# Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2203.01735 · HTML: https://mlsanity.com/paper/2203.01735/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 3 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020)
- [RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment](https://mlsanity.com/paper/1910.05839/) (2019)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World](https://mlsanity.com/paper/2004.05551/) (2020)
- [Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2002.04114/) (2020)
- [Triplet-Center Loss for Multi-View 3D Object Retrieval](https://mlsanity.com/paper/1803.06189/) (2018)
- [Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/1912.01230/) (2019)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [Spectral Feature Transformation for Person Re-identification](https://mlsanity.com/paper/1811.11405/) (2018)
- [Hetero-Center Loss for Cross-Modality Person Re-Identification](https://mlsanity.com/paper/1910.09830/) (2019)
- [Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation](https://mlsanity.com/paper/1908.04126/) (2019)
- [Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification](https://mlsanity.com/paper/1907.09659/) (2019)
- [RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model](https://mlsanity.com/paper/2007.07452/) (2020)
- [G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2106.07853/) (2021)

## Built on by (most cited first, 26 of 26)

- [Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2212.00226/) (2022)
- [Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2401.06825/) (2024)
- [Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.11708/) (2024)
- [DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing](https://mlsanity.com/paper/2407.08132/) (2024)
- [PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2304.01537/) (2023)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2402.19026/) (2024)
- [Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning](https://mlsanity.com/paper/2302.08212/) (2023)
- [Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.08316/) (2023)
- [ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification](https://mlsanity.com/paper/2505.17821/) (2025)
- [Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.03240/) (2023)
- [Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning](https://mlsanity.com/paper/2406.12316/) (2024)
- [Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2511.02685/) (2025)
- [Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification](https://mlsanity.com/paper/2210.05438/) (2022)
- [SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection](https://mlsanity.com/paper/2601.02249/) (2026)
- [Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification](https://mlsanity.com/paper/2401.01839/) (2024)
- [BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2603.14243/) (2026)
- [YYDS: Visible-Infrared Person Re-Identification with Coarse Descriptions](https://mlsanity.com/paper/2403.04183/) (2024)
- [Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.10782/) (2024)
- [Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2407.12758/) (2024)
- [FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network](https://mlsanity.com/paper/2407.16129/) (2024)
- [Mix-Modality Person Re-Identification: A New and Practical Paradigm](https://mlsanity.com/paper/2412.04719/) (2024)
- [CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2511.10309/) (2025)
- [OmniPerson: Unified Identity-Preserving Pedestrian Generation](https://mlsanity.com/paper/2512.02554/) (2025)
- [Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2603.16165/) (2026)
- [CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification](https://mlsanity.com/paper/2604.02808/) (2026)

## Abstract (arXiv)

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It formulates modality mixup procedure as Markov decision process, where an actor-critic agent learns dynamical and local linear interpolation policy between different regions of cross-modality images under a deep reinforcement learning framework. Such policy guarantees modality-invariance in a more continuous latent space and avoids manifold intrusion by the corrupted mixed modality samples. Moreover, to further counter modality discrepancy and enforce invariant visual semantics at the feature-level, MID employs modality-adaptive convolution decomposition to disassemble a regular convolution layer into modality-specific basis layers and a modality-shared coefficient layer. Extensive experimental results on two challenging benchmarks demonstrate superior performance of MID over state-of-the-art methods.