EfficientNet - AshokBhat/ml GitHub Wiki

Description

  • State of the art CNN introduced by Google in 2019.

Paper

Abstract

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 MobileNet 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]] 84.4% [top-1 / 97.1% top-5 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet.

Our EfficientNets also transfer well and achieve [state-of-the-art]] [[accuracy]] on [CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters

FAQ

  • What are EfficientNets?
  • How does their performance compare against previous CNN?

See also