Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment

TL;DR

This paper enhances CLIP-based no-reference image quality assessment by incorporating a magnitude-aware cue and adaptive fusion, significantly improving performance without additional training.

Contribution

Introduces a magnitude-aware auxiliary cue and confidence-guided fusion scheme to improve CLIP-based IQA performance.

Findings

Outperforms standard CLIP-based IQA methods on multiple benchmarks.

Effective normalization of CLIP features via Box-Cox transformation.

No task-specific training required for the proposed method.

Abstract

Recent efforts have repurposed the Contrastive Language-Image Pre-training (CLIP) model for No-Reference Image Quality Assessment (NR-IQA) by measuring the cosine similarity between the image embedding and textual prompts such as "a good photo" or "a bad photo." However, this semantic similarity overlooks a critical yet underexplored cue: the magnitude of the CLIP image features, which we empirically find to exhibit a strong correlation with perceptual quality. In this work, we introduce a novel adaptive fusion framework that complements cosine similarity with a magnitude-aware quality cue. Specifically, we first extract the absolute CLIP image features and apply a Box-Cox transformation to statistically normalize the feature distribution and mitigate semantic sensitivity. The resulting scalar summary serves as a semantically-normalized auxiliary cue that complements cosine-based prompt matching. To integrate both cues effectively, we further design a confidence-guided fusion scheme that adaptively weighs each term according to its relative strength. Extensive experiments on multiple benchmark IQA datasets demonstrate that our method consistently outperforms standard CLIP-based IQA and state-of-the-art baselines, without any task-specific training.