Table 2 Comparison of classification error between a CNN and the equivalent network using INRF elements instead of linear RF filters.
From: Evidence for the intrinsically nonlinear nature of receptive fields in vision
Dataset | CNN | INRFnet |
|---|---|---|
MNIST | 0.48 | 0.43 |
CIFAR10 | 24.28 | 16.78 |
CIFAR100 | 57.01 | 48.8 |
SVHN | 6.26 | 3.41 |