Batch-normalized Maxout Network in Network

TL;DR

This paper introduces the Maxout Network In Network (MIN), a deep architecture combining maxout units, batch normalization, dropout, and average pooling to improve discriminability and information abstraction, achieving state-of-the-art results on multiple datasets.

Contribution

The paper proposes a novel MIN architecture that integrates maxout units with batch normalization and average pooling, enhancing model performance and robustness.

Findings

Achieved state-of-the-art accuracy on MNIST, CIFAR-10, and CIFAR-100 datasets.

Demonstrated improved training stability and generalization.

Compared favorably with existing models on SVHN dataset.

Abstract

This paper reports a novel deep architecture referred to as Maxout network In Network (MIN), which can enhance model discriminability and facilitate the process of information abstraction within the receptive field. The proposed network adopts the framework of the recently developed Network In Network structure, which slides a universal approximator, multilayer perceptron (MLP) with rectifier units, to exact features. Instead of MLP, we employ maxout MLP to learn a variety of piecewise linear activation functions and to mediate the problem of vanishing gradients that can occur when using rectifier units. Moreover, batch normalization is applied to reduce the saturation of maxout units by pre-conditioning the model and dropout is applied to prevent overfitting. Finally, average pooling is used in all pooling layers to regularize maxout MLP in order to facilitate information abstraction in every receptive field while tolerating the change of object position. Because average pooling preserves all features in the local patch, the proposed MIN model can enforce the suppression of irrelevant information during training. Our experiments demonstrated the state-of-the-art classification performance when the MIN model was applied to MNIST, CIFAR-10, and CIFAR-100 datasets and comparable performance for SVHN dataset.