Papers › Data Extrapolation for Text-to-image Generation on Small Datasets
Data Extrapolation for Text-to-image Generation on Small Datasets
Senmao Ye, Fei Liu
Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce new information and yield only marginal improvements. In this paper, we propose a new data augmentation method for text-to-image generation using linear extrapolation. Specifically, we apply linear extrapolation only on text feature, and new image data are retrieved from the internet by search engines. For the reliability of new text-image pairs, we design two outlier detectors to purify retrieved images. Based on extrapolation, we construct training samples dozens of times larger than the original dataset, resulting in a significant improvement in text-to-image performance. Moreover, we propose a NULL-guidance to refine score estimation, and apply recurrent affine transformation to fuse text information. Our model achieves FID scores of 7.91, 9.52 and 5.00 on the CUB, Oxford and COCO datasets. The code and data will be available on GitHub (https://github.com/senmaoy/RAT-Diffusion).
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text-to-Image Generation | COCO (Common Objects in Context) | RAT-Diffusion | FID | 5.00 | #1 of 69 | Archive leaderboard | report |
| Text-to-Image Generation | CUB | RAT-Diffusion | FID | 6.36 | #1 of 20 | Archive leaderboard | report |
| Text-to-Image Generation | CUB | RAT-Diffusion | Inception score | 6.56 | #1 of 20 | Archive leaderboard | report |
| Text-to-Image Generation | Oxford 102 Flowers | RAT-Diffusion | FID | 9.52 | #1 of 8 | Archive leaderboard | report |
| Text-to-Image Generation | Oxford 102 Flowers | RAT-Diffusion | Inception score | 4.35 | #1 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections