Y Zhang, J Zhang, Q Wang, Z Zhong - arXiv preprint arXiv:2004.10694, 2020 - arxiv.org
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 …
M Tan, Q Le - International conference on machine learning, 2021 - proceedings.mlr.press
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 …
M Tan, QV Le - arXiv preprint arXiv:1907.09595, 2019 - arxiv.org
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 …
B Yang, G Bender, QV Le… - Advances in neural …, 2019 - proceedings.neurips.cc
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 …