Convolutional neural networks learns spatial features and are heavily interlinked within kernels. The SE module have broken the traditional route of neural networks passing the entire result to next layer. Instead SE only passes important features to be learned with its squeeze and excitation (SE) module. We propose variations of the SE module which improvises the process of squeeze and excitation and enhances the performance. The proposed squeezing or exciting the layer makes it possible for having a smooth transition of layer weights. These proposed variations also retain the characteristics of SE module. The experimented results are carried out on residual networks and the results are tabulated.

翻译：卷积神经网络学习空间特征，且其内部核之间高度互联。SE模块打破了神经网络传统上将完整结果传递至下一层的路径，而是通过其挤压与激励（SE）模块仅传递重要特征以供学习。我们提出了SE模块的变体，这些变体改进了挤压与激励过程并提升了性能。所提出的对层进行挤压或激励的操作使得层权重的平滑过渡成为可能。这些变体还保留了SE模块的特性。实验结果在残差网络上进行，并已列表呈现。