Domain Adaptive Learning with Multi-granularity Features for Unsupervised Person Re-identification
Sign Up to like & getrecommendations! Published in 2022 at "Chinese Journal of Electronics"
DOI: 10.1049/cje.2020.00.072
Abstract: Unsupervised person re-identification (Re-ID) aims to improve the model's scalability and obtain better Re-ID results in the unlabeled data domain. In this paper, we propose an unsupervised person Re-ID method based on multi-granularity feature representation… read more here.
Keywords: person; multi granularity; granularity; domain ... See more keywords
Two-Branch Asymmetric Model With Alternately Clustering for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2021.3125828
Abstract: In the field of unsupervised person Re-identification (Re-ID), mainstream methods adopt cluster algorithm to generate pseudo labels for training. Despite the effectiveness, the cluster algorithm generates noisy labels, which are retained in further model updating… read more here.
Keywords: branch; two branch; unsupervised person; alternately clustering ... See more keywords
Global Relation-Aware Contrast Learning for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3194084
Abstract: The goal of unsupervised person re-identification (Re-ID) is to use unlabeled person images to learn discriminative features. In recent years, many approaches have adopted clustered pseudo labels to construct proxies for contrastive learning, and have… read more here.
Keywords: relation aware; learning; unsupervised person; person identification ... See more keywords
POSR: Pose-Aligned Outlier Sample Relabeling for Unsupervised Person Reidentification
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Instrumentation and Measurement"
DOI: 10.1109/tim.2025.3546396
Abstract: Unsupervised person reidentification (Re-ID) is crucial since it enables the matching of individuals without labeled data. Existing clustering-based methods directly discard outlier samples. However, these discarded outliers are not noise samples. In contrast, they are… read more here.
Keywords: outlier sample; person reidentification; aligned outlier; pose aligned ... See more keywords
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2022.3213193
Abstract: Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsupervised Re-ID is clustering-based, which generates pseudo labels by clustering and uses the… read more here.
Keywords: camera; camera aware; unsupervised person; aware proxies ... See more keywords
A Real-Time Memory Updating Strategy for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3266166
Abstract: Recently, clustering-based methods have been the dominant solution for unsupervised person re-identification (ReID). Memory-based contrastive learning is widely used for its effectiveness in unsupervised representation learning. However, we find that the inaccurate cluster proxies and… read more here.
Keywords: updating strategy; unsupervised person; cluster; strategy ... See more keywords
Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2024.3409685
Abstract: Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground-truth labels. Most existing methods rely on pseudo labels estimated via iterative clustering and thus are highly susceptible to performance penalties incurred by the… read more here.
Keywords: person; person identification; pairwise relationship; unsupervised person ... See more keywords
Complementary pseudolabel based on global-and-channel information for unsupervised person reidentification
Sign Up to like & getrecommendations! Published in 2023 at "Journal of Electronic Imaging"
DOI: 10.1117/1.jei.32.2.023030
Abstract: Abstract. Unsupervised person reidentification (re-ID) is designed to deal with the problem that in industrial application scenarios, the consistent features of the same person cannot be fully mined due to the lack of annotated information… read more here.
Keywords: information; person reidentification; person; unsupervised person ... See more keywords
Learning the Meta Feature Transformer for Unsupervised Person Re-Identification
Sign Up to like & getrecommendations! Published in 2024 at "Mathematics"
DOI: 10.3390/math12121812
Abstract: Although unsupervised person re-identification (Re-ID) has drawn increasing research attention, it still faces the challenge of learning discriminative features in the absence of pairwise labels across disjoint camera views. To tackle the issue of label… read more here.
Keywords: person identification; transformer; feature transformer; unsupervised person ... See more keywords