DeepAI AI Chat
Log In Sign Up

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

by   Mingxing Tan, et al.

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 84.4 top-1 / 97.1 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 magnitude fewer parameters. Source code is at


SplitNet: Divide and Co-training

The width of a neural network matters since increasing the width will ne...

Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP...

EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search

Embedding Convolutional Neural Network (CNN) into edge devices for infer...

EfficientNetV2: Smaller Models and Faster Training

This paper introduces EfficientNetV2, a new family of convolutional netw...

Greedy Network Enlarging

Recent studies on deep convolutional neural networks present a simple pa...

TResNet: High Performance GPU-Dedicated Architecture

Many deep learning models, developed in recent years, reach higher Image...