Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network

TL;DR

This paper introduces a hybrid attention-based neural network combining vision transformers and CNNs to improve image quality assessment, especially for GAN-generated images, outperforming existing methods.

Contribution

The paper proposes a novel hybrid architecture with attention mechanisms and deformable convolutions to enhance spatial relationship modeling in IQA models.

Findings

Outperforms state-of-the-art IQA methods on four datasets.

Ranks first in NTIRE 2022 Perceptual IQA Challenge.

Effectively models spatial relationships among image patches.

Abstract

Image quality assessment (IQA) algorithm aims to quantify the human perception of image quality. Unfortunately, there is a performance drop when assessing the distortion images generated by generative adversarial network (GAN) with seemingly realistic texture. In this work, we conjecture that this maladaptation lies in the backbone of IQA models, where patch-level prediction methods use independent image patches as input to calculate their scores separately, but lack spatial relationship modeling among image patches. Therefore, we propose an Attention-based Hybrid Image Quality Assessment Network (AHIQ) to deal with the challenge and get better performance on the GAN-based IQA task. Firstly, we adopt a two-branch architecture, including a vision transformer (ViT) branch and a convolutional neural network (CNN) branch for feature extraction. The hybrid architecture combines interaction information among image patches captured by ViT and local texture details from CNN. To make the features from shallow CNN more focused on the visually salient region, a deformable convolution is applied with the help of semantic information from the ViT branch. Finally, we use a patch-wise score prediction module to obtain the final score. The experiments show that our model outperforms the state-of-the-art methods on four standard IQA datasets and AHIQ ranked first on the Full Reference (FR) track of the NTIRE 2022 Perceptual Image Quality Assessment Challenge.