A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification

• URL: http://arxiv.org/abs/2511.05092v1
• Date: Fri, 07 Nov 2025 09:17:48 GMT
• Title: A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification
• Authors: Ruolin Li, Min Liu, Yuan Bian, Zhaoyang Li, Yuzhen Li, Xueping Wang, Yaonan Wang,
• Abstract summary: We propose a Dual-stage Prompt-driven Privacy-preserving Paradigm (DPPP)<n>In the first stage, we generate rich prompts incorporating multi-dimensional attributes that drive the diffusion model to synthesize diverse data end-to-end.<n>In the second stage, we propose a Prompt-driven Disentanglement Mechanism (PDM) to learn domain-invariant generalization features.
• Score: 42.56589115173974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With growing concerns over data privacy, researchers have started using virtual data as an alternative to sensitive real-world images for training person re-identification (Re-ID) models. However, existing virtual datasets produced by game engines still face challenges such as complex construction and poor domain generalization, making them difficult to apply in real scenarios. To address these challenges, we propose a Dual-stage Prompt-driven Privacy-preserving Paradigm (DPPP). In the first stage, we generate rich prompts incorporating multi-dimensional attributes such as pedestrian appearance, illumination, and viewpoint that drive the diffusion model to synthesize diverse data end-to-end, building a large-scale virtual dataset named GenePerson with 130,519 images of 6,641 identities. In the second stage, we propose a Prompt-driven Disentanglement Mechanism (PDM) to learn domain-invariant generalization features. With the aid of contrastive learning, we employ two textual inversion networks to map images into pseudo-words representing style and content, respectively, thereby constructing style-disentangled content prompts to guide the model in learning domain-invariant content features at the image level. Experiments demonstrate that models trained on GenePerson with PDM achieve state-of-the-art generalization performance, surpassing those on popular real and virtual Re-ID datasets.

Related papers

• DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer [21.788582116033684]
  Video Face Swapping (VFS) requires seamlessly injecting a source identity into a target video.<n>Existing methods struggle to maintain identity similarity and attribute preservation while preserving temporal consistency.<n>We propose a comprehensive framework to seamlessly transfer the superiority of Image Face Swapping to the video domain.
  arXiv  Detail & Related papers  (2026-01-04T08:07:11Z)
• OmniPerson: Unified Identity-Preserving Pedestrian Generation [12.060261814704022]
  We introduce OmniPerson, the first unified identity-preserving pedestrian generation pipeline for ReID tasks.<n>We present PersonSyn, the first large-scale dataset for multi-reference, controllable pedestrian generation.<n>We will open-source the full, pretrained model, and the PersonSyn dataset.
  arXiv  Detail & Related papers  (2025-12-02T09:24:34Z)
• Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval [15.126709823382539]
  This work advances Contrastive Language-Image Pre-training (CLIP) for person representation learning.<n>We develop a noise-resistant data construction pipeline that leverages the in-context learning capabilities of MLLMs.<n>We introduce the GA-DMS framework, which improves cross-modal alignment by adaptively masking noisy textual tokens.
  arXiv  Detail & Related papers  (2025-09-11T03:06:22Z)
• Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation [66.66243874361103]
  dataset generation faces two key challenges: 1) aligning generated samples with the target domain and 2) producing informative samples beyond the training data.<n>We propose Concept-Aware LoRA, a novel fine-tuning approach that selectively identifies and updates only the weights associated with necessary concepts for domain alignment.<n>We demonstrate its effectiveness in generating datasets for urban-scene segmentation, outperforming baseline and state-of-the-art methods in in-domain settings.
  arXiv  Detail & Related papers  (2025-03-28T06:23:29Z)
• UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition [42.86969216015855]
  Face recognition (FR) stands as one of the most crucial applications in computer vision.<n>We propose a framework to enhance intra-class diversity for synthetic face recognition, shortened as UIFace.<n> Experiments show that our method significantly surpasses previous approaches with even less training data and half the size of synthetic dataset.
  arXiv  Detail & Related papers  (2025-02-27T06:22:18Z)
• Personalized Representation from Personalized Generation [36.848215621708235]
  We formalize the challenge of using personalized synthetic data to learn personalized representations.<n>We show that our method improves personalized representation learning for diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T18:59:03Z)
• Retrieval-guided Cross-view Image Synthesis [3.7477511412024573]
  Cross-view image synthesis presents significant challenges in establishing reliable correspondences.<n>We propose a retrieval-guided framework that reimagines how retrieval techniques can facilitate effective cross-view image synthesis.<n>Our work bridges information retrieval and synthesis tasks, offering insights into how retrieval techniques can address complex cross-domain synthesis challenges.
  arXiv  Detail & Related papers  (2024-11-29T07:04:44Z)
• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning [57.91881829308395]
  Identity-preserving text-to-image generation (ID-T2I) has received significant attention due to its wide range of application scenarios like AI portrait and advertising. We present textbfID-Aligner, a general feedback learning framework to enhance ID-T2I performance.
  arXiv  Detail & Related papers  (2024-04-23T18:41:56Z)
• VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition [13.81887339529775]
  VIGFace is a novel framework capable of generating synthetic facial images.<n>It shows clear separability between existing individuals and virtual face images, allowing one to create synthetic images with confidence.<n>It ensures improved performance through data augmentation by incorporating real existing images.
  arXiv  Detail & Related papers  (2024-03-13T06:11:41Z)
• Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search [60.626459715780605]
  Given a descriptive text query, text-based person search aims to retrieve the best-matched target person from an image gallery. Such a cross-modal retrieval task is quite challenging due to significant modality gap, fine-grained differences and insufficiency of annotated data. In this paper, we propose a simple yet effective dual Transformer model for text-based person search.
  arXiv  Detail & Related papers  (2023-11-15T16:26:49Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.