# Deep Ensembling for Perceptual Image Quality Assessment

arXiv: https://arxiv.org/abs/2305.09141 · HTML: https://mlsanity.com/paper/2305.09141/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 63 references that are in the map.
- First posted on arXiv 16 May 2023.

## Builds on (most cited first, 10 of 10)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [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)
- [dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs](https://mlsanity.com/paper/1904.06505/) (2019)
- [On the Use of Deep Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/1602.05531/) (2016)
- [A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment](https://mlsanity.com/paper/1705.05126/) (2017)

## Built on by (most cited first, 8 of 8)

- [MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization](https://mlsanity.com/paper/2509.01411/) (2025)
- [A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic](https://mlsanity.com/paper/2505.00534/) (2025)
- [MetaQAP - A Meta-Learning Approach for Quality-Aware Pretraining in Image Quality Assessment](https://mlsanity.com/paper/2506.16601/) (2025)
- [Enhancing Wireless Device Identification through RF Fingerprinting: Leveraging Transient Energy Spectrum Analysis](https://mlsanity.com/paper/2506.17439/) (2025)
- [Attention-Based Ensemble Learning for Crop Classification Using Landsat 8-9 Fusion](https://mlsanity.com/paper/2506.18321/) (2025)
- [A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement](https://mlsanity.com/paper/2506.18323/) (2025)
- [Deep Learning-Based Age Estimation and Gender Deep Learning-Based Age Estimation and Gender Classification for Targeted Advertisement](https://mlsanity.com/paper/2507.18565/) (2025)
- [No-Reference Image Contrast Assessment with Customized EfficientNet-B0](https://mlsanity.com/paper/2509.21967/) (2025)

## Abstract (arXiv)

Blind image quality assessment is a challenging task particularly due to the unavailability of reference information. Training a deep neural network requires a large amount of training data which is not readily available for image quality. Transfer learning is usually opted to overcome this limitation and different deep architectures are used for this purpose as they learn features differently. After extensive experiments, we have designed a deep architecture containing two CNN architectures as its sub-units. Moreover, a self-collected image database BIQ2021 is proposed with 12,000 images having natural distortions. The self-collected database is subjectively scored and is used for model training and validation. It is demonstrated that synthetic distortion databases cannot provide generalization beyond the distortion types used in the database and they are not ideal candidates for general-purpose image quality assessment. Moreover, a large-scale database of 18.75 million images with synthetic distortions is used to pretrain the model and then retrain it on benchmark databases for evaluation. Experiments are conducted on six benchmark databases three of which are synthetic distortion databases (LIVE, CSIQ and TID2013) and three are natural distortion databases (LIVE Challenge Database, CID2013 and KonIQ-10 k). The proposed approach has provided a Pearson correlation coefficient of 0.8992, 0.8472 and 0.9452 subsequently and Spearman correlation coefficient of 0.8863, 0.8408 and 0.9421. Moreover, the performance is demonstrated using perceptually weighted rank correlation to indicate the perceptual superiority of the proposed approach. Multiple experiments are conducted to validate the generalization performance of the proposed model by training on different subsets of the databases and validating on the test subset of BIQ2021 database.