Network In Network

TLDR

The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. The authors propose Network In Network (NIN), a deep network that replaces conventional convolutional layers with micro neural networks to enhance discriminability of local patches within the receptive field. NIN replaces each convolutional filter with a multilayer perceptron micro network that slides over the input, producing feature maps that are stacked to form deeper layers. NIN achieves state‑of‑the‑art classification on CIFAR‑10 and CIFAR‑100, with robust performance on SVHN and MNIST, while enabling interpretable global average pooling that reduces overfitting.

Abstract

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.