HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stoimchev, Marjan, Koloski, Boshko, Levatić, Jurica, Kocev, Dragi, Džeroski, Sašo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910050464825344
author Stoimchev, Marjan
Koloski, Boshko
Levatić, Jurica
Kocev, Dragi
Džeroski, Sašo
author_facet Stoimchev, Marjan
Koloski, Boshko
Levatić, Jurica
Kocev, Dragi
Džeroski, Sašo
contents Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchies where instances belong to multiple branches, and they rarely exploit unlabeled data. We introduce HELM (\textit{Hierarchical and Explicit Label Modeling}), a novel framework that overcomes these limitations. HELM: (i) uses hierarchy-specific class tokens within a Vision Transformer to capture nuanced label interactions; (ii) employs graph convolutional networks to explicitly encode the hierarchical structure and generate hierarchy-aware embeddings; and (iii) integrates a self-supervised branch to effectively leverage unlabeled imagery. We perform a comprehensive evaluation on four remote sensing image (RSI) datasets (UCM, AID, DFC-15, MLRSNet). HELM achieves state-of-the-art performance, consistently outperforming strong baselines in both supervised and semi-supervised settings, demonstrating particular strength in low-label scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11783
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
Stoimchev, Marjan
Koloski, Boshko
Levatić, Jurica
Kocev, Dragi
Džeroski, Sašo
Computer Vision and Pattern Recognition
Artificial Intelligence
Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchies where instances belong to multiple branches, and they rarely exploit unlabeled data. We introduce HELM (\textit{Hierarchical and Explicit Label Modeling}), a novel framework that overcomes these limitations. HELM: (i) uses hierarchy-specific class tokens within a Vision Transformer to capture nuanced label interactions; (ii) employs graph convolutional networks to explicitly encode the hierarchical structure and generate hierarchy-aware embeddings; and (iii) integrates a self-supervised branch to effectively leverage unlabeled imagery. We perform a comprehensive evaluation on four remote sensing image (RSI) datasets (UCM, AID, DFC-15, MLRSNet). HELM achieves state-of-the-art performance, consistently outperforming strong baselines in both supervised and semi-supervised settings, demonstrating particular strength in low-label scenarios.
title HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.11783