TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Medical Image Segmentation	2018 Data Science Bowl	Unet++	Dice	0.8974	# 8
Medical Image Segmentation	2018 Data Science Bowl	Unet++	mIoU	0.9255	# 1
Medical Image Segmentation	2018 Data Science Bowl	Unet++	Recall	-	# 5
Medical Image Segmentation	2018 Data Science Bowl	Unet++	Precision	-	# 4
Semantic Segmentation	Cityscapes val	UNet++ (ResNet-101)	mIoU	75.5	# 67
Medical Image Segmentation	CVC-ClinicDB	U-Net++	mean Dice	0.7940	# 42
Medical Image Segmentation	Kvasir-SEG	U-Net++	Average MAE	0.048	# 13
Medical Image Segmentation	Kvasir-SEG	U-Net++	mean Dice	0.8210	# 49
Medical Image Segmentation	Kvasir-SEG	U-Net++	S-Measure	0.862	# 9
Medical Image Segmentation	Kvasir-SEG	U-Net++	max E-Measure	0.910	# 9
Camouflaged Object Segmentation	PCOD_1200	UNet++	S-Measure	0.801	# 16
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	S measure	0.684	# 1
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	mean E-measure	0.687	# 1
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	weighted F-measure	0.491	# 1
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	mean F-measure	0.553	# 1
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	Dice	0.559	# 5
Video Polyp Segmentation	SUN-SEG-Easy (Unseen)	UNet++	Sensitivity	0.457	# 12
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	S-Measure	0.685	# 1
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	mean E-measure	0.697	# 1
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	weighted F-measure	0.480	# 1
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	mean F-measure	0.544	# 1
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	Dice	0.554	# 5
Video Polyp Segmentation	SUN-SEG-Hard (Unseen)	UNet++	Sensitivity	0.467	# 12

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/video-polyp-segmentation-on-sun-seg-easy-1)](https://paperswithcode.com/sota/video-polyp-segmentation-on-sun-seg-easy-1?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/video-polyp-segmentation-on-sun-seg-hard-1)](https://paperswithcode.com/sota/video-polyp-segmentation-on-sun-seg-hard-1?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/medical-image-segmentation-on-2018-data)](https://paperswithcode.com/sota/medical-image-segmentation-on-2018-data?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/video-polyp-segmentation-on-sun-seg-easy)](https://paperswithcode.com/sota/video-polyp-segmentation-on-sun-seg-easy?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/video-polyp-segmentation-on-sun-seg-hard)](https://paperswithcode.com/sota/video-polyp-segmentation-on-sun-seg-hard?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/camouflaged-object-segmentation-on-pcod-1200)](https://paperswithcode.com/sota/camouflaged-object-segmentation-on-pcod-1200?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/medical-image-segmentation-on-cvc-clinicdb)](https://paperswithcode.com/sota/medical-image-segmentation-on-cvc-clinicdb?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/medical-image-segmentation-on-kvasir-seg)](https://paperswithcode.com/sota/medical-image-segmentation-on-kvasir-seg?p=unet-a-nested-u-net-architecture-for-medical)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unet-a-nested-u-net-architecture-for-medical/semantic-segmentation-on-cityscapes-val)](https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes-val?p=unet-a-nested-u-net-architecture-for-medical)`

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

18 Jul 2018 · Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, Jianming Liang ·

Implementation of different kinds of Unet Models for Image Segmentation - Unet , RCNN-Unet, Attention Unet, RCNN-Attention Unet, Nested Unet

PDF Abstract

Code

Add Remove Mark official

MrGiovanni/Nested-UNet official

2,277

qubvel/segmentation_models.pytorch

↳ Quickstart in

Colab

9,510

PaddlePaddle/PaddleSeg

8,417

MrGiovanni/UNetPlusPlus

2,277

bigmb/Unet-Segmentation-Pytorch-Nes…

1,869

See all 33 implementations

Tasks

Add Remove

Camouflaged Object Segmentation

Image Segmentation

Medical Image Segmentation

Segmentation

Semantic Segmentation

Thermal Image Segmentation

Video Polyp Segmentation

Datasets

Introduced in the Paper:

2018 Data Science Bowl

Used in the Paper:

Cityscapes

Kvasir-SEG

Kvasir

CVC-ClinicDB SUN-SEG-Hard (Unseen) SUN-SEG-Easy (Unseen)

Results from the Paper

Edit

Ranked #5 on Video Polyp Segmentation on SUN-SEG-Easy

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Medical Image Segmentation	2018 Data Science Bowl	Unet++	Dice	0.8974	# 8	Compare
			mIoU	0.9255	# 1	Compare
			Recall	-	# 5	Compare
			Precision	-	# 4	Compare
Medical Image Segmentation	CVC-ClinicDB	U-Net++	mean Dice	0.7940	# 42	Compare
Medical Image Segmentation	Kvasir-SEG	U-Net++	Average MAE	0.048	# 13	Compare
			mean Dice	0.8210	# 49	Compare
			S-Measure	0.862	# 9	Compare
			max E-Measure	0.910	# 9	Compare
Camouflaged Object Segmentation	PCOD_1200	UNet++	S-Measure	0.801	# 16	Compare
Video Polyp Segmentation	SUN-SEG-Easy	UNet++	S measure	0.684	# 1	Compare
			mean E-measure	0.687	# 1	Compare
			weighted F-measure	0.491	# 1	Compare
			mean F-measure	0.553	# 1	Compare
			Dice	0.559	# 5	Compare
Video Polyp Segmentation	SUN-SEG-Easy (Unseen)	UNet++	Sensitivity	0.457	# 12	Compare
Video Polyp Segmentation	SUN-SEG-Hard	UNet++	S-Measure	0.685	# 1	Compare
			mean E-measure	0.697	# 1	Compare
			weighted F-measure	0.480	# 1	Compare
			mean F-measure	0.544	# 1	Compare
			Dice	0.554	# 5	Compare
Video Polyp Segmentation	SUN-SEG-Hard (Unseen)	UNet++	Sensitivity	0.467	# 12	Compare

Results from Other Papers

Task	Dataset	Model	Metric Name	Metric Value	Rank	Source Paper	Compare
Semantic Segmentation	Cityscapes val	UNet++ (ResNet-101)	mIoU	75.5	# 67		See all

Methods

Add Remove

1x1 Convolution • Average Pooling • Batch Normalization • Bottleneck Residual Block • Convolution • Global Average Pooling • Kaiming Initialization • Max Pooling • ReLU • Residual Block • Residual Connection • ResNet • UNet++

Edit Social Preview

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit