你的文本到图像模型对描述噪声是否鲁棒？
Is Your Text-to-Image Model Robust to Caption Noise?
AI总结：
本文通过构建VLM生成描述数据集，实证分析了描述幻觉对文本到图像生成性能的影响，并提出利用VLM置信度分数减轻描述噪声以提升模型鲁棒性的方法。
摘要：
在文本到图像（T2I）生成中，一种普遍的训练技术是利用视觉语言模型（VLMs）进行图像重新描述。尽管已知VLMs存在幻觉现象，会生成偏离视觉现实的描述性内容，但此类描述幻觉对T2I生成性能的影响仍未得到充分探索。通过我们的实证研究，我们首先构建了一个包含VLM生成描述的全面数据集，然后系统分析了描述幻觉如何影响生成结果。我们的发现表明：（1）描述质量的差异在微调过程中持续影响模型输出。（2）VLMs的置信度分数可作为检测和刻画数据分布中噪声相关模式的可靠指标。（3）即使是描述保真度的细微变化也会对所学表示的质量产生显著影响。这些发现共同强调了描述质量对模型性能的深远影响，并凸显了在T2I中需要更复杂的鲁棒训练算法。针对这些观察结果，我们提出了一种利用VLM置信度分数来减轻描述噪声的方法，从而增强T2I模型对描述幻觉的鲁棒性。
英文摘要：
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates from the visual reality, the ramifications of such caption hallucinations on T2I generation performance remain under-explored. Through our empirical investigation, we first establish a comprehensive dataset comprising VLM-generated captions, and then systematically analyze how caption hallucination influences generation outcomes. Our findings reveal that (1) the disparities in caption quality persistently impact model outputs during fine-tuning. (2) VLMs confidence scores serve as reliable indicators for detecting and characterizing noise-related patterns in the data distribution. (3) even subtle variations in caption fidelity have significant effects on the quality of learned representations. These findings collectively emphasize the profound impact of caption quality on model performance and highlight the need for more sophisticated robust training algorithm in T2I. In response to these observations, we propose a approach leveraging VLM confidence score to mitigate caption noise, thereby enhancing the robustness of T2I models against hallucination in caption.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
