Abstract Convolutional Neural Networks (ConvNets) are commonly developed at a fixed
resource budget, and then scaled up for better accuracy if more resources are given. In this …

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the
most computation cost. To make CNNs more efficient, many methods have been proposed …

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster
training speed and better parameter efficiency than previous models. To develop these …

To attain a favorable performance on large-scale datasets, convolutional neural networks
(CNNs) are usually designed to have very high capacity involving millions of parameters. In …

Many deep learning models, developed in recent years, reach higher ImageNet accuracy
than ResNet50, with fewer or comparable FLOPs count. While FLOPs are often seen as a …

This paper proposes an efficient neural network (NN) architecture design methodology
called Chameleon that honors given resource constraints. Instead of developing new …

The rapid advances in Vision Transformer (ViT) refresh the state-of-the-art performances in
various vision tasks, overshadowing the conventional CNN-based models. This ignites a few …

Although convolutional neural networks (CNNs) are now widely used in various computer
vision applications, its huge resource demanding on parameter storage and computation …

Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but
its kernel size is often overlooked. In this paper, we systematically study the impact of …

Convolutional layers are one of the basic building blocks of modern deep neural networks.
One fundamental assumption is that convolutional kernels should be shared for all …