# Meta Batch-Instance Normalization for Generalizable Person Re-Identification

arXiv: https://arxiv.org/abs/2011.14670 · HTML: https://mlsanity.com/paper/2011.14670/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 30 of 77)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://mlsanity.com/paper/2207.11707/) (2022)
- [Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing](https://mlsanity.com/paper/2108.02667/) (2021)
- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification](https://mlsanity.com/paper/2104.01546/) (2021)
- [Part-Aware Transformer for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.03322/) (2023)
- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.00567/) (2024)
- [MADG: Margin-based Adversarial Learning for Domain Generalization](https://mlsanity.com/paper/2311.08503/) (2023)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2407.18568/) (2024)
- [Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification](https://mlsanity.com/paper/2112.08684/) (2021)
- [Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification](https://mlsanity.com/paper/2206.12513/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search](https://mlsanity.com/paper/2207.10320/) (2022)
- [A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2201.09846/) (2022)
- [Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training](https://mlsanity.com/paper/2406.06045/) (2024)
- [Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification](https://mlsanity.com/paper/2203.01723/) (2022)
- [Domain Generalization with Correlated Style Uncertainty](https://mlsanity.com/paper/2212.09950/) (2022)
- [Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification](https://mlsanity.com/paper/2410.06977/) (2024)
- [Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification](https://mlsanity.com/paper/2105.12355/) (2021)
- [Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption](https://mlsanity.com/paper/2203.00672/) (2022)
- [Semi-Supervised Domain Generalizable Person Re-Identification](https://mlsanity.com/paper/2108.05045/) (2021)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)

## Abstract (arXiv)

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.