128 citations · 252 across the 28 of their papers we have counts for
Showing 2018 · cs.CVShow all
3 papers · 2 filters
cs.CV2018
Penetrating the Fog: the Path to Efficient CNN Models
Kun Wan, Boyuan Feng, Shu Yang +1
With the increasing demand to deploy convolutional neural networks (CNNs) on mobile platforms, the sparse kernel approach was proposed, which could save more parameters than the st…
cs.CV2018
Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout
Kun Wan, Boyuan Feng, Lingwei Xie +1
Recently convolutional neural networks (CNNs) achieve great accuracy in visual recognition tasks. DenseNet becomes one of the most popular CNN models due to its effectiveness in fe…
cs.CV2018★ 3 cited
SECS: Efficient Deep Stream Processing via Class Skew Dichotomy
Boyuan Feng, Kun Wan, Shu Yang +1
Despite that accelerating convolutional neural network (CNN) receives an increasing research focus, the save on resource consumption always comes with a decrease in accuracy. To bo…