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

07/25/2017
by   Nikolaos Passalis, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2019

Learning Filter Basis for Convolutional Neural Network Compression

Convolutional neural networks (CNNs) based solutions have achieved state...
research
03/13/2023

Orthogonal Transform Domain Approaches for the Convolutional Layer

In this paper, we propose a set of transform-based neural network layers...
research
06/17/2016

DecomposeMe: Simplifying ConvNets for End-to-End Learning

Deep learning and convolutional neural networks (ConvNets) have been suc...
research
03/25/2020

What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective

Recent works have demonstrated that global covariance pooling (GCP) has ...
research
08/14/2016

About Pyramid Structure in Convolutional Neural Networks

Deep convolutional neural networks (CNN) brought revolution without any ...
research
02/27/2020

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Pooling operators are key components in most Convolutional Neural Networ...
research
04/18/2012

Convolutional Neural Networks Applied to House Numbers Digit Classification

We classify digits of real-world house numbers using convolutional neura...

Please sign up or login with your details

Forgot password? Click here to reset