GaborNet: Gabor filters with learnable parameters in deep convolutional neural networks
This addresses the problem of training efficiency and performance in image recognition for researchers and practitioners, but it is incremental as it modifies existing architectures with constrained filters.
The paper tackled improving convergence and reducing training complexity in deep convolutional neural networks for image recognition by constraining first-layer filters to learnable Gabor functions, resulting in outperforming common convolutional networks on several datasets.
The article describes a system for image recognition using deep convolutional neural networks. Modified network architecture is proposed that focuses on improving convergence and reducing training complexity. The filters in the first layer of the network are constrained to fit the Gabor function. The parameters of Gabor functions are learnable and are updated by standard backpropagation techniques. The system was implemented on Python, tested on several datasets and outperformed the common convolutional networks.