# Understanding How Image Quality Affects Deep Neural Networks

arXiv: https://arxiv.org/abs/1604.04004 · HTML: https://mlsanity.com/paper/1604.04004/

## Key facts

- Cited by 119 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2016.

## Built on by (most cited first, 30 of 119)

- [MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos](https://mlsanity.com/paper/2303.14933/) (2023)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [PRIME: A few primitives can boost robustness to common corruptions](https://mlsanity.com/paper/2112.13547/) (2021)
- [Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression](https://mlsanity.com/paper/2301.13838/) (2023)
- [Towards Semantic Communications: Deep Learning-Based Image Semantic Coding](https://mlsanity.com/paper/2208.04094/) (2022)
- [Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection](https://mlsanity.com/paper/2407.12582/) (2024)
- [Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology](https://mlsanity.com/paper/2206.14973/) (2022)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization](https://mlsanity.com/paper/2307.01946/) (2023)
- [Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines](https://mlsanity.com/paper/2112.00659/) (2021)
- [NoisyMix: Boosting Model Robustness to Common Corruptions](https://mlsanity.com/paper/2202.01263/) (2022)
- [Augraphy: A Data Augmentation Library for Document Images](https://mlsanity.com/paper/2208.14558/) (2022)
- [The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review](https://mlsanity.com/paper/2402.13635/) (2024)
- [Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models](https://mlsanity.com/paper/2108.06581/) (2021)
- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification](https://mlsanity.com/paper/2112.14299/) (2021)
- [I-SplitEE: Image classification in Split Computing DNNs with Early Exits](https://mlsanity.com/paper/2401.10541/) (2024)
- [Early-exit deep neural networks for distorted images: providing an efficient edge offloading](https://mlsanity.com/paper/2108.09343/) (2021)
- [DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection](https://mlsanity.com/paper/2302.02005/) (2023)
- [Packet-Loss-Tolerant Split Inference for Delay-Sensitive Deep Learning in Lossy Wireless Networks](https://mlsanity.com/paper/2104.13629/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Level](https://mlsanity.com/paper/2303.01899/) (2023)
- [On the Robustness of Object Detection Models on Aerial Images](https://mlsanity.com/paper/2308.15378/) (2023)
- [AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems](https://mlsanity.com/paper/2101.09752/) (2021)
- [A trainable monogenic ConvNet layer robust in front of large contrast changes in image classification](https://mlsanity.com/paper/2109.06926/) (2021)
- [Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery](https://mlsanity.com/paper/2205.08002/) (2022)
- [Confidence-based Reliable Learning under Dual Noises](https://mlsanity.com/paper/2302.05098/) (2023)
- [Operationalizing Convolutional Neural Network Architectures for Prohibited Object Detection in X-Ray Imagery](https://mlsanity.com/paper/2110.04906/) (2021)
- [Certifying Model Accuracy under Distribution Shifts](https://mlsanity.com/paper/2201.12440/) (2022)
- [Does lossy image compression affect racial bias within face recognition?](https://mlsanity.com/paper/2208.07613/) (2022)

## Abstract (arXiv)

Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks. In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, contrast, JPEG, and JPEG2000 compression. We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise. These results enable future work in developing deep neural networks that are more invariant to quality distortions.