Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

TL;DR

This paper introduces Convolutional BoF (CBoF), a novel, trainable pooling method for CNNs that handles variable image sizes, reduces parameters, and improves classification accuracy using a quantization-based approach inspired by Bag-of-Features.

Contribution

The paper presents a new end-to-end trainable pooling layer, CBoF, that enhances CNN flexibility, efficiency, and accuracy by integrating a quantization-based pooling inspired by Bag-of-Features.

Findings

CBoF reduces network parameters significantly.

CBoF improves classification accuracy over state-of-the-art methods.

CBoF handles images of various sizes natively.

Abstract

Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are becoming increasingly larger, using millions of parameters, while they are restricted to handling images of fixed size. In this paper, a quantization-based approach, inspired from the well-known Bag-of-Features model, is proposed to overcome these limitations. The proposed approach, called Convolutional BoF (CBoF), uses RBF neurons to quantize the information extracted from the convolutional layers and it is able to natively classify images of various sizes as well as to significantly reduce the number of parameters in the network. In contrast to other global pooling operators and CNN compression techniques the proposed method utilizes a trainable pooling layer that it is end-to-end differentiable, allowing the network to be trained using regular back-propagation and to achieve greater distribution shift invariance than competitive methods. The ability of the proposed method to reduce the parameters of the network and increase the classification accuracy over other state-of-the-art techniques is demonstrated using three image datasets.