FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Patricio, Alvaro, Dehban, Atabak, Ventura, Rodrigo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918132665286656
author Patricio, Alvaro
Dehban, Atabak
Ventura, Rodrigo
author_facet Patricio, Alvaro
Dehban, Atabak
Ventura, Rodrigo
contents Recent advances in diffusion-based generative models have demonstrated significant potential in augmenting scarce datasets for object detection tasks. Nevertheless, most recent models rely on resource-intensive full fine-tuning of large-scale diffusion models, requiring enterprise-grade GPUs (e.g., NVIDIA V100) and thousands of synthetic images. To address these limitations, we propose Flux LoRA Augmentation (FLORA), a lightweight synthetic data generation pipeline. Our approach uses the Flux 1.1 Dev diffusion model, fine-tuned exclusively through Low-Rank Adaptation (LoRA). This dramatically reduces computational requirements, enabling synthetic dataset generation with a consumer-grade GPU (e.g., NVIDIA RTX 4090). We empirically evaluate our approach on seven diverse object detection datasets. Our results demonstrate that training object detectors with just 500 synthetic images generated by our approach yields superior detection performance compared to models trained on 5000 synthetic images from the ODGEN baseline, achieving improvements of up to 21.3% in mAP@.50:.95. This work demonstrates that it is possible to surpass state-of-the-art performance with far greater efficiency, as FLORA achieves superior results using only 10% of the data and a fraction of the computational cost. This work demonstrates that a quality and efficiency-focused approach is more effective than brute-force generation, making advanced synthetic data creation more practical and accessible for real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21712
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
Patricio, Alvaro
Dehban, Atabak
Ventura, Rodrigo
Computer Vision and Pattern Recognition
Recent advances in diffusion-based generative models have demonstrated significant potential in augmenting scarce datasets for object detection tasks. Nevertheless, most recent models rely on resource-intensive full fine-tuning of large-scale diffusion models, requiring enterprise-grade GPUs (e.g., NVIDIA V100) and thousands of synthetic images. To address these limitations, we propose Flux LoRA Augmentation (FLORA), a lightweight synthetic data generation pipeline. Our approach uses the Flux 1.1 Dev diffusion model, fine-tuned exclusively through Low-Rank Adaptation (LoRA). This dramatically reduces computational requirements, enabling synthetic dataset generation with a consumer-grade GPU (e.g., NVIDIA RTX 4090). We empirically evaluate our approach on seven diverse object detection datasets. Our results demonstrate that training object detectors with just 500 synthetic images generated by our approach yields superior detection performance compared to models trained on 5000 synthetic images from the ODGEN baseline, achieving improvements of up to 21.3% in mAP@.50:.95. This work demonstrates that it is possible to surpass state-of-the-art performance with far greater efficiency, as FLORA achieves superior results using only 10% of the data and a fraction of the computational cost. This work demonstrates that a quality and efficiency-focused approach is more effective than brute-force generation, making advanced synthetic data creation more practical and accessible for real-world scenarios.
title FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.21712