# Generative Retrieval for Unsupervised Text-Based Person Search

arXiv: https://arxiv.org/abs/2609.12965 · HTML: https://mlsanity.com/paper/2609.12965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 67 of its 106 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 30 of 67)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [Person Search with Natural Language Description](https://mlsanity.com/paper/1702.05729/) (2017)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)
- [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)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training](https://mlsanity.com/paper/2303.03032/) (2023)
- [Unpaired Image Captioning via Scene Graph Alignments](https://mlsanity.com/paper/1903.10658/) (2019)
- [Benchmarking and Improving Detail Image Caption](https://mlsanity.com/paper/2405.19092/) (2024)
- [Unsupervised Image Captioning](https://mlsanity.com/paper/1811.10787/) (2018)
- [CLIP-Driven Fine-grained Text-Image Person Re-identification](https://mlsanity.com/paper/2210.10276/) (2022)
- [ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language](https://mlsanity.com/paper/2005.07327/) (2020)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [Deconfounded Image Captioning: A Causal Retrospect](https://mlsanity.com/paper/2003.03923/) (2020)
- [Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments](https://mlsanity.com/paper/1906.09610/) (2019)
- [Exploring Diverse In-Context Configurations for Image Captioning](https://mlsanity.com/paper/2305.14800/) (2023)
- [Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search](https://mlsanity.com/paper/2101.03036/) (2021)
- [Learning Granularity-Unified Representations for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2207.07802/) (2022)
- [TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search](https://mlsanity.com/paper/2105.11628/) (2021)

## Abstract (arXiv)

Text-based person search (TBPS) aims to retrieve images of a target person from a large image gallery based on a given natural language description. Most existing methods rely on supervised learning with manually annotated image-text pairs. In this paper, we explore unsupervised TBPS, with only unlabeled images. We propose GTR+, a two-stage generation-then-retrieval framework. In the generation stage, we introduce a tiered description generation framework designed to produce fine-grained and stylistically diverse textual descriptions through a three-tier sequential process. The base tier leverages an automated question-and-answer mechanism to generate basic visual attribute descriptions; the intermediate tier enhances fine-grained detail using an inter-sample contrastive mechanism; the advanced tier further enriches textual diversity via a stylized expansion mechanism. In the retrieval stage, to mitigate the impact of noisy pseudo texts, we develop an adaptive confidence-weighted retrieval learning framework. We model image-text pairs as clean or noisy using a Gaussian Mixture Model, calibrated by real-time image-text similarity and static text generation probability from the prior stage, yielding adaptive sample weights during training. Beyond that, we also contribute LargeFine-Person, a large-scale TBPS dataset with high-quality, fine-grained, and diverse textual annotations, enabling a practical and generalizable TBPS pre-training benchmark under unsupervised setting. Experiments on multiple TBPS benchmarks demonstrate the effectiveness and generalization of both GTR+ and LargeFine-Person. Code is available at: https://github.com/Flame-Chasers/GTR.