Masked Attribute Description Embedding for Cloth-Changing Person Re-identification

• URL: http://arxiv.org/abs/2401.05646v3
• Date: Tue, 2 Jul 2024 09:56:26 GMT
• Title: Masked Attribute Description Embedding for Cloth-Changing Person Re-identification
• Authors: Chunlei Peng, Boyu Wang, Decheng Liu, Nannan Wang, Ruimin Hu, Xinbo Gao,
• Abstract summary: Cloth-changing person re-identification (CC-ReID) aims to match persons who change clothes over long periods. The key challenge in CC-ReID is to extract clothing-independent features, such as face, hairstyle, body shape, and gait. We propose a Masked Attribute Description Embedding (MADE) method that unifies personal visual appearance and attribute description for CC-ReID.
• Score: 66.53045140286987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cloth-changing person re-identification (CC-ReID) aims to match persons who change clothes over long periods. The key challenge in CC-ReID is to extract clothing-independent features, such as face, hairstyle, body shape, and gait. Current research mainly focuses on modeling body shape using multi-modal biological features (such as silhouettes and sketches). However, it does not fully leverage the personal description information hidden in the original RGB image. Considering that there are certain attribute descriptions which remain unchanged after the changing of cloth, we propose a Masked Attribute Description Embedding (MADE) method that unifies personal visual appearance and attribute description for CC-ReID. Specifically, handling variable clothing-sensitive information, such as color and type, is challenging for effective modeling. To address this, we mask the clothing and color information in the personal attribute description extracted through an attribute detection model. The masked attribute description is then connected and embedded into Transformer blocks at various levels, fusing it with the low-level to high-level features of the image. This approach compels the model to discard clothing information. Experiments are conducted on several CC-ReID benchmarks, including PRCC, LTCC, Celeb-reID-light, and LaST. Results demonstrate that MADE effectively utilizes attribute description, enhancing cloth-changing person re-identification performance, and compares favorably with state-of-the-art methods. The code is available at https://github.com/moon-wh/MADE.

Related papers

• CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification [47.948622774810296]
  We propose a novel framework called CLIP-Driven Cloth-Agnostic Feature Learning (CCAF) for Cloth-Changing Person Re-Identification (CC-ReID) Two modules were custom-designed: the Invariant Feature Prompting (IFP) and the Clothes Feature Minimization (CFM) Experiments have demonstrated the effectiveness of the proposed CCAF, achieving new state-of-the-art performance on several popular CC-ReID benchmarks without any additional inference time.
  arXiv  Detail & Related papers  (2024-06-13T14:56:07Z)
• When StyleGAN Meets Stable Diffusion: a $\mathscr{W}_+$ Adapter for Personalized Image Generation [60.305112612629465]
  Text-to-image diffusion models have excelled in producing diverse, high-quality, and photo-realistic images. We present a novel use of the extended StyleGAN embedding space $mathcalW_+$ to achieve enhanced identity preservation and disentanglement for diffusion models. Our method adeptly generates personalized text-to-image outputs that are not only compatible with prompt descriptions but also amenable to common StyleGAN editing directions.
  arXiv  Detail & Related papers  (2023-11-29T09:05:14Z)
• Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification [78.52704557647438]
  We propose a novel FIne-grained Representation and Recomposition (FIRe$2$) framework to tackle both limitations without any auxiliary annotation or data. Experiments demonstrate that FIRe$2$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks.
  arXiv  Detail & Related papers  (2023-08-21T12:59:48Z)
• Clothes-Changing Person Re-identification with RGB Modality Only [102.44387094119165]
  We propose a Clothes-based Adrial Loss (CAL) to mine clothes-irrelevant features from the original RGB images. Videos contain richer appearance and additional temporal information, which can be used to model propertemporal patterns.
  arXiv  Detail & Related papers  (2022-04-14T11:38:28Z)
• Video Person Re-identification using Attribute-enhanced Features [49.68392018281875]
  We propose a novel network architecture named Attribute Salience Assisted Network (ASA-Net) for attribute-assisted video person Re-ID. To learn a better separation of the target from background, we propose to learn the visual attention from middle-level attribute instead of high-level identities.
  arXiv  Detail & Related papers  (2021-08-16T07:41:27Z)
• CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature [31.425326840578098]
  We propose a novel GAN model which is designed to edit only the parts of a face pertinent to the target attributes. CAFE identifies the facial regions to be transformed by considering both target attributes as well as complementary attributes.
  arXiv  Detail & Related papers  (2020-11-24T05:21:03Z)
• Learning Shape Representations for Clothing Variations in Person Re-Identification [34.559050607889816]
  Person re-identification (re-ID) aims to recognize instances of the same person contained in multiple images taken across different cameras. We propose a novel representation learning model which is able to generate a body shape feature representation without being affected by clothing color or patterns. Case-Net learns a representation of identity that depends only on body shape via adversarial learning and feature disentanglement.
  arXiv  Detail & Related papers  (2020-03-16T17:23:50Z)

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.