Training a V1 Like Layer Using Gabor Filters in Convolutional Neural Networks

It is suggested from neuroscience that the response of V1 neurons in primate visual streams behaves quite like Gabor filters. As an inspiration from primate neural circuits to artificial neural networks, we propose to replace the first layer as a series of Gabor filters in convolutional neural networks. To enhance the performance of the neural network, we introduce a lateral inhibitory mechanism in Gabor filters, enlightened from the research results of neuroscience. To improve performance, we explore a parameter space and search the best suited parameters using cross validation. Experimental results demonstrate that the accuracy can basically match the results of the original convolutional neural networks. However, the adoption of Gabor filters can greatly reduce the time of training, as well as the memory and storage cost.