ReFACT: Updating Text-to-Image Models by Editing the Text Encoder

Dana Arad, Hadas Orgad, Yonatan Belinkov


Abstract
Our world is marked by unprecedented technological, global, and socio-political transformations, posing a significant challenge to textto-image generative models. These models encode factual associations within their parameters that can quickly become outdated, diminishing their utility for end-users. To that end, we introduce ReFACT, a novel approach for editing factual associations in text-to-image models without relaying on explicit input from end-users or costly re-training. ReFACT updates the weights of a specific layer in the text encoder, modifying only a tiny portion of the model’s parameters and leaving the rest of the model unaffected.We empirically evaluate ReFACT on an existing benchmark, alongside a newly curated dataset.Compared to other methods, ReFACT achieves superior performance in both generalization to related concepts and preservation of unrelated concepts.Furthermore, ReFACT maintains image generation quality, making it a practical tool for updating and correcting factual information in text-to-image models.
Anthology ID:
2024.naacl-long.140
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2537–2558
Language:
URL:
https://aclanthology.org/2024.naacl-long.140
DOI:
Bibkey:
Cite (ACL):
Dana Arad, Hadas Orgad, and Yonatan Belinkov. 2024. ReFACT: Updating Text-to-Image Models by Editing the Text Encoder. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2537–2558, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
ReFACT: Updating Text-to-Image Models by Editing the Text Encoder (Arad et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.140.pdf
Copyright:
 2024.naacl-long.140.copyright.pdf