mlsanityData to 14 Oct 2026

Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval

arXiv 2507.10195 ↗First posted 14 Jul 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting, color, and viewpoint, limits the effectiveness of the pretrain-finetune paradigm. To overcome this issue, we propose a unified pipeline incorporating domain adaptation at both image and region levels. Our method features two key components: Domain-aware Diffusion (DaD) for image-level adaptation, which aligns image distributions between synthetic and real-world domains, e.g., CUHK-PEDES, and Multi-granularity Relation Alignment (MRA) for region-level adaptation, which aligns visual regions with descriptive sentences, thereby addressing disparities at a finer granularity. This dual-level strategy effectively bridges the domain gap, achieving state-of-the-art performance on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/MRA.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 65 of its 86 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

65 of 86 references.

References · 65

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  12. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
38 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  3. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  6. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  7. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  9. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  10. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  11. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  12. 2017Generative Adversarial Networks: An Overviewcited by 590
  13. 2023Zero-shot Image-to-Image Translationcited by 505
  14. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  15. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  16. 2018Stacked Cross Attention for Image-Text Matchingcited by 416
  17. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 327
  18. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  19. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  20. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  21. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 172
  22. 2017Person Search with Natural Language Descriptioncited by 149
  23. 2017Dual-Path Convolutional Image-Text Embeddings with Instance Losscited by 145
  24. 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrievalcited by 132
  25. 2021Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identificationcited by 110
  26. 2021DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrievalcited by 102
  27. 2017Improving Person Re-identification by Attribute and Identity Learningcited by 96
  28. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  29. 2023Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusioncited by 81
  30. 2022CLIP-Driven Fine-grained Text-Image Person Re-identificationcited by 79
  31. 2020ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Languagecited by 78
  32. 2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
  33. 2022See Finer, See More: Implicit Modality Alignment for Text-based Person Retrievalcited by 65
  34. 2019Improving Description-based Person Re-identification by Multi-granularity Image-text Alignmentscited by 64
  35. 2021Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Searchcited by 62
  36. 2022Learning Granularity-Unified Representations for Text-to-Image Person Re-identificationcited by 62
  37. 2021TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Searchcited by 57
  38. 2022NFormer: Robust Person Re-identification with Neighbor Transformercited by 57

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Searchcited by 4
  2. 2026Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Searchcited by 0
  3. 2026Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
  2. 2023Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
  3. 2024Multi-path Exploration and Feedback Adjustment for Text-to-Image Person Retrieval
  4. 2025Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
  5. 2025An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval
  6. 2026Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation
  7. 2026ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval
  8. 2025Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning