Convolutional neural network (CNN) pruning has become one of the most successful
network compression approaches in recent years. Existing works on network pruning …

Pruning is a useful technique for decreasing the memory consumption and floating point
operations (FLOPs) of deep convolutional neural network (CNN) models. Nevertheless, at …

Distributed machine learning on edges is widely used in intelligent transportation, smart
home, industrial manufacturing, and underground pipe network monitoring to achieve low …

The prevalence of deep learning has resulted in the widespread deployment of deep neural
networks. However, due to the explosive growth in data volume and advancements in …

Deep learning has been proved to be one of the most effective method in feature encoding
for different intelligent applications such as video-based human action recognition …

The natural world often follows a long-tailed data distribution where only a few classes
account for most of the examples. This long-tail causes classifiers to overfit to the majority …

This paper investigates compressing a pre-trained deep object detector to a lightweight one
by channel pruning, which has proved effective and flexible in promoting efficiency …

Existing research on making sense of deep neural networks often focuses on neuron-level
interpretation, which may not adequately capture the bigger picture of how concepts are …

As a practical approach for compressing convolutional neural networks (CNNs), network
pruning has been rapidly developed in recent years. The conventional methods prune …

This paper proposes a geometric-based technique for compressing convolutional neural
networks to accelerate computations and improve generalization by eliminating non …