Reversible Architectures for Arbitrarily Deep Residual Neural Networks
Open paper
Benchmark
Model
Rank
Results
image-classification-on-stl-10
Hamiltonian
#39
Percentage correct: 85.5
image-classification-on-stl-10
MidPoint
#40
Percentage correct: 84.6
image-classification-on-stl-10
Leapfrog
#41
Percentage correct: 83.7
Rank counts only results with a code link.