2 papers
cs.CV2022
Compact Neural Networks via Stacking Designed Basic Units
Weichao Lan, Yiu-ming Cheung, Juyong Jiang
Unstructured pruning has the limitation of dealing with the sparse and irregular weights. By contrast, structured pruning can help eliminate this drawback but it requires complex c…
cs.CV2020
Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
Weichao Lan, Liang Lan
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of depl…