在文本到图像生成领域，ImageNet能带我们走多远？

How far can we go with ImageNet for Text-to-Image generation?

February 28, 2025

作者: L. Degeorge, A. Ghosh, N. Dufour, D. Picard, V. Kalogeiton

cs.AI

摘要

近期，文本到图像（T2I）生成模型通过在数十亿规模的数据集上训练，遵循“越大越好”的范式，取得了显著成果，这一范式强调数据量而非质量。我们对此既定范式提出挑战，通过展示对小型、精心策划的数据集进行策略性数据增强，能够媲美甚至超越基于大规模网络爬取数据训练的模型。仅利用经过精心设计的文本与图像增强技术优化的ImageNet数据集，我们在GenEval评估中比SD-XL高出2分，在DPGBench上高出5分，同时仅使用了十分之一的参数和千分之一的训练图像。我们的研究结果表明，策略性数据增强，而非庞大的数据集，可能为T2I生成提供一条更为可持续的发展路径。

English

Recent text-to-image (T2I) generation models have achieved remarkable results by training on billion-scale datasets, following a `bigger is better' paradigm that prioritizes data quantity over quality. We challenge this established paradigm by demonstrating that strategic data augmentation of small, well-curated datasets can match or outperform models trained on massive web-scraped collections. Using only ImageNet enhanced with well-designed text and image augmentations, we achieve a +2 overall score over SD-XL on GenEval and +5 on DPGBench while using just 1/10th the parameters and 1/1000th the training images. Our results suggest that strategic data augmentation, rather than massive datasets, could offer a more sustainable path forward for T2I generation.