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

TL;DR

This paper introduces a multi-task multi-structure fusion model for hierarchical image classification, leveraging multiple label structures to improve accuracy over single-structure methods.

Contribution

It proposes a novel fusion approach that combines different label structures and deep architectures for enhanced hierarchical classification performance.

Findings

Outperforms flat and single-structure hierarchical classifiers on CIFAR100 and Car196.

Effectively integrates multiple label structures for better category recognition.

Improves hierarchical classification accuracy significantly.

Abstract

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.