Meta Batch-Instance Normalization for Generalizable Person Re-Identification
This work tackles the problem of poor generalization in person re-identification for computer vision researchers and practitioners, offering an incremental improvement over existing instance normalization techniques.
This paper addresses the poor generalization of supervised person re-identification (Re-ID) methods to unseen domains. The authors propose Meta Batch-Instance Normalization (MetaBIN), a framework that combines learnable batch-instance normalization layers with meta-learning to simulate generalization failures and improve performance on unseen domains. Their model outperforms state-of-the-art methods on large-scale domain generalization Re-ID benchmarks and cross-domain Re-ID problems.
Although supervised person re-identification (Re-ID) methods have shown impressive performance, they suffer from a poor generalization capability on unseen domains. Therefore, generalizable Re-ID has recently attracted growing attention. Many existing methods have employed an instance normalization technique to reduce style variations, but the loss of discriminative information could not be avoided. In this paper, we propose a novel generalizable Re-ID framework, named Meta Batch-Instance Normalization (MetaBIN). Our main idea is to generalize normalization layers by simulating unsuccessful generalization scenarios beforehand in the meta-learning pipeline. To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers. Moreover, we diversify the virtual simulations via our meta-train loss accompanied by a cyclic inner-updating manner to boost generalization capability. After all, the MetaBIN framework prevents our model from overfitting to the given source styles and improves the generalization capability to unseen domains without additional data augmentation or complicated network design. Extensive experimental results show that our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark and the cross-domain Re-ID problem. The source code is available at: https://github.com/bismex/MetaBIN.