# Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2008.02520 · HTML: https://mlsanity.com/paper/2008.02520/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 23 of 23)

- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2304.04205/) (2023)
- [Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2208.02450/) (2022)
- [PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2304.01537/) (2023)
- [FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation](https://mlsanity.com/paper/2503.17940/) (2025)
- [Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID](https://mlsanity.com/paper/2402.00672/) (2024)
- [Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification](https://mlsanity.com/paper/2203.15210/) (2022)
- [Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.08316/) (2023)
- [FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning](https://mlsanity.com/paper/2403.16561/) (2024)
- [Exploring Invariant Representation for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2302.00884/) (2023)
- [Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification](https://mlsanity.com/paper/2104.11539/) (2021)
- [Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification](https://mlsanity.com/paper/2203.01675/) (2022)
- [ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2310.07552/) (2023)
- [MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection](https://mlsanity.com/paper/2403.15209/) (2024)
- [Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning](https://mlsanity.com/paper/2507.12942/) (2025)
- [FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification](https://mlsanity.com/paper/2510.15595/) (2025)
- [Unsupervised Visible-Infrared ReID via Pseudo-label Correction and Modality-level Alignment](https://mlsanity.com/paper/2404.06683/) (2024)
- [Spectral Aware Softmax for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2302.01512/) (2023)
- [YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions](https://mlsanity.com/paper/2403.04183/) (2024)
- [CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2403.05924/) (2024)
- [Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach](https://mlsanity.com/paper/2504.07785/) (2025)
- [CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2208.09844/) (2022)

## Abstract (arXiv)

Visible-infrared person re-identification (VI-ReID) is a challenging and essential task in night-time intelligent surveillance systems. Except for the intra-modality variance that RGB-RGB person re-identification mainly overcomes, VI-ReID suffers from additional inter-modality variance caused by the inherent heterogeneous gap. To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively. Disentangling cross-modality identity-discriminable features leads to more robust retrieval for VI-ReID. To achieve efficient optimization like conventional VAE, we theoretically derive two variational inference terms for the MoG prior under the supervised setting, which not only restricts the identity-discriminable subspace so that the model explicitly handles the cross-modality intra-identity variance, but also enables the MoG distribution to avoid posterior collapse. Furthermore, we propose a triplet swap reconstruction (TSR) strategy to promote the above disentangling process. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on two VI-ReID datasets.