# Semi-Supervised Deep Ensembles for Blind Image Quality Assessment

arXiv: https://arxiv.org/abs/2106.14008 · HTML: https://mlsanity.com/paper/2106.14008/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 26 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [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)
- [Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks](https://mlsanity.com/paper/1511.06314/) (2015)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs](https://mlsanity.com/paper/1904.06505/) (2019)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment](https://mlsanity.com/paper/2003.03849/) (2020)
- [Generalized Negative Correlation Learning for Deep Ensembling](https://mlsanity.com/paper/2011.02952/) (2020)

## Built on by (most cited first, 6 of 6)

- [Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08763/) (2022)
- [A Quality Index Metric and Method for Online Self-Assessment of Autonomous Vehicles Sensory Perception](https://mlsanity.com/paper/2203.02588/) (2022)
- [Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated Videos](https://mlsanity.com/paper/2312.15425/) (2023)
- [Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches](https://mlsanity.com/paper/2207.14769/) (2022)
- [Cross-Dataset-Robust Method for Blind Real-World Image Quality Assessment](https://mlsanity.com/paper/2309.14868/) (2023)
- [MetaQAP - A Meta-Learning Approach for Quality-Aware Pretraining in Image Quality Assessment](https://mlsanity.com/paper/2506.16601/) (2025)

## Abstract (arXiv)

Ensemble methods are generally regarded to be better than a single model if the base learners are deemed to be "accurate" and "diverse." Here we investigate a semi-supervised ensemble learning strategy to produce generalizable blind image quality assessment models. We train a multi-head convolutional network for quality prediction by maximizing the accuracy of the ensemble (as well as the base learners) on labeled data, and the disagreement (i.e., diversity) among them on unlabeled data, both implemented by the fidelity loss. We conduct extensive experiments to demonstrate the advantages of employing unlabeled data for BIQA, especially in model generalization and failure identification.