# Continual Learning for Blind Image Quality Assessment

arXiv: https://arxiv.org/abs/2102.09717 · HTML: https://mlsanity.com/paper/2102.09717/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 94 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)

## Built on by (most cited first, 30 of 36)

- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset](https://mlsanity.com/paper/2405.18842/) (2024)
- [Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop](https://mlsanity.com/paper/2210.00933/) (2022)
- [Modular Blind Video Quality Assessment](https://mlsanity.com/paper/2402.19276/) (2024)
- [CONVIQT: Contrastive Video Quality Estimator](https://mlsanity.com/paper/2206.14713/) (2022)
- [Task-Specific Normalization for Continual Learning of Blind Image Quality Models](https://mlsanity.com/paper/2107.13429/) (2021)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts](https://mlsanity.com/paper/2403.04993/) (2024)
- [Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2409.05540/) (2024)
- [Distilling Knowledge from Object Classification to Aesthetics Assessment](https://mlsanity.com/paper/2206.00809/) (2022)
- [Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics](https://mlsanity.com/paper/2405.18790/) (2024)
- [Semi-Supervised Deep Ensembles for Blind Image Quality Assessment](https://mlsanity.com/paper/2106.14008/) (2021)
- [UID2021: An Underwater Image Dataset for Evaluation of No-reference Quality Assessment Metrics](https://mlsanity.com/paper/2204.08813/) (2022)
- [AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity](https://mlsanity.com/paper/2411.16087/) (2024)
- [Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment](https://mlsanity.com/paper/2209.07126/) (2022)
- [Blind Multimodal Quality Assessment of Low-light Images](https://mlsanity.com/paper/2303.10369/) (2023)
- [Image Quality Assessment in the Modern Age](https://mlsanity.com/paper/2110.09699/) (2021)
- [Learning from Mixed Datasets: A Monotonic Image Quality Assessment Model](https://mlsanity.com/paper/2209.10451/) (2022)
- [HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning](https://mlsanity.com/paper/2309.15038/) (2023)
- [Prompt Customization for Continual Learning](https://mlsanity.com/paper/2404.18060/) (2024)
- [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)
- [Quality Assessment of Low Light Restored Images: A Subjective Study and an Unsupervised Model](https://mlsanity.com/paper/2202.02277/) (2022)
- [Blind Image Quality Assessment: A Brief Survey](https://mlsanity.com/paper/2312.16551/) (2023)
- [MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training](https://mlsanity.com/paper/2508.07590/) (2025)
- [HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2508.15130/) (2025)

## Abstract (arXiv)

The explosive growth of image data facilitates the fast development of image processing and computer vision methods for emerging visual applications, meanwhile introducing novel distortions to the processed images. This poses a grand challenge to existing blind image quality assessment (BIQA) models, failing to continually adapt to such subpopulation shift. Recent work suggests training BIQA methods on the combination of all available human-rated IQA datasets. However, this type of approach is not scalable to a large number of datasets, and is cumbersome to incorporate a newly created dataset as well. In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data. We first identify five desiderata in the new setting with a measure to quantify the plasticity-stability trade-off. We then propose a simple yet effective method for learning BIQA models continually. Specifically, based on a shared backbone network, we add a prediction head for a new dataset, and enforce a regularizer to allow all prediction heads to evolve with new data while being resistant to catastrophic forgetting of old data. We compute the quality score by an adaptive weighted summation of estimates from all prediction heads. Extensive experiments demonstrate the promise of the proposed continual learning method in comparison to standard training techniques for BIQA. We made the code publicly available at https://github.com/zwx8981/BIQA_CL.