Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance


Luc Boudier (École Polytechnique), Loris Manganelli (École Polytechnique), Eleftherios Tsonis (École Polytechnique), Nicolas Dufour (École Polytechnique, École des Ponts), Vicky Kalogeiton (Ecole polytechnique)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Few-shot image classification remains challenging due to the limited availability of labeled examples. Recent approaches have explored generating synthetic training data using text-to-image diffusion models, but often require extensive model fine-tuning or external information sources. We present a novel training-free approach, called DIPSY, that leverages IP-Adapter for image-to-image translation to generate highly discriminative synthetic images using only the available few-shot examples. DIPSY introduces three key innovations: (1) an extended classifier-free guidance scheme that enables independent control over positive and negative image conditioning; (2) a class similarity-based sampling strategy that identifies effective contrastive examples; and (3) a simple yet effective pipeline that requires no model fine-tuning or external captioning and filtering. Experiments across ten benchmark datasets demonstrate that our approach achieves state-of-the-art or comparable performance, while eliminating the need for generative model adaptation or reliance on external tools for caption generation and image filtering. Our results highlight the effectiveness of leveraging dual image prompting with positive-negative guidance for generating class-discriminative features, particularly for fine-grained classification tasks.

Citation

@inproceedings{Boudier_2025_BMVC,
author    = {Luc Boudier and Loris Manganelli and Eleftherios Tsonis and Nicolas Dufour and Vicky Kalogeiton},
title     = {Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_77/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection