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

arXiv: https://arxiv.org/abs/2204.10485 · HTML: https://mlsanity.com/paper/2204.10485/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 22 Apr 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Understanding Deformable Alignment in Video Super-Resolution](https://mlsanity.com/paper/2009.07265/) (2020)
- [Transformer for Image Quality Assessment](https://mlsanity.com/paper/2101.01097/) (2020)
- [Object Detection in Video with Spatiotemporal Sampling Networks](https://mlsanity.com/paper/1803.05549/) (2018)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [Region-Adaptive Deformable Network for Image Quality Assessment](https://mlsanity.com/paper/2104.11599/) (2021)
- [TediGAN: Text-Guided Diverse Face Image Generation and Manipulation](https://mlsanity.com/paper/2012.03308/) (2020)

## Built on by (most cited first, 30 of 57)

- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment](https://mlsanity.com/paper/2403.10854/) (2024)
- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption](https://mlsanity.com/paper/2503.11221/) (2025)
- [Similarity and Quality Metrics for MR Image-To-Image Translation](https://mlsanity.com/paper/2405.08431/) (2024)
- [Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment](https://mlsanity.com/paper/2305.10983/) (2023)
- [PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images](https://mlsanity.com/paper/2311.15556/) (2023)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution](https://mlsanity.com/paper/2410.17752/) (2024)
- [AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results](https://mlsanity.com/paper/2408.11982/) (2024)
- [Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models](https://mlsanity.com/paper/2412.11423/) (2024)
- [HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment](https://mlsanity.com/paper/2501.01116/) (2025)
- [BAND-2k: Banding Artifact Noticeable Database for Banding Detection and Quality Assessment](https://mlsanity.com/paper/2311.17752/) (2023)
- [You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment](https://mlsanity.com/paper/2310.09560/) (2023)
- [Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment](https://mlsanity.com/paper/2405.09472/) (2024)
- [ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment](https://mlsanity.com/paper/2407.11496/) (2024)
- [Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference](https://mlsanity.com/paper/2412.16939/) (2024)
- [Bridging the Perception Gap in Image Super-Resolution Evaluation](https://mlsanity.com/paper/2503.13074/) (2025)
- [EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing](https://mlsanity.com/paper/2603.14916/) (2026)
- [A New Dataset and Framework for Real-World Blurred Images Super-Resolution](https://mlsanity.com/paper/2407.14880/) (2024)
- [VTONQA: A Multi-Dimensional Quality Assessment Dataset for Virtual Try-on](https://mlsanity.com/paper/2601.02945/) (2026)
- [StarSRGAN: Improving Real-World Blind Super-Resolution](https://mlsanity.com/paper/2307.16169/) (2023)
- [Enhancing Representations through Heterogeneous Self-Supervised Learning](https://mlsanity.com/paper/2310.05108/) (2023)
- [MD-IQA: Learning Multi-scale Distributed Image Quality Assessment with Semi Supervised Learning for Low Dose CT](https://mlsanity.com/paper/2311.08024/) (2023)
- [D4: Text-guided diffusion model-based domain adaptive data augmentation for vineyard shoot detection](https://mlsanity.com/paper/2409.04060/) (2024)
- [Embodied Image Quality Assessment for Robotic Intelligence](https://mlsanity.com/paper/2412.18774/) (2024)
- [Evaluating quality metrics through the lenses of psychophysical measurements of low-level vision](https://mlsanity.com/paper/2503.16264/) (2025)
- [BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIP](https://mlsanity.com/paper/2506.17969/) (2025)
- [MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration](https://mlsanity.com/paper/2508.16887/) (2025)
- [AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment](https://mlsanity.com/paper/2509.26006/) (2025)

## Abstract (arXiv)

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.