A novel transformer-based few-shot learning method for intelligent fault diagnosis with noisy labels under varying working conditions

H Wang, C Li, P Ding, S Li, T Li, C Liu, X Zhang… - Reliability Engineering & …, 2024 - Elsevier
Recent years have witnessed the success of Few-shot Learning (FSL) methods in
equipment reliability enhancement and fault diagnosis, by virtue of learning from limited data …

A semantic perception and CNN-transformer hybrid network for occluded person re-identification

Z Gao, P Chen, T Zhuo, M Liu, L Zhu… - … on Circuits and …, 2023 - ieeexplore.ieee.org
The objective of the occluded person re-identification (ReID) task is to capture the same
person from different camera angles when the pedestrian's body is partially occluded. In this …

Dual clustering co-teaching with consistent sample mining for unsupervised person re-identification

Z Chen, Z Cui, C Zhang, J Zhou… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate
training has been proven to be an effective method to deal with the pseudo label noise …

Superpixel-wise contrast exploration for salient object detection

Y Qiu, J Mei, J Xu - Knowledge-Based Systems, 2024 - Elsevier
Salient object detection (SOD) methods typically consider SOD as a pixel-wise binary
classification problem and utilize the binary cross-entropy (BCE) loss for optimization …

Source-free style-diversity adversarial domain adaptation with privacy-preservation for person re-identification

X Qu, L Liu, L Zhu, L Nie, H Zhang - Knowledge-Based Systems, 2024 - Elsevier
Unsupervised domain adaptation (UDA) techniques for person re-identification (ReID) have
been extensively studied to facilitate the transfer of knowledge from labeled source domains …

[HTML][HTML] Human-in-the-loop cross-domain person re-identification

R Delussu, L Putzu, G Fumera - Expert Systems with Applications, 2023 - Elsevier
Person re-identification is a challenging cross-camera matching problem, which is inherently
subject to domain shift. To mitigate it, many solutions have been proposed so far, based on …

Hierarchical camera-aware contrast extension for unsupervised person re-identification

X Luo, M Jiang, J Kong, X Tao - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised person re-identification (Re-ID) targets to learn discriminative representations
without annotations. Recently, clustering-based methods have shown promising …

Knowledge Consistency Distillation for Weakly Supervised One Step Person Search

Z Li, Y Shi, H Ling, J Chen, R Wang… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Weakly supervised person search targets to detect and identify a person with only bounding
box annotations. Recent approaches have focused on learning person relations in a single …

Reliable cross-camera learning in random camera person re-identification

Z Liu, Y Lin, T Liu, B Du - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Most existing person re-identification (Re-ID) methods rely on high-cost manual annotations.
To overcome the applicable issue, we focus on a novel semi-supervised Re-ID without cross …

Deep Mutual Distillation for Unsupervised Domain Adaptation Person Re-identification

X Gao, Z Chen, J Wei, R Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised domain adaptation person re-identification (UDA person re-ID) aims at
transferring the knowledge on the source domain with expensive manual annotation to the …