# Noise Injection: Improving Out-of-Distribution Generalization for Limited Size Datasets

arXiv: https://arxiv.org/abs/2511.03855 · HTML: https://mlsanity.com/paper/2511.03855/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization](https://mlsanity.com/paper/2009.12829/) (2020)
- [BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients](https://mlsanity.com/paper/2006.01174/) (2020)
- [Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis](https://mlsanity.com/paper/2203.10977/) (2022)
- [Out-of-distribution Detection in Medical Image Analysis: A survey](https://mlsanity.com/paper/2404.18279/) (2024)
- [The Data Addition Dilemma](https://mlsanity.com/paper/2408.04154/) (2024)
- [OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detection](https://mlsanity.com/paper/2503.16247/) (2025)
- [Data Augmentation in Training CNNs: Injecting Noise to Images](https://mlsanity.com/paper/2307.06855/) (2023)

## Abstract (arXiv)

Deep learned (DL) models for image recognition have been shown to fail to generalize to data from different devices, populations, etc. COVID-19 detection from Chest X-rays (CXRs), in particular, has been shown to fail to generalize to out-of-distribution (OOD) data from new clinical sources not covered in the training set. This occurs because models learn to exploit shortcuts - source-specific artifacts that do not translate to new distributions - rather than reasonable biomarkers to maximize performance on in-distribution (ID) data. Rendering the models more robust to distribution shifts, our study investigates the use of fundamental noise injection techniques (Gaussian, Speckle, Poisson, and Salt and Pepper) during training. Our empirical results demonstrate that this technique can significantly reduce the performance gap between ID and OOD evaluation from 0.10-0.20 to 0.01-0.06, based on results averaged over ten random seeds across key metrics such as AUC, F1, accuracy, recall and specificity. Our source code is publicly available at https://github.com/Duongmai127/Noisy-ood