arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.19101cs.CVcs.AI
收藏

AAPMT:通过提示与度量Transformer进行AGI评估

AAPMT: AGI Assessment Through Prompt and Metric Transformer

Shanghai Jiao Tong University(上海交通大学)

Benhao Huang

AI总结:

本文提出AAPMT方法,通过提示设计与Metric Transformer建模AGI质量指标间复杂关系,以更贴近人类感知的方式评估文本到图像模型的感知质量、真实性及图文对应性。

摘要:

文本到图像模型的出现标志着AI生成图像(AGIs)演进中的一个重要里程碑,扩展了它们在设计、娱乐等多个领域的应用。尽管取得了这些突破,AGIs的质量往往仍不理想,这凸显了对有效评估方法的需求。这些方法对于评估图像相对于其文本描述的质量至关重要,并且必须准确反映人类感知。该领域已取得实质性进展,BLIP和DBCNN等创新技术做出了显著贡献。然而,近期研究(包括AGIQA-3K)揭示了当前方法与最先进(SOTA)标准之间的显著差距。这一差距强调了需要更精密、更精确的评估指标。为此,我们的目标是开发一个能够为指标打分的模型,重点关注感知质量、真实性以及文本与图像之间的对应关系等参数,从而更紧密地对齐人类感知。在本文中,我们介绍了一系列有效方法,包括提示设计和Metric Transformer。Metric Transformer是一种受各种AGI质量指标之间复杂相互关系启发的新型结构。代码可在https://github.com/huskydoge/CS3324-Digital-Image-Processing/tree/main/Assignment1获取。

英文摘要:

The emergence of text-to-image models marks a significant milestone in the evolution of AI-generated images (AGIs), expanding their use in diverse domains like design, entertainment, and more. Despite these breakthroughs, the quality of AGIs often remains suboptimal, highlighting the need for effective evaluation methods. These methods are crucial for assessing the quality of images relative to their textual descriptions, and they must accurately mirror human perception. Substantial progress has been achieved in this domain, with innovative techniques such as BLIP and DBCNN contributing significantly. However, recent studies, including AGIQA-3K, reveal a notable discrepancy between current methods and state-of-the-art (SOTA) standards. This gap emphasizes the necessity for a more sophisticated and precise evaluation metric. In response, our objective is to develop a model that could give ratings for metrics, which focuses on parameters like perceptual quality, authenticity, and the correspondence between text and image, that more closely aligns with human perception. In our paper, we introduce a range of effective methods, including prompt designs and the Metric Transformer. The Metric Transformer is a novel structure inspired by the complex interrelationships among various AGI quality metrics. The code is available at https://github.com/huskydoge/CS3324-Digital-Image-Processing/tree/main/Assignment1

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。

↑