Knowledge graph-based image classification - Archive ouverte HAL Access content directly
Journal Articles Data and Knowledge Engineering Year : 2024

Knowledge graph-based image classification

Abstract

This paper introduces a deep learning method for image classification that leverages knowledge formalised as a graph created from information represented by pairs attribute/value. The proposed method investigates a loss function that adaptively combines the classical cross-entropy commonly used in deep learning with a novel penalty function. The novel loss function is derived from the representation of nodes after embedding the knowledge graph and incorporates the proximity between class and image nodes. Its formulation enables the model to focus on identifying the boundary between the most challenging classes to distinguish. Experimental results on several image databases demonstrate improved performance compared to state-of-the-art methods, including classical deep learning algorithms and recent algorithms that incorporate knowledge represented by a graph.
No file

Dates and versions

hal-04484340 , version 1 (29-02-2024)

Identifiers

Cite

Franck Anaël Mbiaya, Christel Vrain, Frédéric Ros, Thi-Bich-Hanh Dao, Yves Lucas. Knowledge graph-based image classification. Data and Knowledge Engineering, 2024, pp.102285. ⟨10.1016/j.datak.2024.102285⟩. ⟨hal-04484340⟩
13 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More