Feature-Space Oversampling for Addressing Class Imbalance in SAR Ship Classification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Awais, Ch Muhammad, Reggiannini, Marco, Moroni, Davide, Karakus, Oktay
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910265375719424
author Awais, Ch Muhammad
Reggiannini, Marco
Moroni, Davide
Karakus, Oktay
author_facet Awais, Ch Muhammad
Reggiannini, Marco
Moroni, Davide
Karakus, Oktay
contents SAR ship classification faces the challenge of long-tailed datasets, which complicates the classification of underrepresented classes. Oversampling methods have proven effective in addressing class imbalance in optical data. In this paper, we evaluated the effect of oversampling in the feature space for SAR ship classification. We propose two novel algorithms inspired by the Major-to-minor (M2m) method M2m$_f$, M2m$_u$. The algorithms are tested on two public datasets, OpenSARShip (6 classes) and FuSARShip (9 classes), using three state-of-the-art models as feature extractors: ViT, VGG16, and ResNet50. Additionally, we also analyzed the impact of oversampling methods on different class sizes. The results demonstrated the effectiveness of our novel methods over the original M2m and baselines, with an average F1-score increase of 8.82% for FuSARShip and 4.44% for OpenSARShip.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06420
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feature-Space Oversampling for Addressing Class Imbalance in SAR Ship Classification
Awais, Ch Muhammad
Reggiannini, Marco
Moroni, Davide
Karakus, Oktay
Computer Vision and Pattern Recognition
SAR ship classification faces the challenge of long-tailed datasets, which complicates the classification of underrepresented classes. Oversampling methods have proven effective in addressing class imbalance in optical data. In this paper, we evaluated the effect of oversampling in the feature space for SAR ship classification. We propose two novel algorithms inspired by the Major-to-minor (M2m) method M2m$_f$, M2m$_u$. The algorithms are tested on two public datasets, OpenSARShip (6 classes) and FuSARShip (9 classes), using three state-of-the-art models as feature extractors: ViT, VGG16, and ResNet50. Additionally, we also analyzed the impact of oversampling methods on different class sizes. The results demonstrated the effectiveness of our novel methods over the original M2m and baselines, with an average F1-score increase of 8.82% for FuSARShip and 4.44% for OpenSARShip.
title Feature-Space Oversampling for Addressing Class Imbalance in SAR Ship Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.06420