Gated Convolutional Networks with Hybrid Connectivity for Image Classification

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10HCGNet-A3#66Percentage correct: 97.86
image-classification-on-cifar-10HCGNet-A2#73Percentage correct: 97.71
image-classification-on-cifar-10HCGNet-A1#96Percentage correct: 96.85
image-classification-on-cifar-100HCGNet-A3#77Percentage correct: 84.04PARAMS: 11.4M
image-classification-on-cifar-100HCGNet-A2#83Percentage correct: 83.46PARAMS: 3.1M
image-classification-on-cifar-100HCGNet-A1#108Percentage correct: 81.87PARAMS: 1.1M
image-classification-on-imagenetHCGNet-C#665Top 1 Accuracy: 80.5%Number of params: 42.2MGFLOPs: 7.1
image-classification-on-imagenetHCGNet-B#779Top 1 Accuracy: 78.5%Number of params: 12.9MGFLOPs: 2.0

Rank counts only results with a code link.