HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we …