English

Data Factory with Minimal Human Effort Using VLMs

Computer Vision and Pattern Recognition 2025-10-08 v1

Abstract

Generating enough and diverse data through augmentation offers an efficient solution to the time-consuming and labour-intensive process of collecting and annotating pixel-wise images. Traditional data augmentation techniques often face challenges in manipulating high-level semantic attributes, such as materials and textures. In contrast, diffusion models offer a robust alternative, by effectively utilizing text-to-image or image-to-image transformation. However, existing diffusion-based methods are either computationally expensive or compromise on performance. To address this issue, we introduce a novel training-free pipeline that integrates pretrained ControlNet and Vision-Language Models (VLMs) to generate synthetic images paired with pixel-level labels. This approach eliminates the need for manual annotations and significantly improves downstream tasks. To improve the fidelity and diversity, we add a Multi-way Prompt Generator, Mask Generator and High-quality Image Selection module. Our results on PASCAL-5i and COCO-20i present promising performance and outperform concurrent work for one-shot semantic segmentation.

Keywords

Cite

@article{arxiv.2510.05722,
  title  = {Data Factory with Minimal Human Effort Using VLMs},
  author = {Jiaojiao Ye and Jiaxing Zhong and Qian Xie and Yuzhou Zhou and Niki Trigoni and Andrew Markham},
  journal= {arXiv preprint arXiv:2510.05722},
  year   = {2025}
}

Comments

Tech report

R2 v1 2026-07-01T06:20:53.983Z