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
.
Filters
Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology
[article]
2022
arXiv
pre-print
Herein, an easy-to-use benchmark is established to evaluate how deep neural networks perform on corrupted pathology images. ...
When designing a diagnostic model for a clinical application, it is crucial to guarantee the robustness of the model with respect to a wide range of image corruptions. ...
Introduction Deep neural networks (DNNs) have recently made significant advances to a variety of computer vision tasks [8, 13, 22 ]. ...
arXiv:2206.14973v1
fatcat:v7reipx7tvbq5ehrai2peq2bzi
CheXphotogenic: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays
[article]
2020
arXiv
pre-print
The use of smartphones to take photographs of chest x-rays represents an appealing solution for scaled deployment of deep learning models for chest x-ray interpretation. ...
All models were developed by different groups and submitted to the CheXpert challenge, and re-applied to smartphone photos of x-rays in the CheXphoto dataset without further tuning. ...
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. arXiv:1903.12261 [cs, stat], March 2019. Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. ...
arXiv:2011.06129v1
fatcat:sjexsybznfgptl4pylyk2p7sve
A Tour of Unsupervised Deep Learning for Medical Image Analysis
[article]
2018
arXiv
pre-print
In the last few years, both supervised and unsupervised deep learning achieved promising results in the area of medical imaging and image analysis. ...
Deep Boltzmann machine and Generative adversarial network. ...
Conflict of Interest Statement Authors declare that there is no any conflict of interest in the publication of this manuscript. ...
arXiv:1812.07715v1
fatcat:4dd75wfhvnf7db3v72575tikoi
Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
2021
Medical Image Analysis
In this paper, we evaluate the robustness of deep diagnostic models by adversarial attack. ...
Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. ...
Through the above analyses, we hope our robust-benchmark datasets can serve as the benchmark to evaluate the common perturbation robustness of deep diagnostic models in a standard manner. ...
doi:10.1016/j.media.2021.101977
pmid:33550005
fatcat:dyyp4d24hvduto4gknjufups7e
Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases
2019
Zenodo
In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. ...
Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. ...
Acknowledgements We would like to thank Frank Ihlenburg for his valuable comments and acknowledge Kaggle for availing the dataset for this work. ...
doi:10.5281/zenodo.3251086
fatcat:xrcjdgjj5rfvrn45zbxkdfxw24
Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases
2019
Zenodo
In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. ...
Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. ...
Acknowledgements We would like to thank Frank Ihlenburg for his valuable comments and acknowledge Kaggle for availing the dataset for this work. ...
doi:10.5281/zenodo.3246577
fatcat:3mgn5amws5d6fbrnd7edbhsii4
Epileptic Seizure Detection: A Deep Learning Approach
[article]
2018
arXiv
pre-print
Furthermore, our approach is shown to be robust in noisy and real-life conditions. ...
Compared to current methods that are quite sensitive to noise, the proposed method maintains its high detection performance in the presence of common EEG artifacts (muscle activities and eye-blinking) ...
In general, it is hard to obtain sufficient well-labeled data for training deep neural networks in real life applications. ...
arXiv:1803.09848v1
fatcat:uhxdxmoab5bdvcziuwuiew7hyi
A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives
[article]
2020
arXiv
pre-print
In this primer we review the budding field of motion capture with deep learning. ...
In particular, we will discuss the principles of those novel algorithms, highlight their potential as well as pitfalls for experimentalists, and provide a glimpse into the future. ...
Acknowledgments: We thank Yash Sharma for discussions around future directions in self-supervised learning, Erin Diel, Maxime Vidal, Claudio Michaelis, Thomas Biasi for comments on the manuscript. ...
arXiv:2009.00564v2
fatcat:w22iv453cbaa5fidf5hwemcxeu
Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise
[article]
2023
arXiv
pre-print
In the past years, deep learning has seen an increase in usage in the domain of histopathological applications. ...
vision benchmarks no systematic gain of the other methods can be shown. ...
Acknowledgments The research is funded by the Ministerium für Soziales und Integration, Baden Württemberg, Germany. ...
arXiv:2301.01054v2
fatcat:aibroprxvbaefpfedahx3u6z7q
Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
[article]
2020
arXiv
pre-print
Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution (OOD) inputs. ...
The most promising approaches have been predominantly focused on improving model uncertainty (e.g. deep ensembles and Bayesian neural networks) and post-processing techniques for OOD detection (e.g. ...
Benchmarking neural
network robustness to common corruptions and perturba-
tions. arXiv preprint arXiv:1903.12261, 2019b.
Hendrycks, D. and Gimpel, K. ...
arXiv:2007.05134v1
fatcat:pmnpoztl4zhqzervozxwon3twq
Certainty Pooling for Multiple Instance Learning
[article]
2020
arXiv
pre-print
Multiple Instance Learning is a form of weakly supervised learning in which the data is arranged in sets of instances called bags with one label assigned per bag. ...
We present a novel pooling operator called Certainty Pooling which incorporates the model certainty into bag predictions resulting in a more robust and explainable model. ...
In order to account for the stochastic nature of deep neural network (DNN) convergence, we repeat the experiment 20 times with different random seeds for every algorithm and training set size, and take ...
arXiv:2008.10548v1
fatcat:mpt5fcdaibagppqa6topxhs7jy
FMRI BRAIN IMAGE SEGMENTATION AND CLASSIFIATION USING BIG DATA ANALYTICS
2020
International Journal of Recent Trends in Engineering and Research
However, the amount of data is far too much for manual analysis, which has been one of the biggest obstacles in the effective use of MRI. ...
The final classification process such as deep learning approach concludes that a person is diseased or not. ...
Scalable network structures have the potential to make deep network for medical images more reusable. ...
doi:10.23883/ijrter.conf.20200315.033.snada
fatcat:rmsslknwwvaozbn6qt2xirp33a
Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data
[article]
2020
arXiv
pre-print
We close this gap by presenting a series of tests including a large variety of contemporary uncertainty estimation techniques, in order to determine whether they are able to identify out-of-distribution ...
When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's prediction on abnormal inputs. ...
Although the generalization capabilities of deep neural networks have been hailed tremendously in the past -and often rightfully so -they might produce a false sense of security in users for applications ...
arXiv:2011.03274v1
fatcat:mgukmgna6re7folppuxzg7g35u
A Robust System for Noisy Image Classification Combining Denoising Autoencoder and Convolutional Neural Network
2018
International Journal of Advanced Computer Science and Applications
The aim of this study is to develop a robust image classification system which performs well at regular to massive noise levels. ...
To solve this issue, several researches have been conducted utilizing denoising autoencoder (DAE) to restore original images from noisy images and then Convolutional Neural Network (CNN) is used for classification ...
Convolutional neural network (CNN) [19] - [22] is the most successful hierarchical deep neural network structure. ...
doi:10.14569/ijacsa.2018.090131
fatcat:ppyr5ru6mreixalyt5ejhbyeym
Assessing Uncertainty Estimation Methods for 3D Image Segmentation under Distribution Shifts
[article]
2024
arXiv
pre-print
This research contributes to enhancing the utility of deep learning in healthcare, making diagnostic predictions more robust and trustworthy. ...
This limitation hinders the expressiveness and reliability of deep learning models in health applications. ...
In contrast to BNNs, deep ensemble does not infer a distribution over the parameter of a neural network. ...
arXiv:2402.06937v1
fatcat:grrbp3js75apfg247wop4wycpy
« Previous
Showing results 1 — 15 out of 503 results