Learn Class Hierarchy using Convolutional Neural Networks

TL;DR

This paper introduces a novel neural network architecture for hierarchical image classification, combining deep linear layers with cross-entropy and center loss to better capture class hierarchies and improve classification performance.

Contribution

It proposes a flexible architecture that extends existing neural networks to learn hierarchical class relationships and global hierarchy information simultaneously.

Findings

Outperforms traditional flat classifiers in hierarchical image classification tasks.

Effectively captures local and global class hierarchy information.

Reduces hierarchy violations compared to standard methods.

Abstract

A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as problems of hierarchical classification, in which the classes to be predicted are organized in a hierarchy of classes. In this paper, we propose a new architecture for hierarchical classification of images, introducing a stack of deep linear layers with cross-entropy loss functions and center loss combined. The proposed architecture can extend any neural network model and simultaneously optimizes loss functions to discover local hierarchical class relationships and a loss function to discover global information from the whole class hierarchy while penalizing class hierarchy violations. We experimentally show that our hierarchical classifier presents advantages to the traditional classification approaches finding application in computer vision tasks.