Network In Network
This addresses the need for better local feature abstraction in convolutional neural networks, offering a novel architecture that improves classification accuracy and interpretability, though it is an incremental advancement over existing methods.
The paper tackled the problem of enhancing model discriminability for local patches in deep networks by proposing Network In Network (NIN), which uses micro neural networks instead of linear filters, and achieved state-of-the-art classification performances on CIFAR-10 and CIFAR-100 datasets.
We propose a novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract the data within the receptive field. We instantiate the micro neural network with a multilayer perceptron, which is a potent function approximator. The feature maps are obtained by sliding the micro networks over the input in a similar manner as CNN; they are then fed into the next layer. Deep NIN can be implemented by stacking mutiple of the above described structure. With enhanced local modeling via the micro network, we are able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers. We demonstrated the state-of-the-art classification performances with NIN on CIFAR-10 and CIFAR-100, and reasonable performances on SVHN and MNIST datasets.