Results 131 to 140 of about 4,886 (174)
Optimizing Depthwise Separable Convolution Operations on GPUs [PDF]
IEEE Transactions on Parallel and Distributed Systems, 2022 The depthwise separable convolution is widely used to reduce the computation overhead of multi-channel 2D convolutions. Existing implementations of depthwise separable convolutions target accelerating model training with large batch size with a large number of samples to be processed at once.
Zheng Wang, Lu Gangzhao, Weizhe Zhang
exaly +4 more sources
Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks [PDF]
Sensors, 2021 Kejun Wang, Liangliang Liu, Gang Hu
exaly +2 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Falcon: Lightweight and Accurate Convolution Based on Depthwise Separable Convolution
Knowledge and Information Systems, 2023U Kang, Jun-Gi Jang
exaly +2 more sources
Xception: Deep Learning With Depthwise Separable Convolutions [PDF]
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution).
exaly +4 more sources
Accelerating Depthwise Separable Convolutions with Vector Processor
2021Depthwise separable convolution has demonstrated its advantages in reducing the number of parameters and neural network calculations. Convolution-oriented hardware accelerators are outstanding in terms of saving resources and energy. However, lightweight networks designed for small processors do not perform efficiently on these accelerators.
Yuekai Zhao, Jianzhuang Lu, Xiaowen Chen
openaire +2 more sources
Pruning Depthwise Separable Convolutions for MobileNet Compression
2020 International Joint Conference on Neural Networks (IJCNN), 2020Deep convolutional neural networks are good at accuracy while bad at efficiency. To improve the inference speed, two directions have been explored in the past, lightweight model designing and network weight pruning. Lightweight models have been proposed to improve the speed with good enough accuracy.
Cheng-Hao Tu 0001 +3 more
openaire +1 more source
A CNN Accelerator on FPGA Using Depthwise Separable Convolution
IEEE Transactions on Circuits and Systems II: Express Briefs, 2018 Accepted by IEEE Transaction on Circuits and Systems II: Express Briefs, Volume 65, Issue 10, Oct ...
Lin Bai, Yiming Zhao, Xinming Huang
exaly +4 more sources
Depthwise Separable Convolution Architectures for Plant Disease Classification
Computers and Electronics in Agriculture, 2019Abstract Convolutional neural network has a huge partake and is still a dominating tool in the field of computer vision. In this study, we introduce a model with depthwise separable convolution architecture for plant disease detection based on images of leaves.
Kamal Kc, Mingyang Wu, Zhendong Yin
exaly +3 more sources
Generative Robotic Grasping Using Depthwise Separable Convolution
Computers & Electrical Engineering, 2021Abstract In this paper, we present an end-to-end approach method using deep learning for grasp detection. Our method is a real-time processing method for discrete depth image sampling and the problems of long calculation times and difficulty in registration caused by object modelling and global searching in traditional methods.
Yadong Teng, Pengxiang Gao
openaire +1 more source
Source Separation and Depthwise Separable Convolutions for Computer Audition (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence, 2021Given recent advances in deep music source separation, we propose a feature representation method that combines source separation with a state-of-the-art representation learning technique that is suitably repurposed for computer audition (i.e. machine listening).
Gabriel Mersy, Jin Hong Kuan
openaire +2 more sources