HyperAI
HyperAI
Startseite
Plattform
Dokumentation
Neuigkeiten
Forschungsarbeiten
Tutorials
Datensätze
Wiki
SOTA
LLM-Modelle
GPU-Rangliste
Veranstaltungen
Suche
Über
Nutzungsbedingungen
Datenschutzrichtlinie
Deutsch
HyperAI
HyperAI
Toggle Sidebar
Seite durchsuchen…
⌘
K
Command Palette
Search for a command to run...
Plattform
Startseite
SOTA
Halbüberwachte Semantische Segmentierung
Semi Supervised Semantic Segmentation On 3
Semi Supervised Semantic Segmentation On 3
Metriken
Validation mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Columns
Modellname
Validation mIoU
Paper Title
SemiVL (ViT-B/16)
76.2
SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (DeepLab v3+ with ResNet-101)
73.0
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
CW-BASS (DeepLab v3+ with ResNet-50)
65.87
CW-BASS: Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation
SemiSegContrast (DeepLab v3+ with ResNet-50 backbone, MSCOCO pretrained)
64.9%
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
SegSDE (MTL decoder with ResNet101, ImageNet pretrained, unlabeled image sequences)
62.09%
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation
ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained)
60.28%
Bootstrapping Semantic Segmentation with Regional Contrast
SemiSegContrast (DeepLab v2 with ResNet-101 backbone, MSCOCO pretrained)
59.4%
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained)
58.70%
The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)
56.9%
GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained)
56.53%
Bootstrapping Semantic Segmentation with Regional Contrast
DMT (DeepLab v2 MSCOCO/ImageNet pre-trained)
54.80%
DMT: Dynamic Mutual Training for Semi-Supervised Learning
ClassMix (DeepLab v2 MSCOCO pretrained)
54.07%
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
CutMix (DeepLab v2, ImageNet pre-trained)
51.2
Semi-supervised semantic segmentation needs strong, varied perturbations
0 of 13 row(s) selected.
Previous
Next
Semi Supervised Semantic Segmentation On 3 | SOTA | HyperAI