# Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

arXiv: https://arxiv.org/abs/2203.01723 · HTML: https://mlsanity.com/paper/2203.01723/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 3 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Learning to Optimize Domain Specific Normalization for Domain Generalization](https://mlsanity.com/paper/1907.04275/) (2019)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/1803.09786/) (2018)
- [Domain Generalization with Domain-Specific Aggregation Modules](https://mlsanity.com/paper/1809.10966/) (2018)
- [Batch Normalization Embeddings for Deep Domain Generalization](https://mlsanity.com/paper/2011.12672/) (2020)
- [Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice](https://mlsanity.com/paper/1905.03422/) (2019)
- [Style Normalization and Restitution for Domain Generalization and Adaptation](https://mlsanity.com/paper/2101.00588/) (2021)
- [Domain Adaptation through Synthesis for Unsupervised Person Re-identification](https://mlsanity.com/paper/1804.10094/) (2018)
- [Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification](https://mlsanity.com/paper/1807.01440/) (2018)
- [Scalable Person Re-identification on Supervised Smoothed Manifold](https://mlsanity.com/paper/1703.08359/) (2017)
- [Multi-Domain Adversarial Feature Generalization for Person Re-Identification](https://mlsanity.com/paper/2011.12563/) (2020)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Dual Distribution Alignment Network for Generalizable Person Re-Identification](https://mlsanity.com/paper/2007.13249/) (2020)

## Built on by (most cited first, 10 of 10)

- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification](https://mlsanity.com/paper/2502.06619/) (2025)
- [Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification](https://mlsanity.com/paper/2405.19695/) (2024)
- [Multilinear subspace learning for person re-identification based fusion of high order tensor features](https://mlsanity.com/paper/2505.15825/) (2025)
- [Domain generalization Person Re-identification on Attention-aware multi-operation strategery](https://mlsanity.com/paper/2210.10409/) (2022)
- [Generalizable Person Search on Open-world User-Generated Video Content](https://mlsanity.com/paper/2310.10068/) (2023)
- [Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification](https://mlsanity.com/paper/2406.14797/) (2024)
- [Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification](https://mlsanity.com/paper/2407.07351/) (2024)
- [Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation](https://mlsanity.com/paper/2408.03608/) (2024)

## Abstract (arXiv)

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.