# Source-free Unsupervised Domain Adaptation for Blind Image Quality Assessment

arXiv: https://arxiv.org/abs/2207.08124 · HTML: https://mlsanity.com/paper/2207.08124/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 54 references that are in the map.
- First posted on arXiv 17 Jul 2022.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [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)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [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)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks](https://mlsanity.com/paper/2002.09140/) (2020)
- [A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction](https://mlsanity.com/paper/1708.08190/) (2017)
- [Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics](https://mlsanity.com/paper/2101.10842/) (2021)
- [Blind Predicting Similar Quality Map for Image Quality Assessment](https://mlsanity.com/paper/1805.08493/) (2018)
- [Deep Transfer Network: Unsupervised Domain Adaptation](https://mlsanity.com/paper/1503.00591/) (2015)
- [LIQA: Lifelong Blind Image Quality Assessment](https://mlsanity.com/paper/2104.14115/) (2021)
- [No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.08561/) (2020)
- [Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks](https://mlsanity.com/paper/2004.06163/) (2020)
- [LIRA: Lifelong Image Restoration from Unknown Blended Distortions](https://mlsanity.com/paper/2008.08242/) (2020)

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

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [KVQ: Kwai Video Quality Assessment for Short-form Videos](https://mlsanity.com/paper/2402.07220/) (2024)
- [NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results](https://mlsanity.com/paper/2404.11313/) (2024)
- [VisualCritic: Making LMMs Perceive Visual Quality Like Humans](https://mlsanity.com/paper/2403.12806/) (2024)
- [MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection](https://mlsanity.com/paper/2302.04589/) (2023)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment](https://mlsanity.com/paper/2603.20086/) (2026)

## Abstract (arXiv)

Existing learning-based methods for blind image quality assessment (BIQA) are heavily dependent on large amounts of annotated training data, and usually suffer from a severe performance degradation when encountering the domain/distribution shift problem. Thanks to the development of unsupervised domain adaptation (UDA), some works attempt to transfer the knowledge from a label-sufficient source domain to a label-free target domain under domain shift with UDA. However, it requires the coexistence of source and target data, which might be impractical for source data due to the privacy or storage issues. In this paper, we take the first step towards the source-free unsupervised domain adaptation (SFUDA) in a simple yet efficient manner for BIQA to tackle the domain shift without access to the source data. Specifically, we cast the quality assessment task as a rating distribution prediction problem. Based on the intrinsic properties of BIQA, we present a group of well-designed self-supervised objectives to guide the adaptation of the BN affine parameters towards the target domain. Among them, minimizing the prediction entropy and maximizing the batch prediction diversity aim to encourage more confident results while avoiding the trivial solution. Besides, based on the observation that the IQA rating distribution of single image follows the Gaussian distribution, we apply Gaussian regularization to the predicted rating distribution to make it more consistent with the nature of human scoring. Extensive experimental results under cross-domain scenarios demonstrated the effectiveness of our proposed method to mitigate the domain shift.