Few Shot Semantic Segmentation On Coco 20I 5

Metriken

FB-IoU

Mean IoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	FB-IoU	Mean IoU	Paper Title	Repository
MIANet (VGG-16)	73.81	51.03	MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation	-
AENet (ResNet-50)	78.5	57.1	Eliminating Feature Ambiguity for Few-Shot Segmentation
HSNet (HM, ResNet-50)	72.2	49.4	HM: Hybrid Masking for Few-Shot Segmentation	-
DACM (ResNet-50)	71.6	48.1	Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
APANet (ResNet-50)	-	43	APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation	-
SCCAN (ResNet-50)	74.2	53.9	Self-Calibrated Cross Attention Network for Few-Shot Segmentation
IMR-HSNet (ResNet-50)	-	44.4	Iterative Few-shot Semantic Segmentation from Image Label Text
DiffewS(SD2.1)	-	60.7	Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
PGMA-Net (ResNet-50)	76.7	57.1	Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond	-
DGPNet (ResNet-50)	-	56.2	Dense Gaussian Processes for Few-Shot Segmentation
RePRI (ResNet-50)	-	41.6	Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
ProtoFormer (ResNet-50)	73.3	53.4	Prototype as Query for Few Shot Semantic Segmentation
FWB (ResNet-101)	-	23.65	Feature Weighting and Boosting for Few-Shot Segmentation
FECANet (ResNet-50)	71.1	47.6	FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
VAT (ResNet-101)	72.4	47.9	Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
APANet (VGG-16)	-	43.2	APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation	-
RePRI (CECE-M,ResNet-50)	-	46.9	Clustered-patch Element Connection for Few-shot Learning	-
SSP (ResNet-101)	-	50.2	Self-Support Few-Shot Semantic Segmentation
CWT (ResNet-50)	-	41.3	Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
MCE (ResNet-50)	-	51.04	Masked Cross-image Encoding for Few-shot Segmentation	-

0 of 81 row(s) selected.