swMATH ID: 39587
Software Authors: Mingxing Tan, Quoc V. Le
Description: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3
Homepage: https://arxiv.org/abs/1905.11946
Source Code:  https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
Related Software: ImageNet; PyTorch; CIFAR; Adam; GitHub; TensorFlow; AlexNet; BERT; MobileNetV2; ShuffleNet; Xception; MNIST; Keras; XNOR-Net; Inception-v4; StarGAN; SqueezeNet; SSD; darch; Python
Cited in: 18 Publications

Citations by Year