TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification

Domain generalizable person re-identification (reid) is a challenging task in computer vision, which aims to apply a trained reid model to unseen domains. Prior works either combine the data in all the training domains to capture domain-invariant features, or adopt a mixture of experts to investigate domain-specific information. In this work, we argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of reid models. To this end, we design a novel framework, which we name two-stream adaptive learning (TAL), to simultaneously model these two kinds of information. Specifically, a domain-specific stream is proposed to capture the training domain statistics with batch normalization (BN) parameters, whereas an adaptive matching layer is designed to dynamically aggregate domain-level information. In the meantime, we design an adaptive BN layer in the domain-invariant stream to approximate the statistic of unseen domains, such that our model is capable of handling various novel scenes. These two streams work adaptively and collaboratively to learn generalizable reid features. As validated by extensive experiments, our framework can be applied to both single-source and multi-source domain generalization tasks, where the results show that our framework notably outperforms the state-of-the-art methods.