Saved in:
Bibliographic Details
Main Authors: Li, Zekun, Shi, Yinghuan, Gao, Yang, Xu, Dong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.08364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914379972214784
author Li, Zekun
Shi, Yinghuan
Gao, Yang
Xu, Dong
author_facet Li, Zekun
Shi, Yinghuan
Gao, Yang
Xu, Dong
contents Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significantly in task configurations, model choices, and experimental pipelines, making it difficult to fairly compare methods or assess their effectiveness across different scenarios. Moreover, there remains a lack of systematic understanding of the full DiffDA workflow. In this work, we introduce UniDiffDA, a unified analytical framework that decomposes DiffDA methods into three core components: model fine-tuning, sample generation, and sample utilization. This perspective enables us to identify key differences among existing methods and clarify the overall design space. Building on this framework, we develop a comprehensive and fair evaluation protocol, benchmarking representative DiffDA methods across diverse low-data classification tasks. Extensive experiments reveal the relative strengths and limitations of different DiffDA strategies and offer practical insights into method design and deployment. All methods are re-implemented within a unified codebase, with full release of code and configurations to ensure reproducibility and to facilitate future research.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08364
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
Li, Zekun
Shi, Yinghuan
Gao, Yang
Xu, Dong
Computer Vision and Pattern Recognition
Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significantly in task configurations, model choices, and experimental pipelines, making it difficult to fairly compare methods or assess their effectiveness across different scenarios. Moreover, there remains a lack of systematic understanding of the full DiffDA workflow. In this work, we introduce UniDiffDA, a unified analytical framework that decomposes DiffDA methods into three core components: model fine-tuning, sample generation, and sample utilization. This perspective enables us to identify key differences among existing methods and clarify the overall design space. Building on this framework, we develop a comprehensive and fair evaluation protocol, benchmarking representative DiffDA methods across diverse low-data classification tasks. Extensive experiments reveal the relative strengths and limitations of different DiffDA strategies and offer practical insights into method design and deployment. All methods are re-implemented within a unified codebase, with full release of code and configurations to ensure reproducibility and to facilitate future research.
title Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.08364