Learn Class Hierarchy using Convolutional Neural Networks

05/18/2020
by   Riccardo La Grassa, et al.
0

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.

READ FULL TEXT

page 3

page 4

research
02/17/2018

Bayes-optimal Hierarchical Classification over Asymmetric Tree-Distance Loss

Hierarchical classification is supervised multi-class classification pro...
research
06/05/2020

Hierarchical Class-Based Curriculum Loss

Classification algorithms in machine learning often assume a flat label ...
research
12/02/2021

Computing Class Hierarchies from Classifiers

A class or taxonomic hierarchy is often manually constructed, and part o...
research
05/08/2020

Hierarchical Deep Convolutional Neural Networks for Multi-category Diagnosis of Gastrointestinal Disorders on Histopathological Images

Deep convolutional neural networks (CNNs) have been successful for a wid...
research
05/09/2015

Probabilistic Cascading for Large Scale Hierarchical Classification

Hierarchies are frequently used for the organization of objects. Given a...
research
09/16/2020

TreeGAN: Incorporating Class Hierarchy into Image Generation

Conditional image generation (CIG) is a widely studied problem in comput...
research
06/30/2015

Discovering Characteristic Landmarks on Ancient Coins using Convolutional Networks

In this paper, we propose a novel method to find characteristic landmark...

Please sign up or login with your details

Forgot password? Click here to reset