TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Few-Shot Semantic Segmentation	COCO-20i (10-shot)	RPMM	Mean IoU	33.1	# 4
Few-Shot Semantic Segmentation	COCO-20i (1-shot)	RPMM (ResNet-50)	Mean IoU	30.6	# 72
Few-Shot Semantic Segmentation	COCO-20i (5-shot)	RPMM (ResNet-50)	Mean IoU	35.5	# 69
Few-Shot Semantic Segmentation	COCO-20i -> Pascal VOC (1-shot)	RPMM	Mean IoU	49.6	# 11
Few-Shot Semantic Segmentation	COCO-20i -> Pascal VOC (5-shot)	RPMM	Mean IoU	53.8	# 10
Few-Shot Semantic Segmentation	PASCAL-5i (10-Shot)	RPMM	Mean IoU	57.6	# 4
Few-Shot Semantic Segmentation	PASCAL-5i (1-Shot)	RPMM (ResNet-50)	Mean IoU	56.3	# 89
Few-Shot Semantic Segmentation	PASCAL-5i (5-Shot)	RPMM (ResNet-50)	Mean IoU	57.3	# 85

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-coco-20i-10)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i-10?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-pascal-5i)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-pascal-5i?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-coco-20i-2)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i-2?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-coco-20i)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-coco-20i-5)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i-5?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-coco-20i-1)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i-1?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-pascal-5i-5)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-pascal-5i-5?p=prototype-mixture-models-for-few-shot)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/prototype-mixture-models-for-few-shot/few-shot-semantic-segmentation-on-pascal-5i-1)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-pascal-5i-1?p=prototype-mixture-models-for-few-shot)`

Prototype Mixture Models for Few-shot Semantic Segmentation

ECCV 2020 · Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye ·

Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82\% with only a moderate cost for model size and inference speed.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Code

Add Remove Mark official

Yang-Bob/PMMs official

163

Tasks

Add Remove

Few-Shot Semantic Segmentation

Segmentation

Semantic Segmentation

Datasets

PASCAL-5i

Results from the Paper

Edit

Ranked #4 on Few-Shot Semantic Segmentation on PASCAL-5i (10-Shot)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Few-Shot Semantic Segmentation	COCO-20i (10-shot)	RPMM	Mean IoU	33.1	# 4	Compare
Few-Shot Semantic Segmentation	COCO-20i (1-shot)	RPMM (ResNet-50)	Mean IoU	30.6	# 72	Compare
Few-Shot Semantic Segmentation	COCO-20i (5-shot)	RPMM (ResNet-50)	Mean IoU	35.5	# 69	Compare
Few-Shot Semantic Segmentation	COCO-20i -> Pascal VOC (1-shot)	RPMM	Mean IoU	49.6	# 11	Compare
Few-Shot Semantic Segmentation	COCO-20i -> Pascal VOC (5-shot)	RPMM	Mean IoU	53.8	# 10	Compare
Few-Shot Semantic Segmentation	PASCAL-5i (10-Shot)	RPMM	Mean IoU	57.6	# 4	Compare
Few-Shot Semantic Segmentation	PASCAL-5i (1-Shot)	RPMM (ResNet-50)	Mean IoU	56.3	# 89	Compare
Few-Shot Semantic Segmentation	PASCAL-5i (5-Shot)	RPMM (ResNet-50)	Mean IoU	57.3	# 85	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Prototype Mixture Models for Few-shot Semantic Segmentation

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove