The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

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

Structural pruning enables model acceleration by removing structurally-grouped parameters
from neural networks. However, the parameter-grouping patterns vary widely across …

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

Large-kernel convolutional neural networks (ConvNets) have recently received extensive
research attention but two unresolved and critical issues demand further investigation. 1) …

Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of
neural networks. There has been a flurry of algorithms that try to solve this practical problem …

Structured pruning is a commonly used technique in deploying deep neural networks
(DNNs) onto resource-constrained devices. However, the existing pruning methods are …

Channel pruning has been broadly recognized as an effective technique to reduce the
computation and memory cost of deep convolutional neural networks. However …

Compared to convolutional layers, fully-connected (FC) layers are better at modeling the
long-range dependencies but worse at capturing the local patterns, hence usually less …

Structural re-parameterization has drawn increasing attention in various computer vision
tasks. It aims at improving the performance of deep models without introducing any …