# MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion

arXiv: https://arxiv.org/abs/2205.10101 · HTML: https://mlsanity.com/paper/2205.10101/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 64 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [DeepViT: Towards Deeper Vision Transformer](https://mlsanity.com/paper/2103.11886/) (2021)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Deep Learning Based Text Classification: A Comprehensive Review](https://mlsanity.com/paper/2004.03705/) (2020)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Transformer for Image Quality Assessment](https://mlsanity.com/paper/2101.01097/) (2020)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [NTIRE 2021 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2105.03072/) (2021)
- [An Alternative Cross Entropy Loss for Learning-to-Rank](https://mlsanity.com/paper/1911.09798/) (2019)
- [No-Reference Image Quality Assessment by Hallucinating Pristine Features](https://mlsanity.com/paper/2108.04165/) (2021)
- [Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness](https://mlsanity.com/paper/2105.07139/) (2021)
- [KonIQ-10k: Towards an ecologically valid and large-scale IQA database](https://mlsanity.com/paper/1803.08489/) (2018)
- [Learning to Blindly Assess Image Quality in the Laboratory and Wild](https://mlsanity.com/paper/1907.00516/) (2019)
- [Learning to Rank for Active Learning: A Listwise Approach](https://mlsanity.com/paper/2008.00078/) (2020)
- [Deep Perceptual Image Quality Assessment for Compression](https://mlsanity.com/paper/2103.01114/) (2021)

## Built on by (most cited first, 10 of 10)

- [NTIRE 2024 Quality Assessment of AI-Generated Content Challenge](https://mlsanity.com/paper/2404.16687/) (2024)
- [Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment](https://mlsanity.com/paper/2312.04838/) (2023)
- [Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey](https://mlsanity.com/paper/2404.11159/) (2024)
- [AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity](https://mlsanity.com/paper/2411.16087/) (2024)
- [You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment](https://mlsanity.com/paper/2310.09560/) (2023)
- [Blind CT Image Quality Assessment Using DDPM-derived Content and Transformer-based Evaluator](https://mlsanity.com/paper/2310.03118/) (2023)
- [A Lightweight Parallel Framework for Blind Image Quality Assessment](https://mlsanity.com/paper/2402.12043/) (2024)
- [No-Reference Image Quality Assessment with Global-Local Progressive Integration and Semantic-Aligned Quality Transfer](https://mlsanity.com/paper/2408.03885/) (2024)
- [VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results](https://mlsanity.com/paper/2509.09190/) (2025)
- [Cost Savings from Automatic Quality Assessment of Generated Images](https://mlsanity.com/paper/2510.16179/) (2025)

## Abstract (arXiv)

Measuring the perceptual quality of images automatically is an essential task in the area of computer vision, as degradations on image quality can exist in many processes from image acquisition, transmission to enhancing. Many Image Quality Assessment(IQA) algorithms have been designed to tackle this problem. However, it still remains un settled due to the various types of image distortions and the lack of large-scale human-rated datasets. In this paper, we propose a novel algorithm based on the Swin Transformer [31] with fused features from multiple stages, which aggregates information from both local and global features to better predict the quality. To address the issues of small-scale datasets, relative rankings of images have been taken into account together with regression loss to simultaneously optimize the model. Furthermore, effective data augmentation strategies are also used to improve the performance. In comparisons with previous works, experiments are carried out on two standard IQA datasets and a challenge dataset. The results demonstrate the effectiveness of our work. The proposed method outperforms other methods on standard datasets and ranks 2nd in the no-reference track of NTIRE 2022 Perceptual Image Quality Assessment Challenge [53]. It verifies that our method is promising in solving diverse IQA problems and thus can be used to real-word applications.