Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment

TL;DR

This paper introduces DGQA, a novel unsupervised domain adaptation framework that improves blind image quality assessment by intelligently selecting distortion types to bridge synthetic and authentic image domains.

Contribution

The paper proposes a distortion-guided unsupervised domain adaptation method that reduces negative transfer and enhances generalization in blind image quality assessment.

Findings

DGQA outperforms existing methods in cross-domain BIQA tasks.

Adaptive multi-domain selection effectively matches data distributions.

DGQA can be combined with existing BIQA models for improved performance.

Abstract

The annotation of blind image quality assessment (BIQA) is labor-intensive and time-consuming, especially for authentic images. Training on synthetic data is expected to be beneficial, but synthetically trained models often suffer from poor generalization in real domains due to domain gaps. In this work, we make a key observation that introducing more distortion types in the synthetic dataset may not improve or even be harmful to generalizing authentic image quality assessment. To solve this challenge, we propose distortion-guided unsupervised domain adaptation for BIQA (DGQA), a novel framework that leverages adaptive multi-domain selection via prior knowledge from distortion to match the data distribution between the source domains and the target domain, thereby reducing negative transfer from the outlier source domains. Extensive experiments on two cross-domain settings (synthetic distortion to authentic distortion and synthetic distortion to algorithmic distortion) have demonstrated the effectiveness of our proposed DGQA. Besides, DGQA is orthogonal to existing model-based BIQA methods, and can be used in combination with such models to improve performance with less training data.