Visual-language pre-training (VLP) have achieved remarkable success in multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that multi-modal large language models (MLLMs) can enhance visual-language representation learning by improving data quality. Our approach is simple, utilizing MLLMs to extend multiple captions for each image. To prevent the bias that introduced by MLLMs' hallucinations and intrinsic caption styles, we propose a "text shearing" to keep the lengths of extended captions identical to the originals. In image-text retrieval, our method consistently obtains 5.6 ~ 35.0% and 16.8 ~ 46.1% improvement on R@1 under the fine-tuning and zero-shot settings, respectively. Notably, our zero-shot results are comparable to fine-tuning on target datasets, which encourages more exploration on the versatile use of MLLMs.

翻译：视觉-语言预训练（VLP）在多模态任务中取得了显著成功，这主要归功于大规模图像-文本数据集的可用性。在本研究中，我们证明多模态大语言模型（MLLMs）能够通过提升数据质量来增强视觉-语言表示学习。我们的方法简洁明了，利用MLLMs为每张图像扩展多个描述文本。为避免MLLMs的幻觉和固有描述风格引入的偏差，我们提出“文本剪枝”策略，使扩展后的描述文本长度与原始文本保持一致。在图像-文本检索任务中，我们的方法在微调和零样本设置下，R@1指标分别稳定提升5.6%~35.0%和16.8%~46.1%。值得注意的是，我们的零样本结果可与目标数据集上的微调效果相媲美，这鼓励进一步探索MLLMs的多样化应用。