Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems
Open paper
Benchmark
Model
Rank
Results
image-classification-on-cifar-100
Wide ResNet+Cutout+no BN scale/offset learning
#121
Percentage correct: 82.95
image-classification-on-cifar-10
Wide ResNet+cutout
#127
Percentage correct: 96.71
Rank counts only results with a code link.