# Deep Neural Networks for Blind Image Quality Assessment: Addressing the Data Challenge

arXiv: https://arxiv.org/abs/2109.12161 · HTML: https://mlsanity.com/paper/2109.12161/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 127 references that are in the map.
- First posted on arXiv 24 Sep 2021.

## Builds on (most cited first, 21 of 21)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [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)
- [OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks](https://mlsanity.com/paper/1312.6229/) (2013)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs](https://mlsanity.com/paper/1904.06505/) (2019)
- [Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach](https://mlsanity.com/paper/1609.04757/) (2016)
- [On the Use of Deep Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/1602.05531/) (2016)
- [KonIQ-10k: Towards an ecologically valid and large-scale IQA database](https://mlsanity.com/paper/1803.08489/) (2018)
- [A Detail Based Method for Linear Full Reference Image Quality Prediction](https://mlsanity.com/paper/1709.03124/) (2017)

## Built on by (most cited first, 3 of 3)

- [MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion](https://mlsanity.com/paper/2205.10101/) (2022)
- [Degraded Reference Image Quality Assessment](https://mlsanity.com/paper/2110.14899/) (2021)
- [Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment](https://mlsanity.com/paper/2406.09858/) (2024)

## Abstract (arXiv)

The enormous space and diversity of natural images is usually represented by a few small-scale human-rated image quality assessment (IQA) datasets. This casts great challenges to deep neural network (DNN) based blind IQA (BIQA), which requires large-scale training data that is representative of the natural image distribution. It is extremely difficult to create human-rated IQA datasets composed of millions of images due to constraints of subjective testing. While a number of efforts have focused on design innovations to enhance the performance of DNN based BIQA, attempts to address the scarcity of labeled IQA data remain surprisingly missing. To address this data challenge, we construct so far the largest IQA database, namely Waterloo Exploration-II, which contains 3,570 pristine reference and around 3.45 million singly and multiply distorted images. Since subjective testing for such a large dataset is nearly impossible, we develop a novel mechanism that synthetically assigns perceptual quality labels to the distorted images. We construct a DNN-based BIQA model called EONSS, train it on Waterloo Exploration-II, and test it on nine subject-rated IQA datasets, without any retraining or fine-tuning. The results show that with a straightforward DNN architecture, EONSS is able to outperform the very state-of-the-art in BIQA, both in terms of quality prediction performance and execution speed. This study strongly supports the view that the quantity and quality of meaningfully annotated training data, rather than a sophisticated network architecture or training strategy, is the dominating factor that determines the performance of DNN-based BIQA models. (Note: Since this is an ongoing project, the final versions of Waterloo Exploration-II database, quality annotations, and EONSS, will be made publicly available in the future when it culminates.)