# Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification arXiv: https://arxiv.org/abs/2307.03240 ยท HTML: https://mlsanity.com/paper/2307.03240/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Builds on 40 of its 84 references that are in the map. - First posted on arXiv 6 Jul 2023. ## Builds on (most cited first, 30 of 40) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017) - [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015) - [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017) - [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017) - [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019) - [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020) - [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) - [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020) - [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020) - [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023) - [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) - [Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences](https://mlsanity.com/paper/2108.07422/) (2021) - [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022) - [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021) - [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021) - [CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2101.08467/) (2021) - [Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2304.04205/) (2023) - [Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification](https://mlsanity.com/paper/2007.13890/) (2020) - [Hetero-Center Loss for Cross-Modality Person Re-Identification](https://mlsanity.com/paper/1910.09830/) (2019) - [Deep Learning under Privileged Information Using Heteroscedastic Dropout](https://mlsanity.com/paper/1805.11614/) (2018) - [Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2203.01735/) (2022) - [Visualizing Deep Similarity Networks](https://mlsanity.com/paper/1901.00536/) (2019) - [Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-spectral Hallucination and Low-rank Embedding](https://mlsanity.com/paper/1611.06638/) (2016) - [SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2102.12137/) (2021) - [Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification](https://mlsanity.com/paper/1905.10048/) (2019) - [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021) - [PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2304.01537/) (2023) ## Built on by (most cited first, 6 of 6) - [Multi-modal Crowd Counting via a Broker Modality](https://mlsanity.com/paper/2407.07518/) (2024) - [Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2511.02685/) (2025) - [Diverse Semantics-Guided Feature Alignment and Decoupling for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2505.00619/) (2025) - [Bidirectional Multi-Step Domain Generalization for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.10782/) (2024) - [Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2607.15220/) (2026) - [Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification](https://mlsanity.com/paper/2608.06943/) (2026) ## Abstract (arXiv) Visible-infrared person re-identification seeks to retrieve images of the same individual captured over a distributed network of RGB and IR sensors. Several V-I ReID approaches directly integrate both V and I modalities to discriminate persons within a shared representation space. However, given the significant gap in data distributions between V and I modalities, cross-modal V-I ReID remains challenging. Some recent approaches improve generalization by leveraging intermediate spaces that can bridge V and I modalities, yet effective methods are required to select or generate data for such informative domains. In this paper, the Adaptive Generation of Privileged Intermediate Information training approach is introduced to adapt and generate a virtual domain that bridges discriminant information between the V and I modalities. The key motivation behind AGPI^2 is to enhance the training of a deep V-I ReID backbone by generating privileged images that provide additional information. These privileged images capture shared discriminative features that are not easily accessible within the original V or I modalities alone. Towards this goal, a non-linear generative module is trained with an adversarial objective, translating V images into intermediate spaces with a smaller domain shift w.r.t. the I domain. Meanwhile, the embedding module within AGPI^2 aims to produce similar features for both V and generated images, encouraging the extraction of features that are common to all modalities. In addition to these contributions, AGPI^2 employs adversarial objectives for adapting the intermediate images, which play a crucial role in creating a non-modality-specific space to address the large domain shifts between V and I domains. Experimental results conducted on challenging V-I ReID datasets indicate that AGPI^2 increases matching accuracy without extra computational resources during inference.