Papers with Code · CC BY-SA 4.0
Semi-Supervised Semantic Segmentation
Models that are trained with a small number of labeled examples and a large number of unlabeled examples and whose aim is to learn to segment an image (i.e. assign a class to every pixel).
데이터셋
45개Cityscapes 12.5% labeledPascal VOC 2012 12.5% labeledCityscapes 25% labeledPASCAL VOC 2012 25% labeledCityscapes 50% labeledPascal VOC 2012 6.25% labeledCityscapes 6.25% labeledPASCAL VOC 2012 1464 labelsPASCAL VOC 2012 92 labeledPASCAL VOC 2012 183 labeledPASCAL VOC 2012 732 labeledPASCAL VOC 2012 366 labeledPASCAL VOC 2012 50%Pascal VOC 2012 5% labeledCityscapes 100 samples labeledPascal VOC 2012 2% labeledSemanticKITTInuScenesCOCO 1/128 labeledCOCO 1/256 labeledCOCO 1/64 labeledScribbleKITTICOCO 1/512 labeledCOCO 1/32 labeledPascal VOC 2012 1% labeledADE20K 1/16 labeledADE20K 1/32 labeledCityscapes 2% labeledCityscapes 5% labeledCityscapes 93 labeled