Few-Shot Learning on COCO-20i (5-shot)

Metric: learnable parameters (million) (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	learnable parameters (million)▼	Augmentations	Paper	Date↕	Code
1	DCAMA (ResNet-101)	47.7	No	Dense Cross-Query-and-Support Attention Weighted...	2022-07-18	Code
2	DCAMA (ResNet-50)	47.7	No	Dense Cross-Query-and-Support Attention Weighted...	2022-07-18	Code
3	FWB (ResNet-101)	43	No	Feature Weighting and Boosting for Few-Shot Segm...	2019-09-28	Code
4	PPNet (ResNet-50)	31.5	No	Part-aware Prototype Network for Few-shot Semant...	2020-07-13	Code
5	BAM (ResNet-50)	26.7	No	Learning What Not to Segment: A New Perspective ...	2022-03-15	Code
6	CyCTR (ResNet-50)	15.4	No	Few-Shot Segmentation via Cycle-Consistent Trans...	2021-06-04	Code
7	PFENet (ResNet-101)	10.3	No	Prior Guided Feature Enrichment Network for Few-...	2020-08-04	Code
8	HSNet (ResNet-101)	2.5	No	Hypercorrelation Squeeze for Few-Shot Segmentation	2021-04-04	Code
9	HSNet (ResNet-50)	2.5	No	Hypercorrelation Squeeze for Few-Shot Segmentation	2021-04-04	Code
10	MSDNet (ResNet-101)	1.5	No	MSDNet: Multi-Scale Decoder for Few-Shot Semanti...	2024-09-17	Code
11	MSDNet (ResNet-50)	1.5	No	MSDNet: Multi-Scale Decoder for Few-Shot Semanti...	2024-09-17	Code

#1DCAMA (ResNet-101)SOTA
47.7
learnable parameters (million)· 2022-07-18
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation Code
#2DCAMA (ResNet-50)
47.7
learnable parameters (million)· 2022-07-18
Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation Code
#3FWB (ResNet-101)SOTA
43
learnable parameters (million)· 2019-09-28
Feature Weighting and Boosting for Few-Shot Segmentation Code
#4PPNet (ResNet-50)
31.5
learnable parameters (million)· 2020-07-13
Part-aware Prototype Network for Few-shot Semantic Segmentation Code
#5BAM (ResNet-50)
26.7
learnable parameters (million)· 2022-03-15
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation Code
#6CyCTR (ResNet-50)
15.4
learnable parameters (million)· 2021-06-04
Few-Shot Segmentation via Cycle-Consistent Transformer Code
#7PFENet (ResNet-101)
10.3
learnable parameters (million)· 2020-08-04
Prior Guided Feature Enrichment Network for Few-Shot Segmentation Code
#8HSNet (ResNet-101)
2.5
learnable parameters (million)· 2021-04-04
Hypercorrelation Squeeze for Few-Shot Segmentation Code
#9HSNet (ResNet-50)
2.5
learnable parameters (million)· 2021-04-04
Hypercorrelation Squeeze for Few-Shot Segmentation Code
#10MSDNet (ResNet-101)
1.5
learnable parameters (million)· 2024-09-17
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping Code
#11MSDNet (ResNet-50)
1.5
learnable parameters (million)· 2024-09-17
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping Code