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 …

Vision transformers have recently achieved competitive results across various vision tasks
but still suffer from heavy computation costs when processing a large number of tokens …

Most neural network pruning methods, such as filter-level and layer-level prunings, prune
the network model along one dimension (depth, width, or resolution) solely to meet a …

Network pruning is one of the chief means for improving the computational efficiency of
Deep Neural Networks (DNNs). Pruning-based methods generally discard network kernels …

Vision-language pre-trained models have achieved impressive performance on various
downstream tasks. However their large model sizes hinder their utilization on platforms with …

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

Deep learning has shown significant successes in person reidentification (re-id) tasks.
However, most existing works focus on discriminative feature learning and impose complex …

Densely structured pruning methods utilizing simple pruning heuristics can deliver
immediate compression and acceleration benefits with acceptable benign performances …

Structured pruning methods which are capable of delivering a densely pruned network are
among the most popular techniques in the realm of neural network pruning, where most …

As deep CNNs get larger, it becomes more challenging to deploy them on resource-
restricted mobile devices. Filter-level pruning is one of the most popular methods to …