文本印刷图像：弥合图像-文本模态鸿沟以实现大型视觉语言模型的文本中心训练
Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
提出将文本直接渲染为图像（TPI）来桥接模态鸿沟，为LVLM在仅有文本数据时提供低成本训练方案，可复用于数据稀缺场景下的视觉语言模型微调与数据增强。
原文依据 we propose a Text-Printed Image (TPI), which generates synthetic images by directly rendering the given textual description on a plain white canvas.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的大型视觉语言模型（LVLM）已被应用于多样化的视觉问答（VQA）任务。然而，要实现实用性能通常需要针对特定任务进行微调，并依赖大量图像-文本对，而这些数据收集成本高昂。在本工作中，我们研究文本中心训练，即仅提供文本描述而无需真实图像的设定，作为一种低成本数据扩展的范式。与图像不同，图像的收集常受隐私限制和稀缺领域数据不足的制约，而文本则广泛可得。此外，文本易于编辑，能够借助大语言模型以极少的人工投入实现自动多样化和扩展。尽管在可扩展性和成本方面相比图像收集具有明显优势，但由于图像-文本模态鸿沟，仅用原始文本而无图像进行训练在VQA任务上仍收益有限。为解决该问题，我们提出文本印刷图像（TPI），通过将给定的文本描述直接渲染在纯白画布上生成合成图像。这种简单的渲染将文本投影到图像模态，并能以低成本集成到许多现有的LVLM训练流程中。此外，TPI保留了文本的语义，而文本到图像模型往往无法做到这一点。在四个模型和七个基准上的系统性实验表明，TPI能够实现比扩散模型生成的合成图像更有效的文本中心训练。我们进一步探索TPI作为一种低成本数据增强策略，并展示其实际效用。总体而言，我们的发现凸显了文本中心训练的巨大潜力，并更广泛地描绘了通往LVLM全自动数据生成的道路。
英文原文摘要 1729 字符
Recent large vision-language models (LVLMs) have been applied to diverse VQA tasks. However, achieving practical performance typically requires task-specific fine-tuning with large numbers of image-text pairs, which are costly to collect. In this work, we study text-centric training, a setting where only textual descriptions are available and no real images are provided, as a paradigm for low-cost data scaling. Unlike images, whose collection is often restricted by privacy constraints and scarcity in niche domains, text is widely available. Moreover, text is easily editable, enabling automatic diversification and expansion with LLMs at minimal human effort. While this offers clear advantages over image collection in terms of scalability and cost, training on raw text without images still yields limited gains on VQA tasks because of the image-text modality gap. To address this issue, we propose a Text-Printed Image (TPI), which generates synthetic images by directly rendering the given textual description on a plain white canvas. This simple rendering projects text into the image modality and can be integrated into many existing LVLM training pipelines at low cost. Moreover, TPI preserves the semantics of the text, whereas text-to-image models often fail to do. Across four models and seven benchmarks, our systematic experiments show that TPI enables more effective text-centric training than synthetic images generated by a diffusion model. We further explore TPI as a low-cost data-augmentation strategy and demonstrate its practical utility. Overall, our findings highlight the significant potential of text-centric training and, more broadly, chart a path toward fully automated data generation for LVLMs.