A survey of deep network techniques all classifiers can adopt

A Ghods, DJ Cook - Data mining and knowledge discovery, 2021 - Springer
Deep neural networks (DNNs) have introduced novel and useful tools to the machine
learning community. Other types of classifiers can potentially make use of these tools as well …

Coarse-to-fine: Progressive knowledge transfer-based multitask convolutional neural network for intelligent large-scale fault diagnosis

Y Wang, R Liu, D Lin, D Chen, P Li… - … on Neural Networks …, 2021 - ieeexplore.ieee.org
In modern industry, large-scale fault diagnosis of complex systems is emerging and
becoming increasingly important. Most deep learning-based methods perform well on small …

Label relation graphs enhanced hierarchical residual network for hierarchical multi-granularity classification

J Chen, P Wang, J Liu, Y Qian - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Hierarchical multi-granularity classification (HMC) assigns hierarchical multi-granularity
labels to each object and focuses on encoding the label hierarchy, eg,[" Albatross"," Laysan …

[HTML][HTML] Unimodal regularisation based on beta distribution for deep ordinal regression

VM Vargas, PA Gutiérrez, C Hervás-Martínez - Pattern Recognition, 2022 - Elsevier
Currently, the use of deep learning for solving ordinal classification problems, where
categories follow a natural order, has not received much attention. In this paper, we propose …

A parallel grid-search-based SVM optimization algorithm on Spark for passenger hotspot prediction

D Xia, Y Zheng, Y Bai, X Yan, Y Hu, Y Li… - Multimedia Tools and …, 2022 - Springer
Predicting passenger hotspots helps drivers quickly pick up travelers, reduces cruise
expenses, and maximizes revenue per unit time in intelligent transportation systems. To …

Fabric retrieval based on multi-task learning

J Xiang, N Zhang, R Pan, W Gao - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
Due to the potential values in many areas such as e-commerce and inventory management,
fabric image retrieval, which is a special case in Content Based Image Retrieval (CBIR), has …

Hierarchical semantic risk minimization for large-scale classification

Y Wang, Z Wang, Q Hu, Y Zhou… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Hierarchical structures of labels usually exist in large-scale classification tasks, where labels
can be organized into a tree-shaped structure. The nodes near the root stand for coarser …

Tumor bagging: a novel framework for brain tumor segmentation using metaheuristic optimization algorithms

SN Shivhare, N Kumar - Multimedia Tools and Applications, 2021 - Springer
Brain tumor segmentation is a challenging research problem and several methods in
literature have been suggested for addressing the same. In this paper, we propose a novel …

Integrating model-and data-driven methods for synchronous adaptive multi-band image fusion

S Lin, Z Han, D Li, J Zeng, X Yang, X Liu, F Liu - Information Fusion, 2020 - Elsevier
A novel synchronous adaptive framework for multi-band image fusion is proposed, based on
integrated model-and data-driven (MDDR) techniques. This approach includes a deep stack …

Bio-inspired representation learning for visual attention prediction

Y Yuan, H Ning, X Lu - IEEE transactions on cybernetics, 2019 - ieeexplore.ieee.org
Visual attention prediction (VAP) is a significant and imperative issue in the field of computer
vision. Most of the existing VAP methods are based on deep learning. However, they do not …