Medical Image Segmentation On Kvasir Seg

Métriques

Average MAE

mean Dice

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Average MAE	mean Dice	Paper Title	Repository
FANet	0.8153	0.8803	FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation
ResUNet++ + TTA + CRF	-	0.8508	A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation
RUPNet	-	0.7658	RUPNet: Residual upsampling network for real-time polyp segmentation	-
TGA-Net	-	0.8982	TGANet: Text-guided attention for improved polyp segmentation
ESFPNet-L	-	0.931	ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video
TransNetR	-	0.8706	TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing
ColonSegNet	-	0.8206	Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
COMMA (ResNet-50)	0.024	0.904	COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation	-
EffiSegNet-B4	-	0.9483	EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder	-
HarDNet-DFUS	-	0.9363	HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation
DoubleUnet-DCA	-	0.8516	Dual Cross-Attention for Medical Image Segmentation
MEGANet(ResNet-34)	0.026	0.911	MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation
HarDNet-MSEG	0.025	0.912	HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS
UACANet-S	0.026	0.905	UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
AG-CUResNeSt	-	0.902	AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation
SEP	-	0.9411	Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation	-
COMMA (Res2Net-50)	0.027	0.901	COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation	-
RAPUNet	-	0.939	MetaFormer and CNN Hybrid Model for Polyp Image Segmentation
MSRF-Net	-	0.9217	MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation
EMCAD	-	0.928	EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation

0 of 56 row(s) selected.