Results 11 to 20 of about 4,886 (174)

Lightweight image classifier using dilated and depthwise separable convolutions [PDF]

Journal of Cloud Computing: Advances, Systems and Applications, 2020
The image classification based on cloud computing suffers from difficult deployment as the network depth and data volume increase. Due to the depth of the model and the convolution process of each layer will produce a great amount of calculation, the GPU
Wei Sun, Xiaorui Zhang, Xiaozheng He
doaj   +2 more sources

An Energy-Efficient Convolution Unit for Depthwise Separable Convolutional Neural Networks [PDF]

2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021
High performance but computationally expensive Convolutional Neural Networks (CNNs) require both algorithmic and custom hardware improvement to reduce model size and to improve energy efficiency for edge computing applications. Recent CNN architectures employ depthwise separable convolution to reduce the total number of weights and MAC operations ...
Chong, Yi Sheng, Goh, Wang Ling, Ong, Yew-Soon, Nambiar, Vishnu P., Do, Anh Tuan   +4 more
openaire   +3 more sources

Depthwise-STFT Based Separable Convolutional Neural Networks [PDF]

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the fact that the Fourier coefficients can accurately represent important features such as edges in an image.
Sudhakar Kumawat, Shanmuganathan Raman
openaire   +4 more sources

An Enhanced Lightweight Convolutional Neural Network for Ship Detection in Maritime Surveillance System

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022
With the extensive application of artificial intelligence, ship detection from optical satellite remote sensing images using deep learning technology can significantly improve detection accuracy.
Yifan Yin, Xu Cheng, Fan Shi, Meng Zhao, Guoyuan Li, Shengyong Chen   +5 more
doaj   +1 more source

LdsConv: Learned Depthwise Separable Convolutions by Group Pruning [PDF]

Sensors, 2020
Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning.
Wenxiang Lin, Yan Ding 0003, Hua-Liang Wei, Xinglin Pan, Yutong Zhang 0007   +4 more
openaire   +6 more sources

Classification of Petrographic Thin Section Images With Depthwise Separable Convolution and Dilated Convolution

IEEE Access
To enhance the precision and efficiency of petrographic thin section image classification and reduce the subjectivity resulting from manual classification methods, a new classification model (DC-PC-Dilated-IR-V2) in term of the deep convolutional network
Shaowei Pan, Xingxing Cheng, Wenjing Fan
doaj   +3 more sources

Source Separation and Depthwise Separable Convolutions for Computer Audition

CoRR, 2020
2 pages, to appear in the AAAI-21 student abstract and poster ...
Gabriel Mersy, Jin Hong Kuan
openaire   +2 more sources

Detection Method of Autonomous Landing Marker for UAV Based on Deep Learning [PDF]

Hangkong bingqi, 2023
Aiming at improving the real-time performance and accuracy of UAV autonomous landing, a landing marker detection method based on deep learning is proposed.
Li Dan, Deng Fei, Zhao Liangyu, Liu Fuxiang
doaj   +1 more source

Facial Mask Detection Using Depthwise Separable Convolutional Neural Network Model During COVID-19 Pandemic

Frontiers in Public Health, 2022
Deep neural networks have made tremendous strides in the categorization of facial photos in the last several years. Due to the complexity of features, the enormous size of the picture/frame, and the severe inhomogeneity of image data, efficient face ...
Muhammad Zubair Asghar, Muhammad Zubair Asghar, Fahad R. Albogamy, Mabrook S. Al-Rakhami, Junaid Asghar, Mohd Khairil Rahmat, Muhammad Mansoor Alam, Muhammad Mansoor Alam, Muhammad Mansoor Alam, Muhammad Mansoor Alam, Muhammad Mansoor Alam, Adidah Lajis, Haidawati Mohamad Nasir   +12 more
doaj   +1 more source

Sound Event Detection with Depthwise Separable and Dilated Convolutions [PDF]

2020 International Joint Conference on Neural Networks (IJCNN), 2020
State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal context in the extracted features.
Konstantinos Drossos, Stylianos I. Mimilakis, Shayan Gharib, Yanxiong Li, Tuomas Virtanen   +4 more
openaire   +3 more sources