Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment

TL;DR

This paper introduces CSFIQA, a novel multi-scale blind image quality assessment framework that uses selective attention and contrastive learning to better mimic human perception and improve accuracy across diverse datasets.

Contribution

The paper proposes a new BIQA method combining selective attention and scale contrastive learning, effectively filtering redundant information and distinguishing quality variations across scales.

Findings

Achieves up to 8.8% SRCC improvement on real-world distortions.

Outperforms state-of-the-art methods on seven datasets.

Demonstrates better alignment with human visual perception.

Abstract

Human visual perception naturally evaluates image quality across multiple scales, a hierarchical process that existing blind image quality assessment (BIQA) algorithms struggle to replicate effectively. This limitation stems from a fundamental misunderstanding: current multi-scale approaches fail to recognize that quality perception varies dramatically between scales -- what appears degraded when viewed closely may look acceptable from a distance. This inconsistency not only creates misleading ``visual illusions'' during feature fusion but also introduces substantial redundant information that dilutes quality-critical features and leads to imprecise assessments. Our CSFIQA framework advances multi-scale BIQA via two key innovations: (1) a selective focus attention mechanism that mimics human visual attention by filtering out redundant cross-scale information that would otherwise mask subtle quality indicators, and (2) a scale contrastive learning strategy that explicitly learns to distinguish quality variations both across and within scales. By incorporating an adaptive noise sample matching mechanism, CSFIQA effectively identifies perceptual quality discrepancies in the same content viewed at different scales. Experiments demonstrate substantial improvements over state-of-the-art methods across seven datasets, achieving up to 8.8% SRCC improvement on challenging real-world distortions, confirming CSFIQA's superior alignment with human quality perception.