Command Palette
Search for a command to run...
Halbüberwachte Semantische Segmentierung
Semi-Supervised Semantische Segmentierung ist eine Aufgabe im Bereich der Computer Vision, die darauf abzielt, Modelle mit einer kleinen Menge an annotierten Daten und einer großen Menge an unannotierten Daten zu trainieren, um jedes Pixel in einem Bild zu klassifizieren. Diese Methode nutzt unannotierte Daten effektiv, um die Generalisierungsfähigkeit und die Segmentierungsgenauigkeit des Modells zu verbessern, reduziert dabei die Annotationskosten und steigert den Anwendungswert des Modells in realen Szenarien.
Pascal VOC 2012 12.5% labeled
CPS
Cityscapes 12.5% labeled
CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)
Cityscapes 25% labeled
CPS (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)
PASCAL VOC 2012 25% labeled
Dual Teacher
Cityscapes 50% labeled
ClassMix (DeepLab v2 MSCOCO pretrained)
Cityscapes 6.25% labeled
Pascal VOC 2012 6.25% labeled
PASCAL VOC 2012 1464 labels
PASCAL VOC 2012 732 labeled
SemiVL (ViT-B/16)
PASCAL VOC 2012 92 labeled
PASCAL VOC 2012 50%
S4MC
Pascal VOC 2012 5% labeled
ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained)
PASCAL VOC 2012 183 labeled
Cityscapes 100 samples labeled
ClassMix (DeepLab v2 MSCOCO pretrained)
PASCAL VOC 2012 366 labeled
SemiVL (ViT-B/16)
Pascal VOC 2012 2% labeled
ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained)
SemanticKITTI
nuScenes
PLE (Voxel)
COCO 1/128 labeled
COCO 1/256 labeled
COCO 1/64 labeled
ScribbleKITTI
LaserMix (Voxel)
COCO 1/512 labeled
SemiVL
COCO 1/32 labeled
Pascal VOC 2012 1% labeled
ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pre-trained)
ADE20K 1/32 labeled
ADE20K 1/16 labeled
UniMatch V2
Cityscapes 93 labeled
AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)
Cityscapes 5% labeled
Cityscapes 2% labeled
PASCAL Context 12.5% labeled
GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)
Pascal VOC 2012 50% labeled
AllSpark
Stanford 2D-3D
WoodScape
FishSegSSL
PASCAL Context 25% labeled
GuidedMix-Net(DeepLab v2 with ResNet101, ImageNet pretrained)
Cityscapes with extra (no coarse labels)
Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval)
PASCAL VOC 2012 331 labeled
AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)
PASCAL VOC 2012 1000 labels
GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained)
PASCAL VOC 2012 500 labels
GuidedMix-Net(DeepLab v2 with ResNet50, ImageNet pretrained)
2017 Robotic Instrument Segmentation Challenge
MMS (20% Labeled)
Kvasir-Instrument
MMS(20% labeled)
KiTS19
Cityscapes 10% labeled
IM++ (416x208, 2.7m parameters, no pretraining)
SUIM
2D-3D-S
M3L (Linear Fusion B2)