration. We employ the features of interleaved styles to update the feature extractor and classifiers using different forward propagations, which helps to prevent the model from overfitting to certain domain styles. To generate interleaved feature styles, we further propose a new feature stylization approach. It produces a wide range of meaningful styles that are both different and independent from the original styles in the source domain, which caters to the IL methodology. Extensive experimental results show that our model not only consistently outperforms state-of-the-art methods on large-scale benchmarks for DG ReID, but also has clear advantages in computational efficiency. The code is available at https://github.com/WentaoTan/Interleaved-Learning.

翻译：行人重识别中的域泛化是一个具有挑战性的问题，因为在训练过程中不允许访问目标域数据。现有的大多数域泛化行人重识别方法基于相同特征更新特征提取器和分类器参数。这种常见做法导致模型过拟合源域中的现有特征风格，从而在目标域上产生次优的泛化能力。为解决该问题，我们提出一种新颖的风格交错学习框架。与传统学习策略不同，交错学习在每次迭代中包含两次前向传播和一次反向传播。我们利用交错风格的特征，通过不同的前向传播更新特征提取器和分类器，这有助于防止模型过拟合特定域风格。为生成交错特征风格，我们进一步提出一种新的特征风格化方法。该方法能够产生大量有意义的风格，这些风格既不同于源域中的原始风格，又独立于源域中的原始风格，从而契合交错学习的方法论。大量实验结果表明，我们的模型不仅在域泛化行人重识别的大规模基准测试中持续优于现有最先进方法，而且在计算效率方面具有明显优势。代码已在 https://github.com/WentaoTan/Interleaved-Learning 开源。