Plug In, Grade Right: Psychology-Inspired AGIQA
Zhicheng Liao, Baoliang Chen, Hanwei Zhu, Lingyu Zhu, Shiqi Wang, Weisi Lin

TL;DR
This paper introduces a psychometrically inspired grading model for AGIQA that addresses semantic drift and improves image quality assessment by modeling difficulty levels and image ability, enhancing robustness and interpretability.
Contribution
It proposes an Arithmetic GRM-based quality grading module that mitigates semantic drift and can be integrated into various AGIQA frameworks for better performance.
Findings
Improves AGIQA performance across multiple models
Effectively handles natural and screen content images
Provides a more interpretable quality distribution
Abstract
Existing AGIQA models typically estimate image quality by measuring and aggregating the similarities between image embeddings and text embeddings derived from multi-grade quality descriptions. Although effective, we observe that such similarity distributions across grades usually exhibit multimodal patterns. For instance, an image embedding may show high similarity to both "excellent" and "poor" grade descriptions while deviating from the "good" one. We refer to this phenomenon as "semantic drift", where semantic inconsistencies between text embeddings and their intended descriptions undermine the reliability of text-image shared-space learning. To mitigate this issue, we draw inspiration from psychometrics and propose an improved Graded Response Model (GRM) for AGIQA. The GRM is a classical assessment model that categorizes a subject's ability across grades using test items with…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · Multimodal Machine Learning Applications · Domain Adaptation and Few-Shot Learning
