# Data Augmentation in Training CNNs: Injecting Noise to Images

arXiv: https://arxiv.org/abs/2307.06855 · HTML: https://mlsanity.com/paper/2307.06855/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 12 Jul 2023.

## Builds on (most cited first, 5 of 5)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Towards Deep Neural Network Architectures Robust to Adversarial Examples](https://mlsanity.com/paper/1412.5068/) (2014)
- [A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition](https://mlsanity.com/paper/1606.06864/) (2016)
- [TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process](https://mlsanity.com/paper/1703.00645/) (2017)

## Built on by (most cited first, 10 of 10)

- [PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies](https://mlsanity.com/paper/2506.09237/) (2025)
- [SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise](https://mlsanity.com/paper/2312.01523/) (2023)
- [FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed](https://mlsanity.com/paper/2507.03779/) (2025)
- [Policy Gradient-Driven Noise Mask](https://mlsanity.com/paper/2406.14568/) (2024)
- [The Benefit of Noise-Injection for Dynamic Gray-Box Model Creation](https://mlsanity.com/paper/2310.01517/) (2023)
- [Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprinting](https://mlsanity.com/paper/2407.13303/) (2024)
- [Harnessing the Power of Noise: A Survey of Techniques and Applications](https://mlsanity.com/paper/2410.06348/) (2024)
- [Using machine learning to map simulated noisy and laser-limited multidimensional spectra to molecular electronic couplings](https://mlsanity.com/paper/2503.15706/) (2025)
- [Noise Injection: Improving Out-of-Distribution Generalization for Limited Size Datasets](https://mlsanity.com/paper/2511.03855/) (2025)
- [Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning](https://mlsanity.com/paper/2605.23171/) (2026)

## Abstract (arXiv)

Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying magnitudes to Convolutional Neural Network (CNN) architectures. Noise models that are distributed with different density functions are given common magnitude levels via Structural Similarity (SSIM) metric in order to create an appropriate ground for comparison. The basic results are conforming with the most of the common notions in machine learning, and also introduce some novel heuristics and recommendations on noise injection. The new approaches will provide better understanding on optimal learning procedures for image classification.