Medical Image Segmentation On Cvc Colondb

평가 지표

mIoU

mean Dice

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	mean Dice	Paper Title	Repository
PVT-GCASCADE	0.7460	0.8261	G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation
TransFuse-L	0.676	0.744	TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
EMCAD	-	0.9231	EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation
UACANet-S	0.704	0.783	UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
DuAT	0.737	0.819	DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation
SAM-EG	0.689	0.774	SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation	-
ProMISe	0.789	0.874	ProMISe: Promptable Medical Image Segmentation using SAM
COMMA (Res2Net-50)	0.689	0.754	COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation	-
KDAS	0.679	0.759	KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation
UACANet-L	0.678	0.751	UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation
RAPUNet	0.9096	0.9526	MetaFormer and CNN Hybrid Model for Polyp Image Segmentation
Meta-Polyp	0.79	0.867	Meta-Polyp: a baseline for efficient Polyp segmentation
PVT-CASCADE	0.7453	0.8254	Medical Image Segmentation via Cascaded Attention Decoding
HarDNet-MSEG	0.660	0.731	HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS
TransFuse-S	0.696	0.773	TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
ResUNet++ + TTA	0.8466	0.8474	A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation
ESFPNet-L	0.730	0.811	ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video
SSFormer-L	0.721	0.802	Stepwise Feature Fusion: Local Guides Global
Polyp-PVT	0.727	0.808	Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers
CaraNet	0.689	0.773	CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects	-

0 of 23 row(s) selected.