HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Few Shot Semantic Segmentation On Fss 1000 1

Metrics

Mean IoU

Results

Performance results of various models on this benchmark

Model Name
Mean IoU
Paper TitleRepository
SSP87.3Self-Support Few-Shot Semantic Segmentation
HSNet (VGG-16)82.3Hypercorrelation Squeeze for Few-Shot Segmentation
GF-SAM88Bridge the Points: Graph-based Few-shot Segment Anything Semantically
DCAMA (ResNet-101)88.3Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
VAT + MSI (ResNet-101)90.6MSI: Maximize Support-Set Information for Few-Shot Segmentation
DCAMA (Swin-B)90.1Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
HSNet (ResNet-101)86.5Hypercorrelation Squeeze for Few-Shot Segmentation
DACM (ResNet-101)90.8Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
HSNet (HM, ResNet-50)87.1HM: Hybrid Masking for Few-Shot Segmentation-
DCAMA (ResNet-50)88.2Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
HSNet (DifFSS, ResNet-50)86.2DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
HSNet (ResNet-50)85.5Hypercorrelation Squeeze for Few-Shot Segmentation
DCAMA (DifFSS, ResNet-50)88.4DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
VAT (HM, ResNet-50)89.4HM: Hybrid Masking for Few-Shot Segmentation-
Annotation-free FSS (Without Annotation,ResNet-50)85Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
SegGPT (ViT)85.6SegGPT: Segmenting Everything In Context
VAT (ResNet-50)90.1Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
VAT (ResNet-101)90.3Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
DACM (ResNet-50)90.7Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
Annotation-free FSS (With Annotation,ResNet-50)85.7Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
0 of 24 row(s) selected.