Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

Today's scene graph generation (SGG) task is still far from practical, mainly due to the
severe training bias, eg, collapsing diverse" human walk on/sit on/lay on beach" into" human …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Filter pruning has been widely used for neural network compression because of its enabled
practical acceleration. To date, most of the existing filter pruning works explore the …

Network compression has been widely studied since it is able to reduce the memory and
computation cost during inference. However, previous methods seldom deal with …

We propose ResRep, a novel method for lossless channel pruning (aka filter pruning), which
slims down a CNN by reducing the width (number of output channels) of convolutional …

Channel pruning is a class of powerful methods for model compression. When pruning a
neural network, it's ideal to obtain a sub-network with higher accuracy. However, a sub …

The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients'
data privacy and security issues. Private inference (PI) techniques using cryptographic …

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been
partly overcome with recent advances in machine learning and hardware design. Presently …