HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Few Shot Semantic Segmentation On Coco 20I 1

Metrics

Mean IoU

Results

Performance results of various models on this benchmark

Paper Title
PGMA-Net (ResNet-101)59.4Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
GF-SAM58.7Bridge the Points: Graph-based Few-shot Segment Anything Semantically
SegGPT (ViT)56.1SegGPT: Segmenting Everything In Context
PGMA-Net (ResNet-50)54.3Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
Matcher(DINOv2)52.7Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
DiffewS (SD2.1)52.2Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
HMNet (ResNet-50)52.1Hybrid Mamba for Few-Shot Segmentation
AENet (ResNet-50)51.3Eliminating Feature Ambiguity for Few-Shot Segmentation
DCAMA (Swin-B)50.9Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
MSANet (ResNet-101)50.45MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
HDMNet (ResNet-50)50Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
VAT + MSI (ResNet-101)49.8MSI: Maximize Support-Set Information for Few-Shot Segmentation
HMNet (VGG-16)49.1Hybrid Mamba for Few-Shot Segmentation
MSDNet (ResNet-101)48.5MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
BAM (SVF, ResNet-50)48.47Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
SCCAN (ResNet-101)48.2Self-Calibrated Cross Attention Network for Few-Shot Segmentation
PFENet (SVF, ResNet-50)48.02Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
MIANet (ResNet-50)47.66MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation
FPTrans (DeiT-B/16)47Feature-Proxy Transformer for Few-Shot Segmentation
ProtoFormer (ResNet-101)47Prototype as Query for Few Shot Semantic Segmentation
0 of 85 row(s) selected.