# Task-Specific Normalization for Continual Learning of Blind Image Quality Models

arXiv: https://arxiv.org/abs/2107.13429 · HTML: https://mlsanity.com/paper/2107.13429/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 71 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 30 of 34)

- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [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)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (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)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [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)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [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)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [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)
- [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)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Scalable and Order-robust Continual Learning with Additive Parameter Decomposition](https://mlsanity.com/paper/1902.09432/) (2019)
- [Normalization Techniques in Training DNNs: Methodology, Analysis and Application](https://mlsanity.com/paper/2009.12836/) (2020)
- [Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach](https://mlsanity.com/paper/1609.04757/) (2016)

## Built on by (most cited first, 18 of 18)

- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [A Deep Learning based No-reference Quality Assessment Model for UGC Videos](https://mlsanity.com/paper/2204.14047/) (2022)
- [Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception](https://mlsanity.com/paper/2108.08505/) (2021)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2409.05540/) (2024)
- [PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer](https://mlsanity.com/paper/2407.03813/) (2024)
- [Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment](https://mlsanity.com/paper/2209.07126/) (2022)
- [Prompt Customization for Continual Learning](https://mlsanity.com/paper/2404.18060/) (2024)
- [Class Incremental Learning with Task-Specific Batch Normalization and Out-of-Distribution Detection](https://mlsanity.com/paper/2411.00430/) (2024)
- [Adapter-Enhanced Semantic Prompting for Continual Learning](https://mlsanity.com/paper/2412.11074/) (2024)
- [CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation](https://mlsanity.com/paper/2508.10432/) (2025)
- [Plug In, Grade Right: Psychology-Inspired AGIQA](https://mlsanity.com/paper/2512.22780/) (2025)
- [From Global to Granular: Revealing IQA Model Performance via Correlation Surface](https://mlsanity.com/paper/2601.21738/) (2026)
- [HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2508.15130/) (2025)
- [Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling](https://mlsanity.com/paper/2511.19024/) (2025)
- [LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results](https://mlsanity.com/paper/2604.11207/) (2026)
- [MLLM-Guided Semantic Correction for Text-to-Video Generation](https://mlsanity.com/paper/2608.16513/) (2026)
- [Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework](https://mlsanity.com/paper/2609.02529/) (2026)

## Abstract (arXiv)

In this paper, we present a simple yet effective continual learning method for blind image quality assessment (BIQA) with improved quality prediction accuracy, plasticity-stability trade-off, and task-order/-length robustness. The key step in our approach is to freeze all convolution filters of a pre-trained deep neural network (DNN) for an explicit promise of stability, and learn task-specific normalization parameters for plasticity. We assign each new IQA dataset (i.e., task) a prediction head, and load the corresponding normalization parameters to produce a quality score. The final quality estimate is computed by black a weighted summation of predictions from all heads with a lightweight K-means gating mechanism. Extensive experiments on six IQA datasets demonstrate the advantages of the proposed method in comparison to previous training techniques for BIQA.