ELIQ：一种无需标签的进化AI生成图像质量评估框架
ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images
AI总结：
ELIQ通过自动构建正负样本对，利用预训练多模态模型提升质量评估，实现无需人工标注的高质量评估，优于现有无标签方法。
摘要：
生成式文本到图像模型以惊人的速度发展，不断推高感知质量上限，使原有标签对新版本不可靠。为此，我们提出ELIQ，一种无需标签的进化AI生成图像质量评估框架。ELIQ专注于视觉质量和提示图像对齐，自动构建正负样本对，涵盖传统失真和AIGC特定失真模式，通过指令微调将预训练多模态模型转化为质量感知批评者，并利用轻量级门控融合和质量查询变压器预测二维质量。在多个基准测试中，ELIQ在无标签方法中表现优异，可从AI生成内容（AIGC）泛化到用户生成内容（UGC）场景，为持续发展的生成模型提供可扩展的无标签质量评估方案。代码将在发表时发布。
英文摘要：
Generative text-to-image models are advancing at an unprecedented pace, continuously shifting the perceptual quality ceiling and rendering previously collected labels unreliable for newer generations. To address this, we present ELIQ, a Label-free Framework for Quality Assessment of Evolving AI-generated Images. Specifically, ELIQ focuses on visual quality and prompt-image alignment, automatically constructs positive and aspect-specific negative pairs to cover both conventional distortions and AIGC-specific distortion modes, enabling transferable supervision without human annotations. Building on these pairs, ELIQ adapts a pre-trained multimodal model into a quality-aware critic via instruction tuning and predicts two-dimensional quality using lightweight gated fusion and a Quality Query Transformer. Experiments across multiple benchmarks demonstrate that ELIQ consistently outperforms existing label-free methods, generalizes from AI-generated content (AIGC) to user-generated content (UGC) scenarios without modification, and paves the way for scalable and label-free quality assessment under continuously evolving generative models. The code will be released upon publication.
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。
