Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Hao Chen et al.
Summary: This work proposes a generative adversarial network (GAN) for unsupervised representation learning in person re-identification (ReID). By replacing traditional data augmentation with the GAN, augmented views are generated for contrastive learning. The GAN-based augmentation is performed on both id-unrelated and id-related features, and specific contrastive losses are proposed to help the network learn invariance. The method achieves new state-of-the-art unsupervised person ReID performance on large-scale benchmarks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Bo Pang et al.
Summary: This study proposes a novel selective contrastive learning framework for fully unsupervised feature learning. Experimental results demonstrate the superiority of the method in unsupervised person ReID compared with the state of the art.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yingchun Guo et al.
Summary: This paper proposes a method called JAC-Net for person re-identification in an unlabeled target domain. It uses clustering to generate pseudo-labels and optimizes the training network using a joint learning network and a concise attention module. Experiments show that JAC-Net achieves good performance on multiple datasets and reaches a similar level to supervised learning methods.
Article
Computer Science, Information Systems
Yihu Song et al.
Summary: This paper proposes an unsupervised person re-identification (Re-ID) model based on softened labels training method. By utilizing the correlation among image features, reliable positive samples are identified and several modules are designed to further explore the feature correlations. The experimental results demonstrate that the proposed method outperforms most state-of-the-art models in fully unsupervised Re-ID task.
Article
Computer Science, Artificial Intelligence
Kaifang Li et al.
Summary: This research proposes a novel cross-modality disentanglement and shared feedback learning framework for infrared-visible person re-identification. With two networks, the framework achieves modality-level and feature-level alignment while maintaining identity-consistency. Experimental results demonstrate that the method achieves competitive performance compared to state-of-the-art methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jing Zhao et al.
Summary: This study proposes a heterogeneous learning framework based on pseudo-supervised learning, achieving improved feature expression and label prediction in the case of few-shot labeled samples. By constructing a novel isomer as the feature extractor and training it with pseudo-supervised data, the quality of pseudo-labels is enhanced. Furthermore, the introduction of a cross-level asynchronous match mechanism and a knowledge fusion strategy further optimizes the performance.
Article
Computer Science, Artificial Intelligence
Xile Wang et al.
Summary: This study introduces a new Multi-information Fusion reinforced Global Attention (MIFGA) module that effectively combines various information and guides attention learning to extract pedestrian features suitable for clustering. MIFGA includes spatial attention and channel attention, utilizing spatial topology information and channel affinity information, significantly improving the performance of the baseline model and achieving competitive results on multiple standard datasets.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Fengxiang Yang et al.
Summary: This paper proposes a unified framework to solve the problem of unsupervised person re-identification by introducing a Dynamic and Symmetric Cross-Entropy loss and a camera-aware meta-learning algorithm. The proposed method effectively addresses noisy samples and camera shift issues, outperforming state-of-the-art methods in both fully unsupervised re-ID and unsupervised domain adaptive re-ID.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zechen Bai et al.
Summary: This study introduces a novel unsupervised domain adaptation (UDA) method for person re-identification (re-ID) by incorporating the multi-source concept, utilizing multiple source datasets during training to fully exploit labeled data. The research addresses the domain gaps from domain-specific and domain-fusion views, proposing two compatible constructive modules to enhance model performance. The proposed method surpasses state-of-the-art UDA person re-ID methods and achieves comparable performance to supervised approaches without any post-processing techniques.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Computer Science, Information Systems
Wenhui Dong et al.
Summary: This paper proposes an unsupervised cross-domain adaptive person re-identification framework, which combines the internal similarity of the target domain and the similarity between the source domain and the target domain through horizontal pyramid similarity learning. The framework can effectively adapt to the target domain and outperforms state-of-the-art unsupervised cross-domain person re-identification approaches in experiments.
Article
Computer Science, Information Systems
Yuhang Ding et al.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Yingzhi Tang et al.
Article
Computer Science, Artificial Intelligence
Kai Wang et al.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Shaoqing Ren et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Artificial Intelligence
Pedro F. Felzenszwalb et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2010)
