TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Object Detection	COCO minival	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	box AP	57.0	# 1
Instance Segmentation	COCO minival	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	mask AP	48.9	# 1
Object Detection	COCO test-dev	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	box AP	57.3	# 1
Instance Segmentation	COCO test-dev	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	mask AP	49.1	# 1
Instance Segmentation	LVIS v1.0	Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	mask AP	38.1	# 1
Object Detection	LVIS v1.0	Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	box AP	41.6	# 1
Object Detection	PASCAL VOC 2007	Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale)	MAP	89.1%	# 1
Semantic Segmentation	PASCAL VOC 2012 val	Eff-B7 NAS-FPN (Copy-Paste pre-training, single-scale))	mIoU	86.6%	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/object-detection-on-coco-minival)](https://paperswithcode.com/sota/object-detection-on-coco-minival?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/instance-segmentation-on-coco-minival)](https://paperswithcode.com/sota/instance-segmentation-on-coco-minival?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/object-detection-on-coco)](https://paperswithcode.com/sota/object-detection-on-coco?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/instance-segmentation-on-coco)](https://paperswithcode.com/sota/instance-segmentation-on-coco?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/instance-segmentation-on-lvis-v1-0)](https://paperswithcode.com/sota/instance-segmentation-on-lvis-v1-0?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/object-detection-on-lvis-v1-0)](https://paperswithcode.com/sota/object-detection-on-lvis-v1-0?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/object-detection-on-pascal-voc-2007)](https://paperswithcode.com/sota/object-detection-on-pascal-voc-2007?p=simple-copy-paste-is-a-strong-data)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/simple-copy-paste-is-a-strong-data/semantic-segmentation-on-pascal-voc-2012-val)](https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012-val?p=simple-copy-paste-is-a-strong-data)`

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

13 Dec 2020 • Golnaz Ghiasi • Yin Cui • Aravind Srinivas • Rui Qian • Tsung-Yi Lin • Ekin D. Cubuk • Quoc V. Le • Barret Zoph

Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge... (read more)

PDF Abstract

Results from the Paper

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Object Detection	COCO minival	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	box AP	57.0	# 1	Compare
Instance Segmentation	COCO minival	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	mask AP	48.9	# 1	Compare
Object Detection	COCO test-dev	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	box AP	57.3	# 1	Compare
Instance Segmentation	COCO test-dev	Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)	mask AP	49.1	# 1	Compare
Instance Segmentation	LVIS v1.0	Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	mask AP	38.1	# 1	Compare
Object Detection	LVIS v1.0	Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	box AP	41.6	# 1	Compare
Object Detection	PASCAL VOC 2007	Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale)	MAP	89.1%	# 1	Compare
Semantic Segmentation	PASCAL VOC 2012 val	Eff-B7 NAS-FPN (Copy-Paste pre-training, single-scale))	mIoU	86.6%	# 2	Compare

METHOD	TYPE
Pointwise Convolution	Convolutions
Depthwise Convolution	Convolutions
Depthwise Separable Convolution	Convolutions
Entropy Regularization	Regularization
Sigmoid Activation	Activation Functions
PPO	Policy Gradient Methods
Residual Connection	Skip Connections
Tanh Activation	Activation Functions
LSTM	Recurrent Neural Networks
Stochastic Depth	Regularization
Max Pooling	Pooling Operations
Bottleneck Residual Block	Skip Connection Blocks
Residual Block	Skip Connection Blocks
Kaiming Initialization	Initialization
ResNet	Convolutional Neural Networks
Softmax	Output Functions
Mask R-CNN	Instance Segmentation Models
RoIAlign	RoI Feature Extractors
Cascade Mask R-CNN	Instance Segmentation Models
Neural Architecture Search	Neural Architecture Search
Batch Normalization	Normalization
ReLU	Activation Functions
Global Average Pooling	Pooling Operations
NAS-FPN	Feature Extractors
RMSProp	Stochastic Optimization
Squeeze-and-Excitation Block	Image Model Blocks
Swish	Activation Functions
Dropout	Regularization
Average Pooling	Pooling Operations
Dense Connections	Feedforward Networks
Convolution	Convolutions
1x1 Convolution	Convolutions
Inverted Residual Block	Skip Connection Blocks
EfficientNet	Image Models
Copy-Paste	Image Data Augmentation

METHOD

TYPE

Pointwise Convolution