Reception - A Deep Learning Based Hybrid Residual Network
Pranjal Sharma, Ujjwal K. Gupta, Markand P. Oza, Shashikant A. Sharma · 2019
Deep neural networks can be difficult to train and require extensive fine tuning for hyper-parameter optimization. In this paper a generalized deep convolutional hybrid network model is proposed, named Reception that not only can tackle problem of solving optimal kernel size but also have goodness of both ResNet and Inception. The proposed Reception module, compliments the learning of filters having small and large receptive fields. This allows the network to extract the tiniest of details as well as the broadest of shapes. Although this strategy increases the width of the network and the number of parameters, the depth requirement of the network reduces significantly. Moreover, the number of parameters are kept in line using a carefully crafted design. The model when used for classifying ships in satellite images achieves a mean test accuracy of 98.56% with standard deviation of 0.14 in 5-fold cross validation and F1-score of 0.99.