Localized Squeeze and Excitation Block

In this article a new technique called Localized Squeeze and Excitation (LSE) Block is proposed. Using proposed LSE-block one can extract core features from the images in the early stage, which results in smaller deep neural network with much less number of parameters; results in less computation time. By using our proposed technique one can reduce the size of any large deep neural network model. For experimentation the model named ResNet-50 is selected and it is shown that how ResNet-50 can be converted into a smaller neural network by using our proposed technique with better accuracy and less processing time. This work is evaluated on the Breast Cancer Histopathological Image Dataset, both for binary and multi-class problems.