TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Fine-Grained Image Classification	Birdsnap	EfficientNet-B7	Accuracy	84.3%	# 2
Image Classification	CIFAR-10	EfficientNet-B7	Percentage correct	98.9	# 9
Image Classification	CIFAR-10	EfficientNet-B7	PARAMS	64M	# 13
Image Classification	CIFAR-100	EfficientNet-B7	Percentage correct	91.7	# 5
Image Classification	CIFAR-100	EfficientNet-B7	PARAMS	64M	# 10
Fine-Grained Image Classification	FGVC Aircraft	EfficientNet-B7	Accuracy	92.9%	# 12
Image Classification	Flowers-102	EfficientNet-B7	Accuracy	98.8%	# 6
Fine-Grained Image Classification	Food-101	EfficientNet-B7	Accuracy	93.0	# 4
Image Classification	ImageNet	EfficientNet-B7	Top 1 Accuracy	84.4%	# 32
Image Classification	ImageNet	EfficientNet-B7	Top 5 Accuracy	97.1%	# 17
Image Classification	ImageNet	EfficientNet-B7	Number of params	66M	# 37
Image Classification	ImageNet	EfficientNet-B5	Top 1 Accuracy	83.3%	# 44
Image Classification	ImageNet	EfficientNet-B5	Top 5 Accuracy	96.7%	# 21
Image Classification	ImageNet	EfficientNet-B5	Number of params	30M	# 59
Image Classification	ImageNet	EfficientNet-B2	Top 1 Accuracy	79.8%	# 92
Image Classification	ImageNet	EfficientNet-B2	Top 5 Accuracy	94.9%	# 49
Image Classification	ImageNet	EfficientNet-B2	Number of params	9.2M	# 80
Image Classification	ImageNet	EfficientNet-B3	Top 1 Accuracy	81.1%	# 72
Image Classification	ImageNet	EfficientNet-B3	Top 5 Accuracy	95.5%	# 40
Image Classification	ImageNet	EfficientNet-B3	Number of params	12M	# 76
Image Classification	ImageNet	EfficientNet-B1	Top 1 Accuracy	78.8%	# 106
Image Classification	ImageNet	EfficientNet-B1	Top 5 Accuracy	94.4%	# 66
Image Classification	ImageNet	EfficientNet-B1	Number of params	7.8M	# 83
Image Classification	ImageNet	EfficientNet-B0	Top 1 Accuracy	76.3%	# 142
Image Classification	ImageNet	EfficientNet-B0	Top 5 Accuracy	93.2%	# 85
Image Classification	ImageNet	EfficientNet-B0	Number of params	5.3M	# 94
Image Classification	ImageNet	EfficientNet-B6	Top 1 Accuracy	84%	# 36
Image Classification	ImageNet	EfficientNet-B6	Top 5 Accuracy	96.9%	# 19
Image Classification	ImageNet	EfficientNet-B6	Number of params	43M	# 48
Image Classification	ImageNet	EfficientNet-B4	Top 1 Accuracy	82.6%	# 52
Image Classification	ImageNet	EfficientNet-B4	Top 5 Accuracy	96.3%	# 26
Image Classification	ImageNet	EfficientNet-B4	Number of params	19M	# 73
Fine-Grained Image Classification	Oxford-IIIT Pets	EfficientNet-B7	Accuracy	95.4%	# 6
Fine-Grained Image Classification	Stanford Cars	EfficientNet-B7	Accuracy	94.7%	# 11

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-birdsnap)](https://paperswithcode.com/sota/fine-grained-image-classification-on-birdsnap?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-food-101)](https://paperswithcode.com/sota/fine-grained-image-classification-on-food-101?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-cifar-100)](https://paperswithcode.com/sota/image-classification-on-cifar-100?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-flowers-102)](https://paperswithcode.com/sota/image-classification-on-flowers-102?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-oxford-1)](https://paperswithcode.com/sota/fine-grained-image-classification-on-oxford-1?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-cifar-10)](https://paperswithcode.com/sota/image-classification-on-cifar-10?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-stanford)](https://paperswithcode.com/sota/fine-grained-image-classification-on-stanford?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/fine-grained-image-classification-on-fgvc)](https://paperswithcode.com/sota/fine-grained-image-classification-on-fgvc?p=efficientnet-rethinking-model-scaling-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/efficientnet-rethinking-model-scaling-for/image-classification-on-imagenet)](https://paperswithcode.com/sota/image-classification-on-imagenet?p=efficientnet-rethinking-model-scaling-for)`

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

ICML 2019 • Mingxing Tan • Quoc V. Le

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... (read more)

