TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Real-Time Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	mIoU	63.1%	# 19
Real-Time Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	Time (ms)	13	# 5
Real-Time Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	Frame (fps)	76.9	# 4
Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	Mean IoU (class)	63.06%	# 64
Semantic Segmentation	PASCAL VOC 2012 test	Deeplab-v2 + Lovász-Softmax	Mean IoU	79.0%	# 29
Semantic Segmentation	PASCAL VOC 2012 test	Deeplab-v2 with Lovasz-Softmax loss	Mean IoU	79.00%	# 29

🦡 Badges

Include the markdown at the top of your GitHub README.md file to showcase the performance of the model.

Badges are live and will be dynamically updated with the latest ranking of this paper.

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/the-lovasz-softmax-loss-a-tractable-surrogate/real-time-semantic-segmentation-on-cityscapes)](https://paperswithcode.com/sota/real-time-semantic-segmentation-on-cityscapes?p=the-lovasz-softmax-loss-a-tractable-surrogate)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/the-lovasz-softmax-loss-a-tractable-surrogate/semantic-segmentation-on-pascal-voc-2012)](https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012?p=the-lovasz-softmax-loss-a-tractable-surrogate)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/the-lovasz-softmax-loss-a-tractable-surrogate/semantic-segmentation-on-cityscapes)](https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes?p=the-lovasz-softmax-loss-a-tractable-surrogate)`

The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks

CVPR 2018 • Maxim Berman • Amal Rannen Triki • Matthew B. Blaschko

The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses. We present a method for direct optimization of the mean intersection-over-union loss in neural networks, in the context of semantic image segmentation, based on the convex Lov\'asz extension of submodular losses... (read more)

PDF Abstract

Code

Add Remove Mark official

bermanmaxim/LovaszSoftmax official

1,143

CoinCheung/pytorch-loss

780

Gjiangtao/A-Deep-Supervised-Edge-Optimization-Algorithm-for-Salt-Body-Segmentation

Tasks

Add Remove

SEMANTIC SEGMENTATION

Datasets

COCO

Cityscapes

Results from the Paper

Add Remove

Ranked #19 on Real-Time Semantic Segmentation on Cityscapes test

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Real-Time Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	mIoU	63.1%	# 19	Compare
			Time (ms)	13	# 5	Compare
			Frame (fps)	76.9	# 4	Compare
Semantic Segmentation	Cityscapes test	ENet + Lovász-Softmax	Mean IoU (class)	63.06%	# 64	Compare
Semantic Segmentation	PASCAL VOC 2012 test	Deeplab-v2 + Lovász-Softmax	Mean IoU	79.0%	# 29	Compare
Semantic Segmentation	PASCAL VOC 2012 test	Deeplab-v2 with Lovasz-Softmax loss	Mean IoU	79.00%	# 29	Compare

Methods used in the Paper

Add Remove

METHOD	TYPE
🤖 No Methods Found	Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet

Edit Social Preview

The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks Edit social preview

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit Add Remove

Methods used in the Paper Edit Add Remove