Network In Network

TL;DR

The paper introduces 'Network In Network' (NIN), a deep learning architecture that replaces traditional convolutional layers with micro neural networks to improve local feature abstraction and overall classification performance.

Contribution

It proposes a novel micro neural network structure within CNNs, enhancing local modeling and enabling effective global average pooling for better interpretability and reduced overfitting.

Findings

Achieved state-of-the-art results on CIFAR-10 and CIFAR-100 datasets.

Demonstrated improved classification accuracy over traditional CNNs.

Showed reasonable performance on SVHN and MNIST datasets.

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.