MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification

07/02/2021
by   Xiaoni Li, et al.
0

Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes. As the label structure decides its performance, many existing approaches attempt to construct an excellent label structure for promoting the classification results. In this paper, we consider that different label structures provide a variety of prior knowledge for category recognition, thus fusing them is helpful to achieve better hierarchical classification results. Furthermore, we propose a multi-task multi-structure fusion model to integrate different label structures. It contains two kinds of branches: one is the traditional classification branch to classify the common subclasses, the other is responsible for identifying the heterogeneous superclasses defined by different label structures. Besides the effect of multiple label structures, we also explore the architecture of the deep model for better hierachical classification and adjust the hierarchical evaluation metrics for multiple label structures. Experimental results on CIFAR100 and Car196 show that our method obtains significantly better results than using a flat classifier or a hierarchical classifier with any single label structure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/15/2017

Joint Hierarchical Category Structure Learning and Large-Scale Image Classification

We investigate the scalable image classification problem with a large nu...
research
09/13/2022

A Capsule Network for Hierarchical Multi-Label Image Classification

Image classification is one of the most important areas in computer visi...
research
10/05/2021

Bottom-up Hierarchical Classification Using Confusion-based Logit Compression

In this work, we propose a method to efficiently compute label posterior...
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
01/13/2021

Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification

We consider the problem of multi-label classification where the labels l...
research
05/09/2015

Probabilistic Cascading for Large Scale Hierarchical Classification

Hierarchies are frequently used for the organization of objects. Given a...
research
04/12/2021

HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization

The current state-of-the-art model HiAGM for hierarchical text classific...

Please sign up or login with your details

Forgot password? Click here to reset