Multiformer-based hybrid learning with outlier re-assignment for unsupervised person re-identification

Jiang, Min; Zhang, Qian; Kong, Jun

doi:10.1007/s13042-023-01945-z

Cited by 3 publications

(2 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterward, the camera-aware methods used for comparison include SSL, 23 JVTC, 40 IICS, 24 CAP, 26 IIDS, 25 LMCL, 7 and MHOR. 41 SSL 23 proposes a re-ID framework with re-assigned soft label distribution learned from similar images, and it also employs camera labels and partial details of each sample image to guide similarity estimation. JVTC 40 utilizes the combination of local one-hot classification and global multi-class classification to enforce visual and temporal consistency and ensure the quality of label prediction.…”

Section: Comparative Methodsmentioning

confidence: 99%

Joint global feature and part-based pyramid features for unsupervised person re-identification

Zhang,

Fan,

Zhou

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

In recent years, unsupervised person re-identification (re-ID) has attracted a lot of attention because it can save manual annotation costs and adapt to new scenes more conveniently in real-world applications. We focus on fully unsupervised learning-based re-ID, which aims to train a discriminative model based on unlabeled person images. In unsupervised learning, we need to generate pseudo labels by clustering convolutional features and then train convolutional neural network (CNN) models with these pseudo labels. The features used in the clustering process play an important role to ensure the quality of pseudo labels. Hence, we propose an enhancing feature extraction method to increase the reliability of generated pseudo labels and thus facilitate CNN model training. In order to enrich the obtained features, we carry out the feature extraction from both global and local aspects. The global features are extracted with ResNet50 backbone as many existing methods do. The local features are extracted by an additional part-based feature pyramid structure, in which the person image is divided into three parts and the features are extracted from each part with a pyramid structure. Then, we fuse the multi-layer pyramid features for each part as the local features. According to the joint global features and local features, the pseudo labels are predicted using clustering algorithms and further refined based on the similarity between global and local features. In addition, we design an inter-camera association learning component to effectively learn the ID discrimination ability across cameras. Extensive experiments on three large and representative person re-ID datasets demonstrate the effectiveness of the proposed approach.

show abstract

Section: Comparative Methodsmentioning

confidence: 99%

Joint global feature and part-based pyramid features for unsupervised person re-identification

Zhang,

Fan,

Zhou

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…This study examines the viability of network protection by consolidating artificial intelligence/ML into the spaces of mechanized reaction, danger forecast, and peculiarity discovery. Utilizing computer-based intelligence/ML calculations' capacities, associations might have the option to expect and defeat hurtful action, answer immediately to arising dangers, and invigorate their protections [15]. This article investigates the province of simulated intelligence/ML applications in online protection, displaying striking turns of events and their results.…”

Section: Introductionmentioning

confidence: 99%

Leveraging AI/ML for anomaly detection, threat prediction, and automated response

Olakunle Abayomi Ajala,

Olusegun Abiodun Balogun

2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

The rapid evolution of information and communication technologies, notably the Internet, has yielded substantial benefits while posing challenges to information system security. With an increasing frequency of cyber threats—from unauthorized access to data breaches—the digital landscape's vulnerability is evident. Addressing the financial impact of cybercrime, this study delves into the role of Artificial Intelligence (AI) and Machine Learning (ML) technologies in cybersecurity. Analyzing advancements and outcomes, the research explores practical techniques for anomaly detection, threat prediction, and automated response. By investigating prior research and real-world implementations, the study provides valuable insights into the potential of AI/ML, uncovering current trends, challenges, and prospects in enhancing cybersecurity tactics amid a dynamically changing threat landscape.

show abstract

Visible-infrared person re-identification with complementary feature fusion and identity consistency learning

Wang,

Chen,

Chai

et al. 2024

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Multiformer-based hybrid learning with outlier re-assignment for unsupervised person re-identification

Cited by 3 publications

References 64 publications

Joint global feature and part-based pyramid features for unsupervised person re-identification

Joint global feature and part-based pyramid features for unsupervised person re-identification

Leveraging AI/ML for anomaly detection, threat prediction, and automated response

Visible-infrared person re-identification with complementary feature fusion and identity consistency learning

Contact Info

Product

Resources

About