Semi Supervised Semantic Segmentation On 15

Metriken

Validation mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
S4MC	81.11	Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	80.91%	Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization
U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, CutMix)	80.5%	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	80.29%	Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
n-CPS (ResNet-101)	80.26%	n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation
PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)	79.76%	Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
GuidedMix-Net(DeepLab v2 with ResNet101, input-size: 512x512 with multi-scale and flip, ImageNet pretrained)	78.2%	GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
CPCL (DeepLab v3+ with ResNet-101)	77.67%	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
PCT (DeepLab v3+ with ResNet-50 pretrained on ImageNet-1K)	77.26%	Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation
n-CPS (ResNet-50)	77.07%	n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation
GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)	76.5%	GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
CPCL (DeepLab v3+ with ResNet-50)	75.3%	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval)	74.73%	Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval)	71.69%	Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

0 of 14 row(s) selected.