Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment

2026-08-25

AI Summary

该研究针对AI生成图像质量评估中感知保真度和提示对齐度的相互依赖性问题，提出了一种结合对抗与协作学习路径的交互感知框架来解决。

Abstract

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.

Problem

• AI-Generated Image Quality Assessment
• Perceptual Fidelity
• Prompt Alignment
• Interaction-aware Learning

Innovation

• interaction-aware learning framework
• adversarial and collaborative inference pathways
• gated interaction module
• task-aware prompts