Label Hierarchy Transition: Modeling Class Hierarchies to Enhance Deep Classifiers

by   Renzhen Wang, et al.
Xi'an Jiaotong University

Hierarchical classification aims to sort the object into a hierarchy of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address hierarchical classification by decoupling it into several multi-class classification tasks. However, such a multi-task learning strategy fails to fully exploit the correlation among various categories across different hierarchies. In this paper, we propose Label Hierarchy Transition, a unified probabilistic framework based on deep learning, to address hierarchical classification. Specifically, we explicitly learn the label hierarchy transition matrices, whose column vectors represent the conditional label distributions of classes between two adjacent hierarchies and could be capable of encoding the correlation embedded in class hierarchies. We further propose a confusion loss, which encourages the classification network to learn the correlation across different label hierarchies during training. The proposed framework can be adapted to any existing deep network with only minor modifications. We experiment with three public benchmark datasets with various class hierarchies, and the results demonstrate the superiority of our approach beyond the prior arts. Source code will be made publicly available.


Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding

Object categories inherently form a hierarchy with different levels of c...

Inducing a hierarchy for multi-class classification problems

In applications where categorical labels follow a natural hierarchy, cla...

Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification

Hierarchical multi-granularity classification (HMC) assigns hierarchical...

SEAL: Simultaneous Label Hierarchy Exploration And Learning

Label hierarchy is an important source of external knowledge that can en...

Set-valued prediction in hierarchical classification with constrained representation complexity

Set-valued prediction is a well-known concept in multi-class classificat...

Hierarchical Classification of Research Fields in the "Web of Science" Using Deep Learning

This paper presents a hierarchical classification system that automatica...

Please sign up or login with your details

Forgot password? Click here to reset