# Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment

arXiv: https://arxiv.org/abs/2204.08763 · HTML: https://mlsanity.com/paper/2204.08763/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 86 references that are in the map.
- First posted on arXiv 19 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [CycleISP: Real Image Restoration via Improved Data Synthesis](https://mlsanity.com/paper/2003.07761/) (2020)
- [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)
- [The 2018 PIRM Challenge on Perceptual Image Super-resolution](https://mlsanity.com/paper/1809.07517/) (2018)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach](https://mlsanity.com/paper/1609.04757/) (2016)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training](https://mlsanity.com/paper/2006.11280/) (2020)
- [Projected Distribution Loss for Image Enhancement](https://mlsanity.com/paper/2012.09289/) (2020)
- [Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric](https://mlsanity.com/paper/2011.15002/) (2020)
- [NTIRE 2021 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2105.03072/) (2021)
- [Geodesics of learned representations](https://mlsanity.com/paper/1511.06394/) (2015)
- [Region-Adaptive Deformable Network for Image Quality Assessment](https://mlsanity.com/paper/2104.11599/) (2021)
- [Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency](https://mlsanity.com/paper/2006.12704/) (2020)
- [(ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment](https://mlsanity.com/paper/2105.02531/) (2021)
- [Semi-Supervised Deep Ensembles for Blind Image Quality Assessment](https://mlsanity.com/paper/2106.14008/) (2021)
- [Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks](https://mlsanity.com/paper/1904.03639/) (2019)

## Built on by (most cited first, 12 of 12)

- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset](https://mlsanity.com/paper/2405.18842/) (2024)
- [DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator](https://mlsanity.com/paper/2211.04927/) (2022)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations](https://mlsanity.com/paper/2405.02171/) (2024)
- [BPCLIP: A Bottom-up Image Quality Assessment from Distortion to Semantics Based on CLIP](https://mlsanity.com/paper/2506.17969/) (2025)
- [How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices](https://mlsanity.com/paper/2603.05010/) (2026)
- [SAM-IQA: Can Segment Anything Boost Image Quality Assessment?](https://mlsanity.com/paper/2307.04455/) (2023)
- [R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment](https://mlsanity.com/paper/2603.10578/) (2026)
- [From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment](https://mlsanity.com/paper/2609.08316/) (2026)

## Abstract (arXiv)

Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ.