# Impact of Light and Shadow on Robustness of Deep Neural Networks

arXiv: https://arxiv.org/abs/2305.14165 · HTML: https://mlsanity.com/paper/2305.14165/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples](https://mlsanity.com/paper/1709.04114/) (2017)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Maximal Jacobian-based Saliency Map Attack](https://mlsanity.com/paper/1808.07945/) (2018)
- [On Classification of Distorted Images with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.01924/) (2017)
- [DeepCorrect: Correcting DNN models against Image Distortions](https://mlsanity.com/paper/1705.02406/) (2017)
- [Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform](https://mlsanity.com/paper/1811.05819/) (2018)
- [Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such Attacks](https://mlsanity.com/paper/2012.14456/) (2020)
- [Revisiting Edge Detection in Convolutional Neural Networks](https://mlsanity.com/paper/2012.13576/) (2020)
- [Natural Adversarial Objects](https://mlsanity.com/paper/2111.04204/) (2021)

## Abstract (arXiv)

Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced with deliberate manipulations of input data, known as adversarial attacks. Moreover, the accuracy of DNNs is heavily influenced by the distribution of the training dataset. Distortions or perturbations in the color space of input images can introduce out-of-distribution data, resulting in misclassification. In this work, we propose a brightness-variation dataset, which incorporates 24 distinct brightness levels for each image within a subset of ImageNet. This dataset enables us to simulate the effects of light and shadow on the images, so as is to investigate the impact of light and shadow on the performance of DNNs. In our study, we conduct experiments using several state-of-the-art DNN architectures on the aforementioned dataset. Through our analysis, we discover a noteworthy positive correlation between the brightness levels and the loss of accuracy in DNNs. Furthermore, we assess the effectiveness of recently proposed robust training techniques and strategies, including AugMix, Revisit, and Free Normalizer, using the ResNet50 architecture on our brightness-variation dataset. Our experimental results demonstrate that these techniques can enhance the robustness of DNNs against brightness variation, leading to improved performance when dealing with images exhibiting varying brightness levels.