Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910664759443456 |
|---|---|
| author | Hamza, Ali Lojo, Aizea Núñez-Marcos, Adrian Atutxa, Aitziber |
| author_facet | Hamza, Ali Lojo, Aizea Núñez-Marcos, Adrian Atutxa, Aitziber |
| contents | This paper introduces Ali-AUG, a novel single-step diffusion model for efficient labeled data augmentation in industrial applications. Our method addresses the challenge of limited labeled data by generating synthetic, labeled images with precise feature insertion. Ali-AUG utilizes a stable diffusion architecture enhanced with skip connections and LoRA modules to efficiently integrate masks and images, ensuring accurate feature placement without affecting unrelated image content. Experimental validation across various industrial datasets demonstrates Ali-AUG's superiority in generating high-quality, defect-enhanced images while maintaining rapid single-step inference. By offering precise control over feature insertion and minimizing required training steps, our technique significantly enhances data augmentation capabilities, providing a powerful tool for improving the performance of deep learning models in scenarios with limited labeled data. Ali-AUG is especially useful for use cases like defective product image generation to train AI-based models to improve their ability to detect defects in manufacturing processes. Using different data preparation strategies, including Classification Accuracy Score (CAS) and Naive Augmentation Score (NAS), we show that Ali-AUG improves model performance by 31% compared to other augmentation methods and by 45% compared to models without data augmentation. Notably, Ali-AUG reduces training time by 32% and supports both paired and unpaired datasets, enhancing flexibility in data preparation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18678 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model Hamza, Ali Lojo, Aizea Núñez-Marcos, Adrian Atutxa, Aitziber Computer Vision and Pattern Recognition Artificial Intelligence This paper introduces Ali-AUG, a novel single-step diffusion model for efficient labeled data augmentation in industrial applications. Our method addresses the challenge of limited labeled data by generating synthetic, labeled images with precise feature insertion. Ali-AUG utilizes a stable diffusion architecture enhanced with skip connections and LoRA modules to efficiently integrate masks and images, ensuring accurate feature placement without affecting unrelated image content. Experimental validation across various industrial datasets demonstrates Ali-AUG's superiority in generating high-quality, defect-enhanced images while maintaining rapid single-step inference. By offering precise control over feature insertion and minimizing required training steps, our technique significantly enhances data augmentation capabilities, providing a powerful tool for improving the performance of deep learning models in scenarios with limited labeled data. Ali-AUG is especially useful for use cases like defective product image generation to train AI-based models to improve their ability to detect defects in manufacturing processes. Using different data preparation strategies, including Classification Accuracy Score (CAS) and Naive Augmentation Score (NAS), we show that Ali-AUG improves model performance by 31% compared to other augmentation methods and by 45% compared to models without data augmentation. Notably, Ali-AUG reduces training time by 32% and supports both paired and unpaired datasets, enhancing flexibility in data preparation. |
| title | Ali-AUG: Innovative Approaches to Labeled Data Augmentation using One-Step Diffusion Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.18678 |