Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Li, Yu-Jhe; Lin, Ci-Siang; Lin, Yan-Bo; Wang, Yu-Chiang Frank

doi:10.48550/arxiv.1909.09675

Cited by 4 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further compare our method with unsupervised domain adaptive methods including PTGAN [31], CamStyle [41], T-Fusion [22], ARN [19], MAR [34], ECN [39], PDA-Net [18], PAST [35], CAL-CCE [25], CR-GAN [1] and SSG [5], and semi-supervised methods including TAUDL [15], UTAL [16], SSG+ [5], and SSG++ [5]. Under the unsupervised domain adaptive training setting, our method achieves the best performance on both Market1501 and DukeMTMC-reID in Table 2.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Zhang

2020

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptive person Re-IDentification (ReID) is challenging because of the large domain gap between source and target domains, as well as the lackage of labeled data on the target domain. This paper tackles this challenge through jointly enforcing visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. The local one-hot classification assigns images in a training batch with different person IDs, then adopts a Self-Adaptive Classification (SAC) model to classify them. The global multi-class classification is achieved by predicting labels on the entire unlabeled training set with the Memory-based Temporal-guided Cluster (MTC). MTC predicts multi-class labels by considering both visual similarity and temporal consistency to ensure the quality of label prediction.The two classification models are combined in a unified framework, which effectively leverages the unlabeled data for discriminative feature learning. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks. For example, under unsupervised setting, our method outperforms recent unsupervised domain adaptive methods, which leverage more labels for training.

show abstract

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Zhang

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Benefiting from the power of CycleGAN [53], some scholars [12,7] utilize it to translate synthetic images to realistic data. Recently, some researchers attempt to disentangle the image content and style to translate images [10,5,29,22].…”

Section: Domain-adaptive Vision Tasksmentioning

confidence: 99%

Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction

Ji¹,

Han²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Recently, crowd counting using supervised learning achieves a remarkable improvement. Nevertheless, most counters rely on a large amount of manually labeled data. With the release of synthetic crowd data, a potential alternative is transferring knowledge from them to real data without any manual label. However, there is no method to effectively suppress domain gaps and output elaborate density maps during the transferring. To remedy the above problems, this paper proposed a Domain-Adaptive Crowd Counting (DACC) framework, which consists of Interdomain Features Segregation (IFS) and Gaussian-prior Reconstruction (GPR). To be specific, IFS translates synthetic data to realistic images, which contains domain-shared features extraction and domain-independent features decoration. Then a coarse counter is trained on translated data and applied to the real world. Moreover, according to the coarse predictions, GPR generates pseudo labels to improve the prediction quality of the real data. Next, we retrain a final counter using these pseudo labels. Adaptation experiments on six real-world datasets demonstrate that the proposed method outperforms the state-of-the-art methods. Furthermore, the code and pre-trained models will be released as soon as possible.

show abstract

A cross-domain person re-identification algorithm based on distribution-consistency and multi-label collaborative learning

Zhang,

Hao,

et al. 2024

Multimed Tools Appl

View full text Add to dashboard Cite

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Cited by 4 publications

References 45 publications

Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction

A cross-domain person re-identification algorithm based on distribution-consistency and multi-label collaborative learning

Contact Info

Product

Resources

About