HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
Open paper
Benchmark
Model
Rank
Results
image-classification-on-stl-10
HybridNet
–
Percentage correct: 84.10
image-classification-on-stl-10
ResNet baseline
–
Percentage correct: 82.00
image-classification-on-stl-10
SWWAE
–
Percentage correct: 74.33
Rank counts only results with a code link.