Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification

2018-04-25 · Yu-Jhe Li, Fu-En Yang, Yen-Cheng Liu, Yu-Ying Yeh, Xiaofei Du, Yu-Chiang Frank Wang

Person re-identification (Re-ID) aims at recognizing the same person from images taken across different cameras. To address this task, one typically requires a large amount labeled data for training an effective Re-ID model, which might not be practical for real-world applications. To alleviate this limitation, we choose to exploit a sufficient amount of pre-existing labeled data from a different (auxiliary) dataset. By jointly considering such an auxiliary dataset and the dataset of interest (but without label information), our proposed adaptation and re-identification network (ARN) performs unsupervised domain adaptation, which leverages information across datasets and derives domain-invariant features for Re-ID purposes. In our experiments, we verify that our network performs favorably against state-of-the-art unsupervised Re-ID approaches, and even outperforms a number of baseline Re-ID methods which require fully supervised data for training.

📄 PDF Abstract BibTeX arXiv:1804.09347

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Person Re-Identification Transfer Learning Unsupervised Domain Adaptation

Online Unsupervised Domain Adaptation for Person Re-identification

2022-05-09 · Hamza Rami, Matthieu Ospici, Stéphane Lathuilière

Unsupervised domain adaptation for person re-identification (Person Re-ID) is the task of transferring the learned knowledge on the labeled source domain to the unlabeled target domain. Most of the recent papers that add…

Domain Adaptation Online unsupervised domain adaptation Person Re-Identification Unsupervised Domain Adaptation

Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification

2020-07-30 · Yacine Khraimeche, Guillaume-Alexandre Bilodeau, David Steele, Harshad Mahadik

While recent person re-identification (ReID) methods achieve high accuracy in a supervised setting, their generalization to an unlabelled domain is still an open problem. In this paper, we introduce a novel unsupervised …

Disentanglement Domain Adaptation Domain Adaptive Person Re-Identification Generative Adversarial Network+2

Real-Time Online Unsupervised Domain Adaptation for Real-World Person Re-identification

2023-06-06 · Christopher Neff, Armin Danesh Pazho, Hamed Tabkhi

Following the popularity of Unsupervised Domain Adaptation (UDA) in person re-identification, the recently proposed setting of Online Unsupervised Domain Adaptation (OUDA) attempts to bridge the gap towards practical app…

Domain Adaptation Online unsupervised domain adaptation Person Re-Identification Unsupervised Domain Adaptation

Unsupervised Domain Adaptation for Cross-Regional Scenes Person Re-identification

2023-03-15 · Shanghai Jiao Tong Univ 2023 3 · Mao Yanmei, Li Huafeng, Zhang Yafei

In large-scale surveillance systems, the absence of positive cross-camera pedestrian samples in cross-regional scenes poses a limitation on the performance of person re-identification models. To tackle this challenge, an…

Domain Adaptation Domain Adaptive Person Re-Identification Person Re-Identification Style Transfer+1

Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

2019-05-14 · Chuan-Xian Ren, Bo-Hua Liang, Zhen Lei

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The …

Domain Adaptation Domain Adaptive Person Re-Identification Person Re-Identification Unsupervised Domain Adaptation