PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Trinh, Quoc-Huy, Bui, Nhat-Tan, Hoang, Dinh-Hieu, Thi, Phuoc-Thao Vo, Nguyen, Hai-Dang, Jha, Debesh, Bagci, Ulas, Le, Ngan, Tran, Minh-Triet
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929368716017664
author Trinh, Quoc-Huy
Bui, Nhat-Tan
Hoang, Dinh-Hieu
Thi, Phuoc-Thao Vo
Nguyen, Hai-Dang
Jha, Debesh
Bagci, Ulas
Le, Ngan
Tran, Minh-Triet
author_facet Trinh, Quoc-Huy
Bui, Nhat-Tan
Hoang, Dinh-Hieu
Thi, Phuoc-Thao Vo
Nguyen, Hai-Dang
Jha, Debesh
Bagci, Ulas
Le, Ngan
Tran, Minh-Triet
contents Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module (PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05634
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
Trinh, Quoc-Huy
Bui, Nhat-Tan
Hoang, Dinh-Hieu
Thi, Phuoc-Thao Vo
Nguyen, Hai-Dang
Jha, Debesh
Bagci, Ulas
Le, Ngan
Tran, Minh-Triet
Computer Vision and Pattern Recognition
Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module (PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS.
title PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05634