LLM-DiffAug: Enhancing few-shot object detection via LLM-Guided diffusion augmentation

Yunqing Jiang

doi:10.1016/j.knosys.2025.114066

LLM-DiffAug: Enhancing few-shot object detection via LLM-Guided diffusion augmentation

2025-07-06

0

PRE

AI

DOI：10.1016/j.knosys.2025.114066

Original

Original request for help

Save

Abstract

En 中文

• LLM-guided Prompt Generation: We propose LLM-guided Diffusion models for Data Augmentation (LLM-DiffAug), which leverages LLM to generate diverse prompts for diffusion model inpainting. • Inpainting Alignment: We adopt inpaint alignment to reduce background influence and provide more precise control over inpainted areas. • Bounding Box Constraint: We implement box constraints on inpainted objects to better align with given bounding boxes. • Performance Achievement: Systematic evaluation shows significant improvements over baselines and state-of-the-art methods.

Keywords:

LLM-guided Diffusion models

Data Augmentation

Inpainting Alignment

Bounding Box Constraint

Prompt Generation

LLM-DiffAug: Enhancing few-shot object detection via LLM-Guided diffusion augmentation

Abstract

Journal

Organization