Deep Learning in Fringe Projection: a Review

H Liu, N Yan, B Shao, S Yuan, X Zhang - Neurocomputing, 2024 - Elsevier
Fringe projection is widely recognized as a prominent technique for 3D measurement, owing
to its non-contact nature, high precision, and exceptional spatial resolution. However, it …

A CNN pruning approach using constrained binary particle swarm optimization with a reduced search space for image classification

J Tmamna, EB Ayed, R Fourati, A Hussain… - Applied Soft …, 2024 - Elsevier
Deep convolutional neural networks (CNNs) have exhibited exceptional performance in a
range of computer vision tasks. However, these deep CNNs typically demand significant …

FedGKD: Towards Heterogeneous Federated Learning via Global Knowledge Distillation

D Yao, W Pan, Y Dai, Y Wan, X Ding… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Federated learning, as one enabling technology of edge intelligence, has gained substantial
attention due to its efficacy in training deep learning models without data privacy and …

MuxFlow: efficient GPU sharing in production-level clusters with more than 10000 GPUs

X Liu, Y Zhao, S Liu, X Li, Y Zhu, X Liu, X ** - Science China Information …, 2024 - Springer
Large-scale GPU clusters are widely used to speed up both latency-critical (online) and best-
effort (offline) deep learning (DL) workloads. However, similar to the common practice, the …

Tsplit: Fine-grained gpu memory management for efficient dnn training via tensor splitting

X Nie, X Miao, Z Yang, B Cui - 2022 IEEE 38th International …, 2022 - ieeexplore.ieee.org
Since Deep Neural Networks (DNNs) are deeper and larger, performing DNNs training on
existing accelerators (eg, GPUs) is challenging due to their limited device memory capacity …

Network intrusion detection based on the temporal convolutional model

IO Lopes, D Zou, IH Abdulqadder, S Akbar, Z Li… - Computers & …, 2023 - Elsevier
Recurrent networks have been adopted as default architecture in approaches performing
sequence modelling of network intrusion detection problems. However, models based on …

The orchestration of Machine Learning frameworks with data streams and GPU acceleration in Kafka‐ML: A deep‐learning performance comparative

AJ Chaves, C Martín, M Díaz - Expert Systems, 2024 - Wiley Online Library
Abstract Machine Learning (ML) applications need large volumes of data to train their
models so that they can make high‐quality predictions. Given digital revolution enablers …

Exploring the Impact of Code Clones on Deep Learning Software

R Mo, Y Zhang, Y Wang, S Zhang, P **
software systems across various domains. Deep learning frameworks have been proposed …