A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
A simple way to make neural networks robust against diverse image corruptions
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. ...
Here, we demonstrate that a simple but properly tuned training with additive Gaussian and Speckle noise generalizes surprisingly well to unseen corruptions, easily reaching the previous state of the art ...
Furthermore, augmentation methods have also been applied to make the models more robust against image corruptions . ...
arXiv:2001.06057v5
fatcat:iuxisdehcnfrhdtedyp6ougc34
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
While some convolutional neural networks (CNNs) have surpassed human visual abilities in object classification, they often struggle to recognize objects in images corrupted with different types of common ...
Recently, it has been shown that simulating a primary visual cortex (V1) at the front of CNNs leads to small improvements in robustness to these image perturbations. ...
“A simple way to make neural networks robust against diverse image
corruptions”. In: (2020), pp. 1–34. URL: http://arxiv.org/abs/2001.06057.
[12] Joel Dapello et al. ...
arXiv:2110.10645v2
fatcat:7zi7yskvz5dttjviyulzdbxxne
PRIME: A few primitives can boost robustness to common corruptions
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. ...
In this work, we take a step back and follow a principled approach to achieve robustness to common corruptions. ...
This work has been partially supported by the CHIST-ERA program under Swiss NSF Grant 20CH21 180444, and partially by Google via a Postdoctoral Fellowship and a GCP Research Credit Award. ...
arXiv:2112.13547v2
fatcat:hommnaqv6fdj3odve76t7vhpsy
Learning Loss for Test-Time Augmentation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Experimental results on several image classification benchmarks show that the proposed instance-aware test-time augmentation improves the model's robustness against various corruptions. ...
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. ...
Robustness in Convolutional Neural Network: A convolutional neural network is vulnerable to simple corruption. This vulnerability has been studied in several works. ...
arXiv:2010.11422v1
fatcat:kcpa7l42jvamxiiycbvvwbiove
Robustness via Cross-Domain Ensembles
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We present a method for making neural network predictions robust to shifts from the training data distribution. ...
The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. ...
This indicates that using middle domains promotes ensemble diversity in a way that makes it more challenging to create one attack that fools all paths simultaneously, hence this approach can be a promising ...
arXiv:2103.10919v2
fatcat:eegzeizkzrgxdpdjrw7qtnexeu
Diverse Gaussian Noise Consistency Regularization for Robustness and Uncertainty Calibration
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We show that this simple approach improves robustness against various unforeseen noise corruptions by 4.2-18.4\% over adversarial training and other strong diverse data augmentation baselines across several ...
In this paper, we propose a diverse Gaussian noise consistency regularization method for improving robustness of image classifiers under a variety of noise corruptions while still maintaining high clean ...
However, robustness to noise corruptions remains a challenge. ...
arXiv:2104.01231v4
fatcat:jlgknfdfkfhyzf7uab5z2bhvri
Out of Distribution Detection and Adversarial Attacks on Deep Neural Networks for Robust Medical Image Analysis
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For instance, the state-of-the-art Convolutional Neural Networks (CNNs) fail to detect adversarial samples or samples drawn statistically far away from the training distribution. ...
Deep learning models have become a popular choice for medical image analysis. ...
Liang et al. (2018) proposed ODIN (Out-of-DIstribution detector for Neural networks) which is a simple and effective method for detecting OOD images in neural networks. ...
arXiv:2107.04882v1
fatcat:4uf4gxmmtzf5rg7jrj2gfelnxa
Streaming Networks: Increase Noise Robustness and Filter Diversity via Hard-wired and Input-induced Sparsity
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We focus on the problem of robust recognition accuracy of noise-corrupted images. We introduce a novel network architecture called Streaming Networks. ...
Finally, to illustrate increase in filter diversity we illustrate that a distribution of filter weights of the first conv layer gradually approaches uniform distribution as the degree of hard-wired and ...
The gist of sparsity control for network training is to make neurons to be activated with a certain frequency. Thus, providing a diversity of paths within a neural network. ...
arXiv:2004.03334v2
fatcat:rrn6wnghafbubdcygqet55ngai
AugMax: Adversarial Composition of Random Augmentations for Robust Training
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2110.13771v2 fatcat:k6wk56bu3fghxj3xpxtmkdn2yeOther Versions
Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). ...
Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness. ...
[12] , pre-training [13] [14] [15] [16] , and robust network structures [17] [18] [19] , to name a few. ...
arXiv:2110.13771v3
fatcat:e7ulbwviprhyzpoyt72m2tlzem
Training Robust Deep Neural Networks via Adversarial Noise Propagation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Deep neural networks have been found vulnerable to noises like adversarial examples and corruption in practice. ...
Motivated by the fact that hidden layers play a very important role in maintaining a robust model, this paper comes up with a simple yet powerful training algorithm named Adversarial Noise Propagation ...
Goodfellow, Shlens, and Szegedy proposes FGSM as a simple way to generate adversarial examples. ...
arXiv:1909.09034v1
fatcat:lgtngb3vjbhcvdj75qe5in4obm
Pixel to Binary Embedding Towards Robustness for CNNs
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
There are several problems with the robustness of Convolutional Neural Networks (CNNs). ...
P2BE outperforms other binary embedding methods in robustness against adversarial perturbations and visual corruptions that are not shown during training. ...
It implies that designing a sophisticated input space may be a promising way to improve robustness against never-seen visual corruptions. ...
arXiv:2206.05898v1
fatcat:we6si3pagbhe5pfokjeg2l7sni
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. ...
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. ...
A popular way to make networks robust to p adversarial examples is with adversarial training (Madry et al., 2018) , which we use in this paper. ...
arXiv:1912.02781v2
fatcat:s5a7xpmjwjayphmrzqexkxzyni
VCNet: A Robust Approach to Blind Image Inpainting
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we relax the assumption by defining a new blind inpainting setting, making training a blind inpainting neural system robust against various unknown missing region patterns. ...
Specifically, we propose a two-stage visual consistency network (VCN), meant to estimate where to fill (via masks) and generate what to fill. ...
Setting N as a constant value or certain kind of noise makes it and M easy to be distinguished by a deep neural net or even a simple linear classifier from a natural image patch. ...
arXiv:2003.06816v1
fatcat:2755gwvvizfuhjtgkkkx4fijtu
Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We then use this criteria to evaluate a cheap data augmentation technique as a reliable way for demonstrating the natural robustness of neural ODEs against simulated image corruptions across multiple datasets ...
We propose a novel and simple accuracy metric which can be used to evaluate intrinsic robustness and to validate dataset corruption simulators. ...
Acknowledgements The authors thank to each other for the fruitful conversations that led to the project for which this paper consists on a preliminary work. ...
arXiv:2206.08237v1
fatcat:mgdnaltehfferjzgfazuxuluby
On 1/n neural representation and robustness
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our results show that imposing the experimentally observed structure on artificial neural networks makes them more robust to adversarial attacks. ...
A pressing question in these areas is understanding how the structure of the representation used by neural networks affects both their generalization, and robustness to perturbations. ...
A simple way to enforce a power-law decay without changing its architecture is to use the finite-dimensional embedding and directly regularize the eigenspectrum of the neural representation used at layer ...
arXiv:2012.04729v1
fatcat:64n46oqxdzg63ouzhkmiscdx2u
« Previous
Showing results 1 — 15 out of 4,434 results