mlsanityData to 14 Oct 2026

Leveraging Prior Knowledge of Diffusion Model for Person Search

arXiv 2510.01841 ↗First posted 2 Oct 2025cs.CVcited by 1

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Person search aims to jointly perform person detection and re-identification by localizing and identifying a query person within a gallery of uncropped scene images. Existing methods predominantly utilize ImageNet pre-trained backbones, which may be suboptimal for capturing the complex spatial context and fine-grained identity cues necessary for person search. Moreover, they rely on a shared backbone feature for both person detection and re-identification, leading to suboptimal features due to conflicting optimization objectives. In this paper, we propose DiffPS (Diffusion Prior Knowledge for Person Search), a novel framework that leverages a pre-trained diffusion model while eliminating the optimization conflict between two sub-tasks. We analyze key properties of diffusion priors and propose three specialized modules: (i) Diffusion-Guided Region Proposal Network (DGRPN) for enhanced person localization, (ii) Multi-Scale Frequency Refinement Network (MSFRN) to mitigate shape bias, and (iii) Semantic-Adaptive Feature Aggregation Network (SFAN) to leverage text-aligned diffusion features. DiffPS sets a new state-of-the-art on CUHK-SYSU and PRW.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 63 of its 80 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

63 of 80 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features4 Oct
  2. 2024Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers12 Mar
  3. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence24 May
  4. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence23 May
  5. 2023Your Diffusion Model is Secretly a Zero-Shot Classifier28 Mar
  6. 2023DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery17 Mar
  7. 2023Unleashing Text-to-Image Diffusion Models for Visual Perception3 Mar
  8. 2022DiffusionDet: Diffusion Model for Object Detection17 Nov
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  10. 2020Denoising Diffusion Implicit Modelscited by 9,781
  11. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  12. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
38 more
  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  2. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  6. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  7. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  8. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  9. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
  10. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  11. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  12. 2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
  13. 2016Person Re-identification in the Wildcited by 157
  14. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  15. 2023Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentationcited by 112
  16. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 96
  17. 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
  18. 2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
  19. 2023Intriguing properties of generative classifierscited by 52
  20. 2018Person Search via A Mask-Guided Two-Stream CNN Modelcited by 44
  21. 2021Anchor-Free Person Searchcited by 42
  22. 2019Re-ID Driven Localization Refinement for Person Searchcited by 41
  23. 2019Query-guided End-to-End Person Searchcited by 40
  24. 2019Learning Disentangled Representation for Robust Person Re-identificationcited by 40
  25. 2021Sequential End-to-end Network for Efficient Person Searchcited by 38
  26. 2019Mask-Guided Attention Network for Occluded Pedestrian Detectioncited by 36
  27. 2023Do text-free diffusion models learn discriminative visual representations?cited by 33
  28. 2022Cascade Transformers for End-to-End Person Searchcited by 31
  29. 2020Robust Partial Matching for Person Search in the Wildcited by 30
  30. 2020From Handcrafted to Deep Features for Pedestrian Detection: A Surveycited by 30
  31. 2017IAN: The Individual Aggregation Network for Person Searchcited by 29
  32. 2023LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentationcited by 29
  33. 2022PSTR: End-to-End One-Step Person Search With Transformerscited by 26
  34. 2022Domain Generalization via Frequency-domain-based Feature Disentanglement and Interactioncited by 21
  35. 2023Generative Prompt Model for Weakly Supervised Object Localizationcited by 20
  36. 2021Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Searchcited by 19
  37. 2022OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Searchcited by 12
  38. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DiCo: Disentangled Concept Representation for Text-to-image Person Re-identificationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
  2. 2024Lifelong Person Search
  3. 2024Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
  4. 2023VI-Diff: Unpaired Visible-Infrared Translation Diffusion Model for Single Modality Labeled Visible-Infrared Person Re-identification
  5. 2025DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
  6. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers
  7. 2023Emergent Correspondence from Image Diffusion
  8. 2024Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification