paper-with-me

Papers

Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation

2026-03-09 · Zekun Li, Yinghuan Shi, Yang Gao, Dong Xu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.08364

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks

2026-05-12 · Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev, Alexander Gorin 외 arxiv

Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a light…

Synthetic Data GenerationData Augmentation

Styleclone: Face Stylization with Diffusion Based Data Augmentation

2025-08-23 · Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma arxiv

We present StyleClone, a method for training image-to-image translation networks to stylize faces in a specific style, even with limited style images. Our approach leverages textual inversion and diffusion-based guided i…

Image-to-Image TranslationData AugmentationImage Generation

D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition

2025-04-08 · Rupayan Mallick, Sibo Dong, Nataniel Ruiz, Sarah Adel Bargal

Applications of diffusion models for visual tasks have been quite noteworthy. This paper targets making classification models more robust to occlusions for the task of object recognition by proposing a pipeline that util…

Image GenerationObjectObject Recognition

Effective Data Augmentation With Diffusion Models

2023-02-07 · Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data…

Data AugmentationDiversityFew-Shot Image Classificationimage-classification+2

Image retrieval outperforms diffusion models on data augmentation

2023-04-20 · Max F. Burg, Florian Wenzel, Dominik Zietlow, Max Horn 외

Many approaches have been proposed to use diffusion models to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large datasets, often with noisy a…

Data AugmentationImage RetrievalOpen-Ended Question AnsweringRetrieval