EUVIMEDEUVIMED entdecken
Crossref

Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification

Abhipsa Basu, Aviral Gupta, Abhijnya Bhat, Venkatesh Babu Radhakrishnan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (45) · 38205-38213

DOI: 10.1609/aaai.v40i45.41159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Abhipsa Basu und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image classification systems often inherit biases from uneven group representation in training data. For example, in face datasets for hair color classification, blond hair may be disproportionately associated with females, reinforcing stereotypes. A recent approach leverages the Stable Diffusion model to generate balanced training data, but these models often struggle to preserve the original data distribution. In this work, we explore multiple diffusion-finetuning techniques, e.g., LoRA and DreamBooth, to generate images that more accurately represent each training group by learning directly from their samples. Additionally, in order to prevent a single DreamBooth model from being overwhelmed by excessive intra-group variations, we explore a technique of clustering images within each group and train a DreamBooth model per cluster. These models are then used to generate group-balanced data for pretraining, followed by fine-tuning on real data. Experiments on multiple benchmarks demonstrate that the studied finetuning approaches outperform vanilla Stable Diffusion on average and achieve results comparable to SOTA debiasing techniques like Group-DRO, while surpassing them as the dataset bias severity increases.

Zitieren

APA

Basu, A., Gupta, A., Bhat, A., & Radhakrishnan, V. B. (2026). Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), 38205-38213. https://doi.org/10.1609/aaai.v40i45.41159

Vancouver

Basu A, Gupta A, Bhat A, Radhakrishnan VB. Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(45):38205-38213. doi:10.1609/aaai.v40i45.41159

BibTeX
@article{Basu2026,
  author = {Basu, Abhipsa and Gupta, Aviral and Bhat, Abhijnya and Radhakrishnan, Venkatesh Babu},
  title = {Harnessing Diffusion-Generated Synthetic Images for Fair Image Classification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {45},
  pages = {38205--38213},
  doi = {10.1609/aaai.v40i45.41159}
}
Kostenlos starten →