# Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks

arXiv: https://arxiv.org/abs/2106.00673 · HTML: https://mlsanity.com/paper/2106.00673/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 1 Jun 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Deep Learning on Image Denoising: An overview](https://mlsanity.com/paper/1912.13171/) (2019)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Effects of Degradations on Deep Neural Network Architectures](https://mlsanity.com/paper/1807.10108/) (2018)
- [Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift](https://mlsanity.com/paper/1801.05134/) (2018)
- [Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning](https://mlsanity.com/paper/1907.03029/) (2019)
- [On The Classification-Distortion-Perception Tradeoff](https://mlsanity.com/paper/1904.08816/) (2019)
- [Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks](https://mlsanity.com/paper/2003.07119/) (2020)
- [DeepCorrect: Correcting DNN models against Image Distortions](https://mlsanity.com/paper/1705.02406/) (2017)
- [BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration](https://mlsanity.com/paper/2011.01406/) (2020)
- [Classifying degraded images over various levels of degradation](https://mlsanity.com/paper/2006.08145/) (2020)
- [Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion](https://mlsanity.com/paper/2101.04631/) (2021)
- [SHADE: Information Based Regularization for Deep Learning](https://mlsanity.com/paper/1804.10988/) (2018)
- [AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks](https://mlsanity.com/paper/2003.03633/) (2020)

## Built on by (most cited first, 3 of 3)

- [Image Denoising with Control over Deep Network Hallucination](https://mlsanity.com/paper/2201.00429/) (2022)
- [DSR: Towards Drone Image Super-Resolution](https://mlsanity.com/paper/2208.12327/) (2022)
- [Towards Robust Drone Vision in the Wild](https://mlsanity.com/paper/2208.12655/) (2022)

## Abstract (arXiv)

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are trained on clean images and are not robust when handling noisy ones, even if a restoration preprocessing step is applied. While novel methods address this problem, they rely on modified feature extractors and thus necessitate retraining. We instead propose a method that can be applied on a pretrained classifier. Our method exploits a fidelity map estimate that is fused into the internal representations of the feature extractor, thereby guiding the attention of the network and making it more robust to noisy data. We improve the noisy-image classification (NIC) results by significantly large margins, especially at high noise levels, and come close to the fully retrained approaches. Furthermore, as proof of concept, we show that when using our oracle fidelity map we even outperform the fully retrained methods, whether trained on noisy or restored images.