发表机构
South China Normal University; Hong Kong University of Science and Technology (Guangzhou)（华南师范大学; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对AI生成图像质量评估中感知保真度与提示对齐度的交互问题，提出含对抗与协同推理通路的交互感知框架，在基准测试中达最优准确率且具可解释性。
AI 中文摘要
AI生成图像质量评估（AIGIQA）需要联合推理感知保真度与提示对齐度这两个质量维度，现有AIGIQA模型常将二者视为独立变量。但通过重新审视人类评分，我们发现了一个此前被忽略的现象：在人类评分过程中，这两个维度相互依存，同时呈现竞争与协作的互动关系。这一观察表明，统一模型不应将两个维度合并，也不应严格分离，而应自适应地协调二者的相互作用。受此启发，我们引入了一种感知-对齐关系交互感知学习框架，通过对抗与协同推理通路对该关系进行建模。我们的方法未采用刚性双分支架构，而是使用门控交互模块，根据推断出的两个维度间的关系动态路由特征；任务感知提示进一步调节门控行为，使模型能在需要时在竞争与协作间切换。在多个AIGIQA基准上的实验表明，我们的方法不仅达到了当前最优的准确率，还能生成可解释的交互模式，更忠实地模拟了人类的判断。代码可在该https URL获取。
英文摘要
AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity and prompt alignment, two quality dimensions that are often treated as independent in existing AIGIQA models. However, by re-examining human ratings, we uncover a previously overlooked phenomenon: the two dimensions are interdependent and exhibit both competitive and cooperative interactions during human rating. This observation suggests that a unified model should neither collapse the two dimensions nor rigidly separate them, but rather adaptively negotiate their interplay. Motivated by this insight, we introduce an interaction-aware learning framework that models perception-alignment relations through adversarial and collaborative inference pathways. Instead of designing a rigid dual-branch architecture, our method employs a gated interaction module that dynamically routes features according to the inferred relationship between the two dimensions. Task-aware prompts further modulate the gating behaviour, enabling the model to switch between competition and cooperation when necessary. Experiments across multiple AIGIQA benchmarks demonstrate that our approach not only achieves state-of-the-art accuracy but also yields interpretable interaction patterns, offering a more faithful approximation of human judgment. The codes are available at https://github.com/LQAMEI/ACL-IQA.
