Over the past decade, deep-learning-based representations have demonstrated remarkable
performance in academia and industry. The learning capability of convolutional neural …

Over the past few years, larger and deeper neural network models, particularly convolutional
neural networks (CNNs), have consistently advanced state-of-the-art performance across …

We introduce channel permutations as a method to maximize the accuracy of N: M sparse
networks. N: M sparsity requires N out of M consecutive elements to be zero and has been …

Dynamic model pruning is a recent direction that allows for the inference of a different sub-
network for each input sample during deployment. However, current dynamic methods rely …

Traditional channel-wise pruning methods by reducing network channels struggle to
effectively prune efficient CNN models with depth-wise convolutional layers and certain …

The success of CNNs for various vision tasks has been accompanied by a significant
increase in required FLOPs and parameter quantities, which has impeded the deployment of …

In spite of the remarkable performance, deep convolutional neural networks (CNNs) are
typically over-parameterized and computationally expensive. Network pruning has become …

Efficient deep neural network (DNN) models equipped with compact operators (eg,
depthwise convolutions) have shown great potential in reducing DNNs' theoretical …

Federated learning is a private-by-design distributed learning paradigm where clients train
local models on their own data before a central server aggregates their local updates to …

Deep neural networks (DNNs) have demonstrated remarkable success in various fields.
However, the large number of floating-point operations (FLOPs) in DNNs poses challenges …