Convolutional neural networks: A survey
M Krichen - Computers, 2023 - mdpi.com
Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing
industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of …
industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of …
Knowledge distillation in vision transformers: A critical review
In Natural Language Processing (NLP), Transformers have already revolutionized the field
by utilizing an attention-based encoder-decoder model. Recently, some pioneering works …
by utilizing an attention-based encoder-decoder model. Recently, some pioneering works …
Towards efficient post-training quantization of pre-trained language models
Network quantization has gained increasing attention with the rapid growth of large pre-
trained language models~(PLMs). However, most existing quantization methods for PLMs …
trained language models~(PLMs). However, most existing quantization methods for PLMs …
Matrix compression via randomized low rank and low precision factorization
Matrices are exceptionally useful in various fields of study as they provide a convenient
framework to organize and manipulate data in a structured manner. However, modern …
framework to organize and manipulate data in a structured manner. However, modern …
Model compression of deep neural network architectures for visual pattern recognition: Current status and future directions
S Bhalgaonkar, M Munot - Computers and Electrical Engineering, 2024 - Elsevier
Abstract Visual Pattern Recognition Networks (VPRNs) are widely used in various visual
data based applications such as computer vision and edge AI. VPRNs help to enhance a …
data based applications such as computer vision and edge AI. VPRNs help to enhance a …
Illumination and temperature-aware multispectral networks for edge-computing-enabled pedestrian detection
Accurate and efficient pedestrian detection is crucial for the intelligent transportation system
regarding pedestrian safety and mobility, eg, Advanced Driver Assistance Systems, and …
regarding pedestrian safety and mobility, eg, Advanced Driver Assistance Systems, and …
Attention mechanism and texture contextual information for steel plate defects detection
In order to achieve rapid inference and generalization results, the majority of Convolutional
Neural Network (CNN) based semantic segmentation models strive to mine high-level …
Neural Network (CNN) based semantic segmentation models strive to mine high-level …
An information-theoretic justification for model pruning
We study the neural network (NN) compression problem, viewing the tension between the
compression ratio and NN performance through the lens of rate-distortion theory. We choose …
compression ratio and NN performance through the lens of rate-distortion theory. We choose …
Performance optimization for variable bitwidth federated learning in wireless networks
This paper considers improving wireless communication and computation efficiency in
federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge …
federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge …
A wavelet-based compressive deep learning scheme for inverse scattering problems
Z Zong, Y Wang, Z Wei - IEEE Transactions on Geoscience and …, 2022 - ieeexplore.ieee.org
Recently, physics-assisted deep learning schemes (DLSs) have demonstrated the state-of-
the-art performance for solving inverse scattering problems (ISPs). However, most learning …
the-art performance for solving inverse scattering problems (ISPs). However, most learning …