# Towards Generalizable Person Re-identification with a Bi-stream Generative Model

arXiv: https://arxiv.org/abs/2206.09362 · HTML: https://mlsanity.com/paper/2206.09362/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 86 references that are in the map.
- First posted on arXiv 19 Jun 2022.

## Builds on (most cited first, 30 of 49)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [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)
- [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)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [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)
- [Human Semantic Parsing for Person Re-identification](https://mlsanity.com/paper/1804.00216/) (2018)
- [Part-Aligned Bilinear Representations for Person Re-identification](https://mlsanity.com/paper/1804.07094/) (2018)
- [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)
- [A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking](https://mlsanity.com/paper/1711.10378/) (2017)
- [Learning Generalisable Omni-Scale Representations for Person Re-Identification](https://mlsanity.com/paper/1910.06827/) (2019)
- [FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification](https://mlsanity.com/paper/1810.02936/) (2018)
- [Horizontal Pyramid Matching for Person Re-identification](https://mlsanity.com/paper/1804.05275/) (2018)
- [Unsupervised Domain Adaptive Re-Identification: Theory and Practice](https://mlsanity.com/paper/1807.11334/) (2018)
- [Densely Semantically Aligned Person Re-Identification](https://mlsanity.com/paper/1812.08967/) (2018)
- [Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification](https://mlsanity.com/paper/1904.00537/) (2019)
- [Self-training with progressive augmentation for unsupervised cross-domain person re-identification](https://mlsanity.com/paper/1907.13315/) (2019)
- [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017)

## Built on by (most cited first, 7 of 7)

- [Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning](https://mlsanity.com/paper/2211.15076/) (2022)
- [Bright Channel Prior Attention for Multispectral Pedestrian Detection](https://mlsanity.com/paper/2305.12845/) (2023)
- [Mix-Modality Person Re-Identification: A New and Practical Paradigm](https://mlsanity.com/paper/2412.04719/) (2024)
- [Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification](https://mlsanity.com/paper/2407.07351/) (2024)
- [Beyond Seen Bounds: Class-Centric Polarization for Single-Domain Generalized Deep Metric Learning](https://mlsanity.com/paper/2601.09121/) (2026)
- [FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification](https://mlsanity.com/paper/2603.06122/) (2026)
- [FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts](https://mlsanity.com/paper/2603.12912/) (2026)

## Abstract (arXiv)

Generalizable person re-identification (re-ID) has attracted growing attention due to its powerful adaptation capability in the unseen data domain. However, existing solutions often neglect either crossing cameras (e.g., illumination and resolution differences) or pedestrian misalignments (e.g., viewpoint and pose discrepancies), which easily leads to poor generalization capability when adapted to the new domain. In this paper, we formulate these difficulties as: 1) Camera-Camera (CC) problem, which denotes the various human appearance changes caused by different cameras; 2) Camera-Person (CP) problem, which indicates the pedestrian misalignments caused by the same identity person under different camera viewpoints or changing pose. To solve the above issues, we propose a Bi-stream Generative Model (BGM) to learn the fine-grained representations fused with camera-invariant global feature and pedestrian-aligned local feature, which contains an encoding network and two stream decoding sub-networks. Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors. For the CP problem, another stream learns a pedestrian-aligned local feature for pedestrian alignment using information-complete densely semantically aligned part maps. Moreover, a part-weighted loss function is presented to reduce the influence of missing parts on pedestrian alignment. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods on the large-scale generalizable re-ID benchmarks, involving domain generalization setting and cross-domain setting.