Papers
arxiv:2410.01638

Data Extrapolation for Text-to-image Generation on Small Datasets

Published on Oct 2, 2024
Authors:
,

Abstract

Text-to-image generation is enhanced through linear extrapolation of text features and internet-based image retrieval with outlier detection, achieving improved FID scores on standard benchmarks.

AI-generated summary

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).

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2410.01638
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2410.01638 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2410.01638 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.01638 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.