# GraFT: Gradual Fusion Transformer for Multimodal Re-Identification

arXiv: https://arxiv.org/abs/2310.16856 · HTML: https://mlsanity.com/paper/2310.16856/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Person Re-identification in the Wild](https://mlsanity.com/paper/1604.02531/) (2016)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Spatial-Temporal Person Re-identification](https://mlsanity.com/paper/1812.03282/) (2018)
- [On the Benefits of Early Fusion in Multimodal Representation Learning](https://mlsanity.com/paper/2011.07191/) (2020)
- [Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification](https://mlsanity.com/paper/1912.01300/) (2019)
- [Person Re-Identification with a Locally Aware Transformer](https://mlsanity.com/paper/2106.03720/) (2021)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification](https://mlsanity.com/paper/1907.06498/) (2019)
- [MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID](https://mlsanity.com/paper/2111.05059/) (2021)
- [Exploring Invariant Representation for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2302.00884/) (2023)
- [Cluster-level Feature Alignment for Person Re-identification](https://mlsanity.com/paper/2008.06810/) (2020)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)

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

- [Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2403.10254/) (2024)
- [ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification](https://mlsanity.com/paper/2505.17821/) (2025)
- [MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2510.23301/) (2025)
- [Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning](https://mlsanity.com/paper/2504.14847/) (2025)
- [Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance](https://mlsanity.com/paper/2607.23451/) (2026)
- [Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation](https://mlsanity.com/paper/2607.29207/) (2026)
- [Incentive Noise and Structural Prior Infusion for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2609.24539/) (2026)

## Abstract (arXiv)

Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as they rely heavily on late fusion, which postpones the integration of specific modality insights. Addressing this, we introduce the Gradual Fusion Transformer (GraFT) for multimodal ReID. At its core, GraFT employs learnable fusion tokens that guide self-attention across encoders, adeptly capturing both modality-specific and object-specific features. Further bolstering its efficacy, we introduce a novel training paradigm combined with an augmented triplet loss, optimizing the ReID feature embedding space. We demonstrate these enhancements through extensive ablation studies and show that GraFT consistently surpasses established multimodal ReID benchmarks. Additionally, aiming for deployment versatility, we've integrated neural network pruning into GraFT, offering a balance between model size and performance.