PMT-IQA: Progressive Multi-task Learning for Blind Image Quality Assessment

TL;DR

This paper introduces PMT-IQA, a novel model for blind image quality assessment that leverages multi-scale features and progressive multi-task learning to better capture complex distortion patterns and improve regression performance.

Contribution

The paper proposes a new BIQA model combining multi-scale feature extraction and progressive multi-task learning, addressing limitations of existing methods in handling distortion diversity.

Findings

PMT-IQA outperforms existing BIQA methods on four public datasets.

Multi-scale features enhance distortion pattern recognition.

Progressive multi-task learning improves regression accuracy.

Abstract

Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.