↓Skip to main content
  1. PaperReading/
  2. Survey/

Hierarchical Classificaiton

Survey Hierarchical
Table of Contents

Dataset
#

Image Classification
#

Text Classification
#

Dataset Content
WOS Web of Science (WOS) is a document classification dataset that contains 46,985 documents with 134 categories which include 7 parents categories.
RCV1-v2 The RCV1 dataset is a benchmark dataset on text categorization. It is a collection of newswire articles producd by Reuters in 1996-1997. It contains 804,414 manually labeled newswire documents, and categorized with respect to three controlled vocabularies: industries, topics and regions.
New York Times Annotated Corpus The New York Times Annotated Corpus contains over 1.8 million articles written and published by the New York Times between 1987 and 2007. Over 1.5 million documents have at least one tag. Articles are tagged for persons, places, organizations, titles and topics using a controlled vocabulary that is applied consistently across articles.

Graph Classfication
#

Genome Funciton Classification
#

Dataset
Cellcycle Funcat
Derisi Funcat
Eisen Funcat
Expr Funcat
Gasch1 Funcat
Gasch2 Funcat
Seq Funcat
Spo Funcat
Cellcycle GO
Derisi GO
Eisen GO
Expr GO
Gasch1 GO
Gasch2 GO
Seq GO
Spo GO

Paper
#

Image Classification
#

Large-Scale Object Classification Using Label Relation Graphs ECCV 2014
Learning Structured Inference Neural Networks with Label Relations CVPR 2016
Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification CVPR 2022

Text Classification
#

Graph Classfication
#

Hierarchical Graph Representation Learning with Differentiable Pooling NIPS 2018