Few Shot Semantic Segmentation On Pascal 5I 5

المقاييس

Mean IoU

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	Mean IoU	Paper Title	Repository
HDMNet (ResNet-50)	71.8	Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
APANet (VGG-16)	62.6	APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation	-
PFENet (SVF, VGG-16)	69.8	Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
MSHNet	72.3	Multi-similarity based Hyperrelation Network for few-shot segmentation
FECANet (VGG-16)	66.7	FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
ASGNet (ResNet-101)	64.36	Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
PFENet (ResNet-101)	61.4	Prior Guided Feature Enrichment Network for Few-Shot Segmentation
MSDNet (ResNet-50)	68.7	MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
PANet (VGG-16)	55.7	PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment	-
DCAMA (ResNet-50)	68.5	Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
DACM (VAT, ResNet-50)	71.7	Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
SSP (ResNet-101)	73.1	Self-Support Few-Shot Semantic Segmentation
MIANet (ResNet-50)	71.59	MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation	-
SCCAN (ResNet-101)	71.5	Self-Calibrated Cross Attention Network for Few-Shot Segmentation
RePRI (ResNet-50)	66.6	Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
MSANet (ResNet-101)	73.99	MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
MLC (ResNet-50)	66.8	Mining Latent Classes for Few-shot Segmentation
PFENet (SCL, ResNet-50)	62.9	Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
PGNet (ResNet-50)	58.5	Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation	-
MCE (ResNet-50)	70.03	Masked Cross-image Encoding for Few-shot Segmentation	-

0 of 96 row(s) selected.