# MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID

arXiv: https://arxiv.org/abs/2111.05059 · HTML: https://mlsanity.com/paper/2111.05059/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 9 Nov 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (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)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Generative Moment Matching Networks](https://mlsanity.com/paper/1502.02761/) (2015)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [Human Semantic Parsing for Person Re-identification](https://mlsanity.com/paper/1804.00216/) (2018)
- [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020)
- [A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking](https://mlsanity.com/paper/1711.10378/) (2017)
- [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2002.04114/) (2020)
- [Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/1912.01230/) (2019)
- [AlignedReID: Surpassing Human-Level Performance in Person Re-Identification](https://mlsanity.com/paper/1711.08184/) (2017)
- [VRSTC: Occlusion-Free Video Person Re-Identification](https://mlsanity.com/paper/1907.08427/) (2019)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification](https://mlsanity.com/paper/2104.02862/) (2021)
- [Pose Invariant Embedding for Deep Person Re-identification](https://mlsanity.com/paper/1701.07732/) (2017)
- [A Siamese Long Short-Term Memory Architecture for Human Re-Identification](https://mlsanity.com/paper/1607.08381/) (2016)
- [Learning Unbiased Representations via Mutual Information Backpropagation](https://mlsanity.com/paper/2003.06430/) (2020)
- [Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification](https://mlsanity.com/paper/1912.01300/) (2019)
- [Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification](https://mlsanity.com/paper/1907.09659/) (2019)
- [Learning Shape Representations for Clothing Variations in Person Re-Identification](https://mlsanity.com/paper/2003.07340/) (2020)

## Built on by (most cited first, 8 of 8)

- [Modality Unifying Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2309.06262/) (2023)
- [GraFT: Gradual Fusion Transformer for Multimodal Re-Identification](https://mlsanity.com/paper/2310.16856/) (2023)
- [YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions](https://mlsanity.com/paper/2403.04183/) (2024)
- [Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification](https://mlsanity.com/paper/2512.20892/) (2025)
- [Beyond Sharing Weights in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identification](https://mlsanity.com/paper/2310.08026/) (2023)
- [Parameter Hierarchical Optimization for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2404.07930/) (2024)
- [Cross-Modal Retrieval with Cauchy-Schwarz Divergence](https://mlsanity.com/paper/2509.21339/) (2025)
- [Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2512.03745/) (2025)

## Abstract (arXiv)

Learning modality invariant features is central to the problem of Visible-Thermal cross-modal Person Reidentification (VT-ReID), where query and gallery images come from different modalities. Existing works implicitly align the modalities in pixel and feature spaces by either using adversarial learning or carefully designing feature extraction modules that heavily rely on domain knowledge. We propose a simple but effective framework, MMD-ReID, that reduces the modality gap by an explicit discrepancy reduction constraint. MMD-ReID takes inspiration from Maximum Mean Discrepancy (MMD), a widely used statistical tool for hypothesis testing that determines the distance between two distributions. MMD-ReID uses a novel margin-based formulation to match class-conditional feature distributions of visible and thermal samples to minimize intra-class distances while maintaining feature discriminability. MMD-ReID is a simple framework in terms of architecture and loss formulation. We conduct extensive experiments to demonstrate both qualitatively and quantitatively the effectiveness of MMD-ReID in aligning the marginal and class conditional distributions, thus learning both modality-independent and identity-consistent features. The proposed framework significantly outperforms the state-of-the-art methods on SYSU-MM01 and RegDB datasets. Code will be released at https://github.com/vcl-iisc/MMD-ReID