Granular Ball Guided Masking: Structure-aware Data Augmentation

TL;DR

This paper introduces GBGM, a structure-aware data augmentation method guided by Granular Ball Computing, which adaptively masks important regions to improve model robustness across various vision tasks.

Contribution

The paper proposes a novel hierarchical masking strategy that preserves semantic structure, enhancing data augmentation effectiveness for recognition and forensic applications.

Findings

Consistent improvements in image classification accuracy.

Enhanced robustness in masked image reconstruction.

Better detection of image tampering.

Abstract

Deep learning models have achieved remarkable success in computer vision but still rely heavily on large-scale labeled data and tend to overfit when data is limited or distributions shift. Data augmentation -- particularly mask-based information dropping -- can enhance robustness by forcing models to explore complementary cues; however, existing approaches often lack structural awareness and risk discarding essential semantics. We propose Granular Ball Guided Masking (GBGM), a structure-aware augmentation strategy guided by Granular Ball Computing (GBC). GBGM adaptively preserves semantically rich, structurally important regions while suppressing redundant areas through a coarse-to-fine hierarchical masking process, producing augmentations that are both representative and discriminative. Extensive experiments on multiple benchmarks demonstrate consistent improvements not only in image classification and masked image reconstruction, but also in image tampering detection, validating the effectiveness and generalization of GBGM across both recognition and forensic scenarios. Simple and model-agnostic, GBGM integrates seamlessly into CNNs and Vision Transformers, offering a practical paradigm for structure-aware data augmentation.