GBRIP: Granular Ball Representation for Imbalanced Partial Label Learning

TL;DR

This paper introduces GBRIP, a novel framework that uses granular ball representations and multi-center loss to improve partial label learning in imbalanced datasets, effectively capturing intra-class feature distributions and refining label disambiguation.

Contribution

GBRIP is the first to integrate granular ball representation with multi-center loss for imbalanced partial label learning, addressing intra-class imbalance and label disambiguation.

Findings

GBRIP outperforms existing methods on benchmark datasets.

The granular ball approach effectively captures intra-class feature distributions.

Multi-center loss improves label disambiguation and class separation.

Abstract

Partial label learning (PLL) is a complicated weakly supervised multi-classification task compounded by class imbalance. Currently, existing methods only rely on inter-class pseudo-labeling from inter-class features, often overlooking the significant impact of the intra-class imbalanced features combined with the inter-class. To address these limitations, we introduce Granular Ball Representation for Imbalanced PLL (GBRIP), a novel framework for imbalanced PLL. GBRIP utilizes coarse-grained granular ball representation and multi-center loss to construct a granular ball-based nfeature space through unsupervised learning, effectively capturing the feature distribution within each class. GBRIP mitigates the impact of confusing features by systematically refining label disambiguation and estimating imbalance distributions. The novel multi-center loss function enhances learning by emphasizing the relationships between samples and their respective centers within the granular balls. Extensive experiments on standard benchmarks demonstrate that GBRIP outperforms existing state-of-the-art methods, offering a robust solution to the challenges of imbalanced PLL.