AM-BQA: Enhancing blind image quality assessment using attention retractable features and multi-dimensional learning

초록

In the realm of no-reference image quality assessment (NR-IQA), acquiring pristine source content for reference is often unattainable. This absence of reference presents challenges in accurately estimating perceptual scores due to the diversity and complexity of distortion patterns. To tackle these challenges, we introduce a novel approach named AM-BQA: Enhancing Blind Image Quality Assessment using Attention Retractable Features and Multi-Dimensional Learning, designed to capture and analyze complex patterns. Our method involves several steps. Firstly, we extract crucial and intricate features using a vision transformer. Next, we employ a multi-head transpose attention block with a dual key, incorporating overlap convolution patches and transpose attention into these extracted features. Finally, the attention maps generated by this process pass through an attention retractable block and a weighted multi-head layer to calculate the final quality score. By employing this architecture, we enhance both global and local interactions between complex patches. To validate the effectiveness of our approach, we assess it on four standard datasets (LIVE, TID2013, CSIQ, and KADID-10 K), including both synthetic datasets. Additionally, we conduct experiments on authentic datasets and demonstrate that our model achieves state-of-the-art performance across multiple datasets. The source code and pretrained models are available on this GitHub repository: https://github.com/adhikariastha5/AM-BQA.

키워드