HyperAIHyperAI

Command Palette

Search for a command to run...

Plateforme

Few Shot Semantic Segmentation On Pascal 5I 1

Métriques

Mean IoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper Title
SegGPT (ViT)83.2SegGPT: Segmenting Everything In Context
PGMA-Net (ResNet-101)77.6Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
PGMA-Net (ResNet-50)74.1Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
PGMA-Net (ViT-B/16)74.1Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
GF-SAM72.1Bridge the Points: Graph-based Few-shot Segment Anything Semantically
HMNet (ResNet-50)70.4Hybrid Mamba for Few-Shot Segmentation
AENet (ResNet-50)70.3Eliminating Feature Ambiguity for Few-Shot Segmentation
HDMNet (DifFSS, ResNet-50)70.2DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
VAT + MSI (ResNet-101)70.1MSI: Maximize Support-Set Information for Few-Shot Segmentation
HDMNet (ResNet-50)69.4Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
DCAMA (Swin-B)69.3Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
BAM (DifFSS, ResNet-50)69.3DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
MSANet (ResNet-101)69.13MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
DACM (VAT, ResNet-101)69.1Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
BAM (SVF, ResNet-50)68.95Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
FPTrans (DeiT-B/16)68.8Feature-Proxy Transformer for Few-Shot Segmentation
MIANet (ResNet-50)68.72MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation
MSANet (ResNet-50)68.52MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
SCCAN (ResNet-101)68.3Self-Calibrated Cross Attention Network for Few-Shot Segmentation
PFENet (SVF, ResNet-50)68.15Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
0 of 105 row(s) selected.
Few Shot Semantic Segmentation On Pascal 5I 1 | SOTA | HyperAI