Stable Diffusion for Data Augmentation in COCO and Weed Datasets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Deng, Boyang
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916625102405632
author Deng, Boyang
author_facet Deng, Boyang
contents Generative models have increasingly impacted various tasks, from computer vision to interior design and beyond. Stable Diffusion, a powerful diffusion model, enables the creation of high-resolution images with intricate details from text prompts or reference images. An intriguing challenge lies in improving performance for small datasets with image-sparse categories. This study explores the effectiveness of Stable Diffusion by evaluating seven common categories and three widespread weed species. Synthetic images were generated using three Stable Diffusion-based techniques: Image-to-Image Translation, DreamBooth, and ControlNet, each with distinct focuses. Classification and detection tasks were then performed on these synthetic images, and their performance was compared to models trained on original images. Promising results were achieved for certain classes, demonstrating the potential of Stable Diffusion in enhancing image-sparse datasets. This foundational study may accelerate the adaptation of diffusion models across various domains.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03996
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stable Diffusion for Data Augmentation in COCO and Weed Datasets
Deng, Boyang
Computer Vision and Pattern Recognition
Generative models have increasingly impacted various tasks, from computer vision to interior design and beyond. Stable Diffusion, a powerful diffusion model, enables the creation of high-resolution images with intricate details from text prompts or reference images. An intriguing challenge lies in improving performance for small datasets with image-sparse categories. This study explores the effectiveness of Stable Diffusion by evaluating seven common categories and three widespread weed species. Synthetic images were generated using three Stable Diffusion-based techniques: Image-to-Image Translation, DreamBooth, and ControlNet, each with distinct focuses. Classification and detection tasks were then performed on these synthetic images, and their performance was compared to models trained on original images. Promising results were achieved for certain classes, demonstrating the potential of Stable Diffusion in enhancing image-sparse datasets. This foundational study may accelerate the adaptation of diffusion models across various domains.
title Stable Diffusion for Data Augmentation in COCO and Weed Datasets
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.03996