Unsupervised Person Re-Identification via Multi-Label Classification

Wang, Dongkai; Zhang, Shiliang

doi:10.1109/cvpr42600.2020.01099

Cited by 369 publications

(226 citation statements)

References 27 publications

Supporting

Mentioning

226

Contrasting

Order By: Relevance

“…As the popular technology in unlabeled pedestrian image re-id, many researches [3], [17], [18], [20], [30], [40], [46], [48] [30] formulated an unsupervised multi-label classification for per-…”

Section: ) Comparison With Unsupervised Clustering Methodsmentioning

confidence: 99%

“…This paper conducts comparison between unsupervised domain adaptation (UDA) [5], [7], [8], [16], [23] and clustering methods [3], [17], [18], [20], [30], [40], [46], [48]. The re-id results of these methods are reported in it proposed a multi-task dictionary learning method to learn a dataset-shared but target-data-biased person representation, which outperforms the former state-of-the-arts; Li et al [16] exploited useful knowledge of pre-existing labeled data from…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network

Lai

2021

IEEE Access

View full text Add to dashboard Cite

Section: ) Comparison With Unsupervised Clustering Methodsmentioning

confidence: 99%

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network

Lai

2021

IEEE Access

View full text Add to dashboard Cite

“…MAR [23] learned a soft multi-label from an auxiliary domain to learn identity-discriminative features. MMCL [24] predicted the image label by pair-wise similarity and conducted multi-label classification for feature learning. UDAP [25] proposed a self-training framework and provided a theoretical analysis on UDA re-ID.…”

Section: Related Work a Discriminative Learning Without Identitymentioning

confidence: 99%

“…We compare our proposed A 2 G framework with unsupervised, unsupervised domain adaptation, and attribute auxiliary weakly-supervised methods on four cross-dataset person re-ID tasks: Duke-to-Market, Market-to-Duke, MSMTto-Duke, and MSMT-to-Market. We compare three types of approaches, including unsupervised learning methods: PUAL [45], BUC [16], SSL [10], HCT [46], D-MMD [49], CSE [10], and TAUDL [47], transfer learning based methods: SPGAN [20], HHL [22], CFSM [48], ENC [15], UDATP [25], UCDA-CCE [50], PDA-Net [51], PCB-PAST [8], SSG [7], MMCL [24], DG-NET++ [52], B-SNR+GDS-H [53], DGNET [3], OG-Net [54], AE [17], and AD-Cluster [55], and attribute auxiliary weakly supervised method: TJ-AIDL [26].…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

Graph Neural Network Based Attribute Auxiliary Structured Grouping for Person Re-Identification

Tang

Gao²,

Chen

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recently, person re-identification (re-ID) with weakly labeled or unlabeled data has drawn much attention in open-set and cross-domain re-ID systems especially for the attribute auxiliary weakly supervised person re-ID. Although state-of-the-art clustering-based methods have achieved good performance, the pseudo labels generated through clustering are often low-quality and noisy. To address this problem, we propose a graph neural network based Attribute Auxiliary structured Grouping (A 2 G) to improve the confidence of the pseudo labels. Different from the existing clustering-based approaches that only utilize the similarity in feature space, we learn the feature representation from the similarities in both attribute space and feature space by graph learning on the pedestrian attribute graph. Specifically, we first utilize the pair-wise attribute similarity to represent the relation between two pedestrians to construct a pedestrian attribute graph. Furthermore, we aggregate the features from their neighborhood on a pedestrian attribute graph by the graph neural network, which would make the attribute similar pairs closer and simultaneously take the dissimilar pairs further in the feature space. Finally, to avoid the over-confidence of the hard pseudo labels, we regularize the learning of the embedding model with the smoothed pseudo label (SPL) in the optimization of the feature embedding network. We conduct extensive experiments on several person re-ID datasets to validate the efficacy of our proposed method. The results demonstrate that our technique is effective and promising for person re-ID tasks.INDEX TERMS Unsupervised person re-identification, attribute-auxiliary structured grouping, graph neural network.

show abstract

“…(ii) Label prediction methods: Cross-View Asymmetric Metric Learning (CAMEL) [28], Progressive Unsupervised Learning (PUL) [29], MultiAble Learning (MAR) [19], Multi-view Clustering Method (MCM) [30], Transductive Semi-Supervised Metric (TSSML) Learning [31], Unsupervised Graph Association (UGA) [32], Memory-based Multilabel Classification Loss method (MMCL) [33].…”

Section: Comparison To The-state-of-the-artsmentioning

confidence: 99%

Real-World Person Re-Identification via Super-Resolution and Semi-Supervised Methods

Xia

Zhu

2021

IEEE Access

View full text Add to dashboard Cite

Person re-identification has made great progress over the years. However, due to the problem of super-resolution and few labeled samples, it is difficult to apply in practice. In this paper, we propose a semi-supervised super-resolution person re-identification method based on soft multi-labels. Firstly, a Mixed-Space Super-Resolution model (MSSR) is constructed based on Generative Adversarial Networks (GAN), which aims to convert low-resolution person images into high-resolution images. Secondly, a Partbased Graph Convolutional Network (PGCN) is proposed to extract discriminative feature by exploring the relationship of local features within person. Finally, to solve the problem of label limitation, we use the PGCN trained with a small amount of labeled samples to predict the soft multi-labels of unlabeled samples, and further train PGCN with unlabeled samples based on a novel multi-label similarity loss. Experiments have been conducted on the Market1501, CUHK03, and MSMT17 datasets to evaluate this method, which show that it outperforms other semi-supervised methods.

show abstract

Unsupervised Person Re-Identification via Multi-Label Classification

Cited by 369 publications

References 27 publications

Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network

Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network

Graph Neural Network Based Attribute Auxiliary Structured Grouping for Person Re-Identification

Real-World Person Re-Identification via Super-Resolution and Semi-Supervised Methods

Contact Info

Product

Resources

About