# On Classification of Distorted Images with Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1701.01924 · HTML: https://mlsanity.com/paper/1701.01924/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2017.

## Built on by (most cited first, 26 of 26)

- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [Early-exit deep neural networks for distorted images: providing an efficient edge offloading](https://mlsanity.com/paper/2108.09343/) (2021)
- [Inverse Problems Leveraging Pre-trained Contrastive Representations](https://mlsanity.com/paper/2110.07439/) (2021)
- [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)
- [Confidence-based Reliable Learning under Dual Noises](https://mlsanity.com/paper/2302.05098/) (2023)
- [Certifying Model Accuracy under Distribution Shifts](https://mlsanity.com/paper/2201.12440/) (2022)
- [A New Approach to Improve Learning-based Deepfake Detection in Realistic Conditions](https://mlsanity.com/paper/2203.11807/) (2022)
- [Enhancing object detection robustness: A synthetic and natural perturbation approach](https://mlsanity.com/paper/2304.10622/) (2023)
- [Picking Up Quantization Steps for Compressed Image Classification](https://mlsanity.com/paper/2304.10714/) (2023)
- [Collaboratively Learning Federated Models from Noisy Decentralized Data](https://mlsanity.com/paper/2409.02189/) (2024)
- [Perspective Transformation Layer](https://mlsanity.com/paper/2201.05706/) (2022)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learning](https://mlsanity.com/paper/2403.04385/) (2024)
- [Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness](https://mlsanity.com/paper/2406.05006/) (2024)
- [Fast and Robust Structural Damage Analysis of Civil Infrastructure Using UAV Imagery](https://mlsanity.com/paper/2110.04806/) (2021)
- [A Novel Framework for Assessment of Learning-based Detectors in Realistic Conditions with Application to Deepfake Detection](https://mlsanity.com/paper/2203.11797/) (2022)
- [On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks](https://mlsanity.com/paper/2208.11372/) (2022)
- [Impact of Scaled Image on Robustness of Deep Neural Networks](https://mlsanity.com/paper/2209.02132/) (2022)
- [Impact of Colour Variation on Robustness of Deep Neural Networks](https://mlsanity.com/paper/2209.02832/) (2022)
- [Blur Invariants for Image Recognition](https://mlsanity.com/paper/2301.07581/) (2023)
- [Noise robust neural network architecture](https://mlsanity.com/paper/2305.09276/) (2023)
- [Impact of Light and Shadow on Robustness of Deep Neural Networks](https://mlsanity.com/paper/2305.14165/) (2023)
- [Pruning Distorted Images in MNIST Handwritten Digits](https://mlsanity.com/paper/2307.14343/) (2023)
- [Predicting the Reliability of an Image Classifier under Image Distortion](https://mlsanity.com/paper/2412.16881/) (2024)
- [The RealDefocus Benchmark for Defocus Deblurring](https://mlsanity.com/paper/2607.21078/) (2026)

## Abstract (arXiv)

Image blur and image noise are common distortions during image acquisition. In this paper, we systematically study the effect of image distortions on the deep neural network (DNN) image classifiers. First, we examine the DNN classifier performance under four types of distortions. Second, we propose two approaches to alleviate the effect of image distortion: re-training and fine-tuning with noisy images. Our results suggest that, under certain conditions, fine-tuning with noisy images can alleviate much effect due to distorted inputs, and is more practical than re-training.