# FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images

arXiv: https://arxiv.org/abs/2403.14335 · HTML: https://mlsanity.com/paper/2403.14335/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Are Transformers More Robust Than CNNs?](https://mlsanity.com/paper/2111.05464/) (2021)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [Frequency Domain Model Augmentation for Adversarial Attack](https://mlsanity.com/paper/2207.05382/) (2022)
- [Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation](https://mlsanity.com/paper/1906.02611/) (2019)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain](https://mlsanity.com/paper/2108.08487/) (2021)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Improving robustness against common corruptions with frequency biased models](https://mlsanity.com/paper/2103.16241/) (2021)
- [HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness](https://mlsanity.com/paper/2307.11823/) (2023)
- [Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs](https://mlsanity.com/paper/1707.07830/) (2017)
- [On Performance of Multiscale Sparse Fast Fourier Transform Algorithm](https://mlsanity.com/paper/2011.05698/) (2020)

## Built on by (most cited first, 1 of 1)

- [Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics](https://mlsanity.com/paper/2407.06450/) (2024)

## Abstract (arXiv)

Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the applications. This paper presents a novel approach to improve robustness of any classification model, especially on severely corrupted images. Our method (FROST) employs high-frequency features to detect input image corruption type, and select layer-wise feature normalization statistics. FROST provides the state-of-the-art results for different models and datasets, outperforming competitors on ImageNet-C by up to 37.1% relative gain, improving baseline of 40.9% mCE on severe corruptions.