Patch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment
About
With the rapid advancement of image generation technologies, perceptual quality assessment of AI-generated images has emerged as a crucial research direction in computer vision. The core challenge of this task lies in achieving efficient quality assessment for massive generated images. Current mainstream approaches exhibit two key limitations: 1) Methods employing complex feature extraction strategies, while improving performance, incur prohibitive computational costs that hinder real-time inference; 2) Simple image scaling-based solutions, despite their computational efficiency, demonstrate significantly inferior assessment accuracy. To address this critical issue, we propose Patch Knowledge Transfer (PKT), a knowledge distillation-based optimization framework that achieves synergistic optimization of visual representation capability and inference efficiency through an innovative multi-level knowledge transfer mechanism. Specifically, we design a dual-model architecture: a teacher model with local-global hybrid processing provides high-quality supervision signals, while a student model relying solely on global processing efficiently inherits the teacher's representation capacity through multi-level supervision. Extensive experiments conducted on 4 AIGIQA databases demonstrate that the PKT framework enables the student model to maintain performance comparable to the teacher while reducing computational costs by 67.7\%. Furthermore, compared to existing methods, our approach achieves a superior balance between model efficiency and assessment accuracy.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Quality Assessment | AGIQA-3K | SRCC0.8908 | 175 | |
| Image Quality Assessment | AGIQA-1K | SRCC0.8837 | 68 | |
| Image Quality Assessment | AGIQA-1K (random seed 2) | SRCC0.889 | 9 | |
| Image Quality Assessment | AGIQA-3K random seed 2 | SRCC0.8765 | 9 | |
| Image Quality Assessment | AIGCIQA 2023 (random seed 2) | SRCC0.866 | 9 | |
| Image Quality Assessment | PKU-AIGIQA-4K (random seed 2) | SRCC81.86 | 9 | |
| Image Quality Assessment | AIGCIQA 2023 (random splits) | SRCC0.8628 | 9 | |
| Image Quality Assessment | PKU-AIGIQA 4K (random splits) | SRCC0.8113 | 9 |