# Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval

arXiv: https://arxiv.org/abs/2501.15052 · HTML: https://mlsanity.com/paper/2501.15052/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 25 Jan 2025.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification](https://mlsanity.com/paper/2107.12666/) (2021)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval](https://mlsanity.com/paper/2208.08608/) (2022)
- [Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments](https://mlsanity.com/paper/1906.09610/) (2019)
- [STLLM-DF: A Spatial-Temporal Large Language Model with Diffusion for Enhanced Multi-Mode Traffic System Forecasting](https://mlsanity.com/paper/2409.05921/) (2024)

## Built on by (most cited first, 5 of 5)

- [Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook](https://mlsanity.com/paper/2503.18016/) (2025)
- [GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2510.22268/) (2025)
- [Investigating Domain Gaps for Indoor 3D Object Detection](https://mlsanity.com/paper/2508.17439/) (2025)
- [SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking](https://mlsanity.com/paper/2505.24466/) (2025)
- [Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2603.23902/) (2026)

## Abstract (arXiv)

Video surveillance systems are crucial components for ensuring public safety and management in smart city. As a fundamental task in video surveillance, text-to-image person retrieval aims to retrieve the target person from an image gallery that best matches the given text description. Most existing text-to-image person retrieval methods are trained in a supervised manner that requires sufficient labeled data in the target domain. However, it is common in practice that only unlabeled data is available in the target domain due to the difficulty and cost of data annotation, which limits the generalization of existing methods in practical application scenarios. To address this issue, we propose a novel unsupervised domain adaptation method, termed Graph-Based Cross-Domain Knowledge Distillation (GCKD), to learn the cross-modal feature representation for text-to-image person retrieval in a cross-dataset scenario. The proposed GCKD method consists of two main components. Firstly, a graph-based multi-modal propagation module is designed to bridge the cross-domain correlation among the visual and textual samples. Secondly, a contrastive momentum knowledge distillation module is proposed to learn the cross-modal feature representation using the online knowledge distillation strategy. By jointly optimizing the two modules, the proposed method is able to achieve efficient performance for cross-dataset text-to-image person retrieval. acExtensive experiments on three publicly available text-to-image person retrieval datasets demonstrate the effectiveness of the proposed GCKD method, which consistently outperforms the state-of-the-art baselines.