# Dynamic Batch Norm Statistics Update for Natural Robustness

Source: [Dynamic Batch Norm Statistics Update for Natural Robustness](<https://www.sota2.com/research/paper/68fa71101e209131cea4f05f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:27:18.233Z

Authors: Shahbaz Rezaei, Mohammad Sadegh Norouzzadeh

Published: 2023-10-31T17:20:30.000Z

## Abstract

DNNs trained on natural clean samples have been shown to perform poorly on corrupted samples, such as noisy or blurry images. Various data augmentation methods have been recently proposed to improve DNN's robustness against common corruptions. Despite their success, they require computationally expensive training and cannot be applied to off-the-shelf trained models. Recently, it has been shown that updating BatchNorm (BN) statistics of an off-the-shelf model on a single corruption improves its accuracy on that corruption significantly. However, adopting the idea at inference time when the type of corruption is unknown and changing decreases the effectiveness of this method. In this paper, we harness the Fourier domain to detect the corruption type, a challenging task in the image domain. We propose a unified framework consisting of a corruption-detection model and BN statistics update that improves the corruption accuracy of any off-the-shelf trained model. We benchmark our framework on different models and datasets. Our results demonstrate about 8% and 4% accuracy improvement on CIFAR10-C and ImageNet-C, respectively. Furthermore, our framework can further improve the accuracy of state-of-the-art robust models, such as AugMix and DeepAug.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.20649>)

[PDF](<https://arxiv.org/pdf/2310.20649.pdf>)