PDF Abstract

Code

Add Remove Mark official

tensorflow/tpu official

4,142

rwightman/pytorch-image-models

7,520

lukemelas/EfficientNet-PyTorch

↳ Quickstart in

Colab

5,490

osmr/imgclsmob

2,035

qubvel/efficientnet

1,718

See all 76 implementations

Tasks

Add Remove

FINE-GRAINED IMAGE CLASSIFICATION

IMAGE CLASSIFICATION

NEURAL ARCHITECTURE SEARCH

TRANSFER LEARNING

Datasets

CIFAR-10

CIFAR-100

Food-101

Birdsnap

Oxford-IIIT Pets

Results from the Paper

Edit

Ranked #2 on Fine-Grained Image Classification on Birdsnap (using extra training data)

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Fine-Grained Image Classification	Birdsnap	EfficientNet-B7	Accuracy	84.3%	# 2	Compare
Image Classification	CIFAR-10	EfficientNet-B7	Percentage correct	98.9	# 9	Compare
Image Classification	CIFAR-10	EfficientNet-B7	PARAMS	64M	# 13	Compare
Image Classification	CIFAR-100	EfficientNet-B7	Percentage correct	91.7	# 5	Compare
Image Classification	CIFAR-100	EfficientNet-B7	PARAMS	64M	# 10	Compare
Fine-Grained Image Classification	FGVC Aircraft	EfficientNet-B7	Accuracy	92.9%	# 12	Compare
Image Classification	Flowers-102	EfficientNet-B7	Accuracy	98.8%	# 6	Compare
Fine-Grained Image Classification	Food-101	EfficientNet-B7	Accuracy	93.0	# 4	Compare
Image Classification	ImageNet	EfficientNet-B7	Top 1 Accuracy	84.4%	# 32	Compare
			Top 5 Accuracy	97.1%	# 17	Compare
			Number of params	66M	# 37	Compare
Image Classification	ImageNet	EfficientNet-B5	Top 1 Accuracy	83.3%	# 44	Compare
			Top 5 Accuracy	96.7%	# 21	Compare
			Number of params	30M	# 59	Compare
Image Classification	ImageNet	EfficientNet-B2	Top 1 Accuracy	79.8%	# 92	Compare
			Top 5 Accuracy	94.9%	# 49	Compare
			Number of params	9.2M	# 80	Compare
Image Classification	ImageNet	EfficientNet-B3	Top 1 Accuracy	81.1%	# 72	Compare
			Top 5 Accuracy	95.5%	# 40	Compare
			Number of params	12M	# 76	Compare
Image Classification	ImageNet	EfficientNet-B1	Top 1 Accuracy	78.8%	# 106	Compare
			Top 5 Accuracy	94.4%	# 66	Compare
			Number of params	7.8M	# 83	Compare
Image Classification	ImageNet	EfficientNet-B0	Top 1 Accuracy	76.3%	# 142	Compare
			Top 5 Accuracy	93.2%	# 85	Compare
			Number of params	5.3M	# 94	Compare
Image Classification	ImageNet	EfficientNet-B6	Top 1 Accuracy	84%	# 36	Compare
			Top 5 Accuracy	96.9%	# 19	Compare
			Number of params	43M	# 48	Compare
Image Classification	ImageNet	EfficientNet-B4	Top 1 Accuracy	82.6%	# 52	Compare
			Top 5 Accuracy	96.3%	# 26	Compare
			Number of params	19M	# 73	Compare
Fine-Grained Image Classification	Oxford-IIIT Pets	EfficientNet-B7	Accuracy	95.4%	# 6	Compare
Fine-Grained Image Classification	Stanford Cars	EfficientNet-B7	Accuracy	94.7%	# 11	Compare

Methods used in the Paper

Add Remove

METHOD	TYPE
Tanh Activation	Activation Functions
Global Average Pooling	Pooling Operations
Bottleneck Residual Block	Skip Connection Blocks
Max Pooling	Pooling Operations
Kaiming Initialization	Initialization
Residual Connection	Skip Connections
Residual Block	Skip Connection Blocks
ResNet	Convolutional Neural Networks
Depthwise Convolution	Convolutions
Pointwise Convolution	Convolutions
Softmax	Output Functions
Depthwise Separable Convolution	Convolutions
ReLU	Activation Functions
Sigmoid Activation	Activation Functions
LSTM	Recurrent Neural Networks
Squeeze-and-Excitation Block	Image Model Blocks
Inverted Residual Block	Skip Connection Blocks
EfficientNet	Image Models
Weight Decay	Regularization
RMSProp	Stochastic Optimization
Batch Normalization	Normalization
Average Pooling	Pooling Operations
Dense Connections	Feedforward Networks
1x1 Convolution	Convolutions
Convolution	Convolutions
Dropout	Regularization
AutoAugment	Image Data Augmentation
Stochastic Depth	Regularization
Swish	Activation Functions

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods used in the Paper Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods used in the Paper

Add Remove