HyperAI초신경

Semi Supervised Semantic Segmentation On 6

평가 지표

Validation mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained)	72.14%	Bootstrapping Semantic Segmentation with Regional Contrast
SemiSegContrast (DeepLab v2 with ResNet-101 backbone, MSCOCO pretrained)	67.9%	Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained)	67.21%	The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
DMT (DeepLab v2 MSCOCO pre-trained)	67.15%	DMT: Dynamic Mutual Training for Semi-Supervised Learning
CutMix (DeepLab v3+ ImageNet pre-trained)	67.05%	Semi-supervised semantic segmentation needs strong, varied perturbations
ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained)	66.41%	Bootstrapping Semantic Segmentation with Regional Contrast
ClassMix (DeepLab v2 MSCOCO pretrained)	66.15%	ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
CutMix (DeepLab v2 ImageNet pre-trained)	64.81%	Semi-supervised semantic segmentation needs strong, varied perturbations
s4GAN + MLMT (DeepLab v2 MSCOCO/ImageNet pre-trained)	63.3%	Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
s4GAN+MLMT (DeepLab v3+ ImageNet pre-trained)	62.6%	Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)	60.4%	Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Adversarial (DeepLab v2 ImageNet pre-trained)	49.2%	Adversarial Learning for Semi-Supervised Semantic Segmentation

0 of 12 row(s) selected.