# StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessment

arXiv: https://arxiv.org/abs/2207.14489 · HTML: https://mlsanity.com/paper/2207.14489/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 72 references that are in the map.
- First posted on arXiv 29 Jul 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Beyond Sharing Weights for Deep Domain Adaptation](https://mlsanity.com/paper/1603.06432/) (2016)
- [Domain-Adversarial Neural Networks](https://mlsanity.com/paper/1412.4446/) (2014)
- [MixStyle Neural Networks for Domain Generalization and Adaptation](https://mlsanity.com/paper/2107.02053/) (2021)
- [MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13575/) (2021)
- [GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment](https://mlsanity.com/paper/2103.07666/) (2021)
- [No-Reference Point Cloud Quality Assessment via Domain Adaptation](https://mlsanity.com/paper/2112.02851/) (2021)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [Locally Adaptive Structure and Texture Similarity for Image Quality Assessment](https://mlsanity.com/paper/2110.08521/) (2021)
- [Adversarial Teacher-Student Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1804.00644/) (2018)
- [Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration](https://mlsanity.com/paper/2007.11430/) (2020)
- [LIQA: Lifelong Blind Image Quality Assessment](https://mlsanity.com/paper/2104.14115/) (2021)

## Built on by (most cited first, 9 of 9)

- [NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results](https://mlsanity.com/paper/2404.11313/) (2024)
- [Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment](https://mlsanity.com/paper/2405.04167/) (2024)
- [QMamba: On First Exploration of Vision Mamba for Image Quality Assessment](https://mlsanity.com/paper/2406.09546/) (2024)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [QD-PCQA: Quality-Aware Domain Adaptation for Point Cloud Quality Assessment](https://mlsanity.com/paper/2603.03726/) (2026)
- [From Images to Point Clouds: An Efficient Solution for Cross-media Blind Quality Assessment without Annotated Training](https://mlsanity.com/paper/2501.13387/) (2025)
- [Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions](https://mlsanity.com/paper/2601.00225/) (2026)
- [UPDA: Unsupervised Progressive Domain Adaptation for No-Reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2602.11969/) (2026)
- [GT-PCQA: Geometry-Texture Decoupled Point Cloud Quality Assessment with MLLM](https://mlsanity.com/paper/2603.14951/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have shown great potential in non-reference image quality assessment (NR-IQA). However, the annotation of NR-IQA is labor-intensive and time-consuming, which severely limits their application especially for authentic images. To relieve the dependence on quality annotation, some works have applied unsupervised domain adaptation (UDA) to NR-IQA. However, the above methods ignore that the alignment space used in classification is sub-optimal, since the space is not elaborately designed for perception. To solve this challenge, we propose an effective perception-oriented unsupervised domain adaptation method StyleAM for NR-IQA, which transfers sufficient knowledge from label-rich source domain data to label-free target domain images via Style Alignment and Mixup. Specifically, we find a more compact and reliable space i.e., feature style space for perception-oriented UDA based on an interesting/amazing observation, that the feature style (i.e., the mean and variance) of the deep layer in DNNs is exactly associated with the quality score in NR-IQA. Therefore, we propose to align the source and target domains in a more perceptual-oriented space i.e., the feature style space, to reduce the intervention from other quality-irrelevant feature factors. Furthermore, to increase the consistency between quality score and its feature style, we also propose a novel feature augmentation strategy Style Mixup, which mixes the feature styles (i.e., the mean and variance) before the last layer of DNNs together with mixing their labels. Extensive experimental results on two typical cross-domain settings (i.e., synthetic to authentic, and multiple distortions to one distortion) have demonstrated the effectiveness of our proposed StyleAM on NR-IQA.