# Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

arXiv: https://arxiv.org/abs/2112.08684 · HTML: https://mlsanity.com/paper/2112.08684/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Learning to Optimize Domain Specific Normalization for Domain Generalization](https://mlsanity.com/paper/1907.04275/) (2019)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Few-Shot Image Recognition by Predicting Parameters from Activations](https://mlsanity.com/paper/1706.03466/) (2017)
- [MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data](https://mlsanity.com/paper/2002.03366/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2004.08787/) (2020)
- [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)
- [Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach](https://mlsanity.com/paper/1801.00881/) (2018)
- [Batch Normalization Embeddings for Deep Domain Generalization](https://mlsanity.com/paper/2011.12672/) (2020)
- [Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2103.04337/) (2021)
- [Unsupervised Multi-Source Domain Adaptation for Person Re-Identification](https://mlsanity.com/paper/2104.12961/) (2021)
- [Robust Place Categorization with Deep Domain Generalization](https://mlsanity.com/paper/1805.12048/) (2018)
- [Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification](https://mlsanity.com/paper/2008.08528/) (2020)

## Built on by (most cited first, 19 of 19)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training](https://mlsanity.com/paper/2406.06045/) (2024)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification](https://mlsanity.com/paper/2501.16065/) (2025)
- [Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification](https://mlsanity.com/paper/2502.06619/) (2025)
- [Beyond Role-Based Surgical Domain Modeling: Generalizable Re-Identification in the Operating Room](https://mlsanity.com/paper/2503.13028/) (2025)
- [Anti-Forgetting Adaptation for Unsupervised Person Re-identification](https://mlsanity.com/paper/2411.14695/) (2024)
- [Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID](https://mlsanity.com/paper/2310.15913/) (2023)
- [A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification](https://mlsanity.com/paper/2410.08456/) (2024)
- [Feature-Distribution Perturbation and Calibration for Generalized Person ReID](https://mlsanity.com/paper/2205.11197/) (2022)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [Generalizable Person Search on Open-world User-Generated Video Content](https://mlsanity.com/paper/2310.10068/) (2023)
- [Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification](https://mlsanity.com/paper/2410.08466/) (2024)
- [CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion](https://mlsanity.com/paper/2508.04036/) (2025)
- [Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identification](https://mlsanity.com/paper/2603.14012/) (2026)
- [Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification](https://mlsanity.com/paper/2606.16161/) (2026)
- [Cross-Species Animal Re-Identification with Semantic Consistency Learning](https://mlsanity.com/paper/2609.09705/) (2026)

## Abstract (arXiv)

Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time, which is a realistic but challenging problem. In contrast to methods assuming an identical model for different domains, Mixture of Experts (MoE) exploits multiple domain-specific networks for leveraging complementary information between domains, obtaining impressive results. However, prior MoE-based DG ReID methods suffer from a large model size with the increase of the number of source domains, and most of them overlook the exploitation of domain-invariant characteristics. To handle the two issues above, this paper presents a new approach called Mimic Embedding via adapTive Aggregation (META) for DG person ReID. To avoid the large model size, experts in META do not adopt a branch network for each source domain but share all the parameters except for the batch normalization layers. Besides multiple experts, META leverages Instance Normalization (IN) and introduces it into a global branch to pursue invariant features across domains. Meanwhile, META considers the relevance of an unseen target sample and source domains via normalization statistics and develops an aggregation module to adaptively integrate multiple experts for mimicking unseen target domain. Benefiting from a proposed consistency loss and an episodic training algorithm, META is expected to mimic embedding for a truly unseen target domain. Extensive experiments verify that META surpasses state-of-the-art DG person ReID methods by a large margin. Our code is available at https://github.com/xbq1994/META.