Granular Ball Guided Masking: Structure-aware Data Augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Shuyin, Chen, Fan, Dai, Dawei, Yang, Meng, Han, Junwei, Gao, Xinbo, Wang, Guoyin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912824646696960
author Xia, Shuyin
Chen, Fan
Dai, Dawei
Yang, Meng
Han, Junwei
Gao, Xinbo
Wang, Guoyin
author_facet Xia, Shuyin
Chen, Fan
Dai, Dawei
Yang, Meng
Han, Junwei
Gao, Xinbo
Wang, Guoyin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Granular Ball Guided Masking: Structure-aware Data Augmentation
Xia, Shuyin
Chen, Fan
Dai, Dawei
Yang, Meng
Han, Junwei
Gao, Xinbo
Wang, Guoyin
Computer Vision and Pattern Recognition
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.
title Granular Ball Guided Masking: Structure-aware Data Augmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.21011