PAT++: a cautionary tale about generative visual augmentation for Object Re-identification

• URL: http://arxiv.org/abs/2507.15888v1
• Date: Sat, 19 Jul 2025 15:01:05 GMT
• Title: PAT++: a cautionary tale about generative visual augmentation for Object Re-identification
• Authors: Leonardo Santiago Benitez Pereira, Arathy Jeevan,
• Abstract summary: We assess the effectiveness of identity-preserving image generation for object re-identification.<n>Our results show consistent performance degradation, driven by domain shifts and failure to retain identity-defining features.<n>These findings challenge assumptions about the transferability of generative models to fine-grained recognition tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative data augmentation has demonstrated gains in several vision tasks, but its impact on object re-identification - where preserving fine-grained visual details is essential - remains largely unexplored. In this work, we assess the effectiveness of identity-preserving image generation for object re-identification. Our novel pipeline, named PAT++, incorporates Diffusion Self-Distillation into the well-established Part-Aware Transformer. Using the Urban Elements ReID Challenge dataset, we conduct extensive experiments with generated images used for both model training and query expansion. Our results show consistent performance degradation, driven by domain shifts and failure to retain identity-defining features. These findings challenge assumptions about the transferability of generative models to fine-grained recognition tasks and expose key limitations in current approaches to visual augmentation for identity-preserving applications.

Related papers

• Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification [16.586742421279137]
  Attribute-Guide ReID (AG-ReID) is a novel framework to extract fine-grained semantic attributes without additional data or annotations.<n>Our framework operates through a two-stage process: first generating attribute pseudo-labels that capture subtle visual characteristics, then introducing a dual-guidance mechanism.<n>Extensive experiments demonstrate that AG-ReID achieves state-of-the-art results on multiple widely-used Re-ID datasets.
  arXiv  Detail & Related papers  (2025-08-07T03:13:24Z)
• SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification [61.753607285860944]
  We propose a novel two-stage feature learning framework named SD-ReID for AG-ReID.<n>In the first stage, we train a simple ViT-based model to extract coarse-grained representations and controllable conditions.<n>In the second stage, we fine-tune the SD model to learn complementary representations guided by the controllable conditions.
  arXiv  Detail & Related papers  (2025-04-13T12:44:50Z)
• PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification [73.64560354556498]
  Vision Transformer (ViT) tends to overfit on most distinct regions of training data, limiting its generalizability and attention to holistic object features. We present PartFormer, an innovative adaptation of ViT designed to overcome the limitations in object Re-ID tasks. Our framework significantly outperforms state-of-the-art by 2.4% mAP scores on the most challenging MSMT17 dataset.
  arXiv  Detail & Related papers  (2024-08-29T16:31:05Z)
• A Simple Background Augmentation Method for Object Detection with Diffusion Model [53.32935683257045]
  In computer vision, it is well-known that a lack of data diversity will impair model performance. We propose a simple yet effective data augmentation approach by leveraging advancements in generative models. Background augmentation, in particular, significantly improves the models' robustness and generalization capabilities.
  arXiv  Detail & Related papers  (2024-08-01T07:40:00Z)
• Generative Unlearning for Any Identity [6.872154067622779]
  In certain domains related to privacy issues, advanced generative models along with strong inversion methods can lead to potential misuses. We propose an essential yet under-explored task called generative identity unlearning, which steers the model not to generate an image of a specific identity. We propose a novel framework, Generative Unlearning for Any Identity (GUIDE), which prevents the reconstruction of a specific identity by unlearning the generator with only a single image.
  arXiv  Detail & Related papers  (2024-05-16T08:00:55Z)
• 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)
• DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception [78.26734070960886]
  Current perceptive models heavily depend on resource-intensive datasets. We introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. Our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation.
  arXiv  Detail & Related papers  (2024-03-20T04:58:03Z)
• RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos [2.7569134765233536]
  RID-Twin is a pipeline that decouples identity from motion to perform automatic face de-identification in videos. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset.
  arXiv  Detail & Related papers  (2024-03-15T06:59:21Z)
• Transformer for Object Re-Identification: A Survey [69.61542572894263]
  Vision Transformers have spurred a growing number of studies delving deeper into Transformer-based Re-ID. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-01-13T03:17:57Z)
• StyleID: Identity Disentanglement for Anonymizing Faces [4.048444203617942]
  The main contribution of the paper is the design of a feature-preserving anonymization framework, StyleID. As part of the contribution, we present a novel disentanglement metric, three complementing disentanglement methods, and new insights into identity disentanglement. StyleID provides tunable privacy, has low computational complexity, and is shown to outperform current state-of-the-art solutions.
  arXiv  Detail & Related papers  (2022-12-28T12:04:24Z)

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.