Fast Data Attribution for Text-to-Image Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908651059412992 |
|---|---|
| author | Wang, Sheng-Yu Hertzmann, Aaron Efros, Alexei A Zhang, Richard Zhu, Jun-Yan |
| author_facet | Wang, Sheng-Yu Hertzmann, Aaron Efros, Alexei A Zhang, Richard Zhu, Jun-Yan |
| contents | Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them impractical for real-world applications. We propose a novel approach for scalable and efficient data attribution. Our key idea is to distill a slow, unlearning-based attribution method to a feature embedding space for efficient retrieval of highly influential training images. During deployment, combined with efficient indexing and search methods, our method successfully finds highly influential images without running expensive attribution algorithms. We show extensive results on both medium-scale models trained on MSCOCO and large-scale Stable Diffusion models trained on LAION, demonstrating that our method can achieve better or competitive performance in a few seconds, faster than existing methods by 2,500x - 400,000x. Our work represents a meaningful step towards the large-scale application of data attribution methods on real-world models such as Stable Diffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10721 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast Data Attribution for Text-to-Image Models Wang, Sheng-Yu Hertzmann, Aaron Efros, Alexei A Zhang, Richard Zhu, Jun-Yan Computer Vision and Pattern Recognition Machine Learning Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them impractical for real-world applications. We propose a novel approach for scalable and efficient data attribution. Our key idea is to distill a slow, unlearning-based attribution method to a feature embedding space for efficient retrieval of highly influential training images. During deployment, combined with efficient indexing and search methods, our method successfully finds highly influential images without running expensive attribution algorithms. We show extensive results on both medium-scale models trained on MSCOCO and large-scale Stable Diffusion models trained on LAION, demonstrating that our method can achieve better or competitive performance in a few seconds, faster than existing methods by 2,500x - 400,000x. Our work represents a meaningful step towards the large-scale application of data attribution methods on real-world models such as Stable Diffusion. |
| title | Fast Data Attribution for Text-to-Image Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2511.10721 |