A Channel Pruning Algorithm Based on Depth-Wise Separable Convolution Unit
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2956976
Abstract: Deep learning has made significant progress in many fields such as image identification, speech recognition and natural language processing, especially in the field of computer vision. The better performance of the neural network often built… read more here.
Keywords: channel pruning; separable convolution; pruning algorithm; depth wise ... See more keywords
DESEM: Depthwise Separable Convolution-Based Multimodal Deep Learning for In-Game Action Anticipation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3271282
Abstract: In real-time strategy (RTS) games, to defeat their opponents, players need to choose and implement the correct sequential actions. Because RTS games like StarCraft II are real-time, players have a very limited time to choose… read more here.
Keywords: depthwise separable; game; separable convolution; convolution based ... See more keywords
An FPGA-Based Energy-Efficient Reconfigurable Depthwise Separable Convolution Accelerator for Image Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems II: Express Briefs"
DOI: 10.1109/tcsii.2022.3180553
Abstract: With the advances in massive computing ability and big data science, deep neural network (DNN) has been developing rapidly for different applications. However, due to its extensive computation and memory usage requirements, it calls for… read more here.
Keywords: depthwise separable; energy; accelerator; energy efficient ... See more keywords
Gradient Prior-Aided CNN Denoiser With Separable Convolution-Based Optimization of Feature Dimension
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2018.2859791
Abstract: We propose a novel image denoising method based on a convolutional neural network (CNN), which uses the separable convolution and the gradient prior to reduce the computational complexity while enhancing the denoising performance. The proposed… read more here.
Keywords: cnn denoiser; convolution; feature; gradient prior ... See more keywords
Accelerating hologram generation using oriented-separable convolution and wavefront recording planes.
Sign Up to like & getrecommendations! Published in 2022 at "Optics express"
DOI: 10.1364/oe.472121
Abstract: Recently, holographic displays have gained attention owing to their natural presentation of three-dimensional (3D) images; however, the enormous amount of computation has hindered their applicability. This study proposes an oriented-separable convolution accelerated using the wavefront-recording… read more here.
Keywords: wavefront recording; oriented separable; separable convolution; accelerating hologram ... See more keywords