Filters








60,276 Hits in 3.9 sec

Uncertainty-Aware Deep Classifiers using Generative Models [article]

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
2020 arXiv   pre-print
Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution  ...  These approaches use an auxiliary data set during training to represent out-of-distribution samples.  ...  Then, it trains a classifier using both training and the generated samples.  ... 
arXiv:2006.04183v1 fatcat:bjtwcwpxf5bw3bni2d4tpvpn6m

Uncertainty-Aware Deep Classifiers Using Generative Models

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution  ...  These approaches use an auxiliary data set during training to represent out-of-distribution samples.  ...  Then, it trains a classifier using both training and the generated samples.  ... 
doi:10.1609/aaai.v34i04.6015 fatcat:v5lveat4e5fxte3w4pvymkpmzi

Uncertainty aware and explainable diagnosis of retinal disease [article]

Amitojdeep Singh, Sourya Sengupta, Mohammed Abdul Rasheed, Varadharajan Jayakumar, Vasudevan Lakshminarayanan
2021 arXiv   pre-print
Monte Carlo (MC) dropout is used at the test time to generate a distribution of parameters and the predictions approximate the predictive posterior of a Bayesian model.  ...  Explainability methods show the features that a system used to make prediction while uncertainty awareness is the ability of a system to highlight when it is not sure about the decision.  ...  This study presented an uncertainty aware and explainable deep learning model for retinal diagnosis.  ... 
arXiv:2101.12041v1 fatcat:ejr43efr4zbexf2srklyac3cou

An Uncertainty-Aware Transfer Learning-Based Framework for COVID-19 Diagnosis

Afshar Shamsi, Hamzeh Asgharnezhad, Shirin Shamsi Jokandan, Abbas Khosravi, Parham M. Kebria, Darius Nahavandi, Saeid Nahavandi, Dipti Srinivasan
2021 IEEE Transactions on Neural Networks and Learning Systems  
Motivated by these shortcomings, this article proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images.  ...  We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem).  ...  We then develop an ensemble of neural network models trained using different deep features to generate predictive uncertainty estimates.  ... 
doi:10.1109/tnnls.2021.3054306 fatcat:xuywwnjqdrcevhkg3o2f2z6zwq

Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection [article]

Minjie Cai, Minyi Luo, Xionghu Zhong, Hao Chen
2021 arXiv   pre-print
We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation  ...  To this end, we compose a Bayesian CNN-based framework for uncertainty estimation in object detection, and propose an algorithm for generation of uncertainty-aware pseudo-labels.  ...  Uncertainty in deep neural networks The estimation of model uncertainty [34] is critical for generalization and safety of deep neural networks (DNNs) and various approaches for quantifying uncertainty  ... 
arXiv:2108.12612v1 fatcat:3nbokgoi5bge7k5uvriko73guq

MCUa: Multi-level Context and Uncertainty aware Dynamic Deep Ensemble for Breast Cancer Histology Image Classification [article]

Zakaria Senousy, Mohammed M. Abdelsamea, Mohamed Medhat Gaber, Moloud Abdar, U Rajendra Acharya, Abbas Khosravi, Saeid Nahavandi
2021 IEEE Transactions on Biomedical Engineering   pre-print
In this paper, we propose a novel CNN, called Multi-level Context and Uncertainty aware (MCUa) dynamic deep learning ensemble model.MCUamodel consists of several multi-level context-aware models to learn  ...  It exploits the high sensitivity to the multi-level contextual information using an uncertainty quantification component to accomplish a novel dynamic ensemble model.MCUamodelhas achieved a high accuracy  ...  MCUa MODEL In this section, we describe our proposed Multi-level Context and uncertainty aware (MCUa) dynamic deep learning ensemble model in details.  ... 
doi:10.1109/tbme.2021.3107446 pmid:34460359 arXiv:2108.10709v1 fatcat:ww2gff7svzhxlnc3mfguf733ai

An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis [article]

Afshar Shamsi Jokandan, Hamzeh Asgharnezhad, Shirin Shamsi Jokandan, Abbas Khosravi, Parham M.Kebria, Darius Nahavandi, Saeid Nahavandi, Dipti Srinivasan
2020 arXiv   pre-print
Motivated by these shortcomings, this paper proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images.  ...  We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem).  ...  We then develop an ensemble of neural network models trained using different deep features to generate predictive uncertainty estimates.  ... 
arXiv:2007.14846v1 fatcat:tsvx4hpgwfalfmtgnlh5qdybsi

Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration [article]

Christian Tomani, Florian Buettner
2021 arXiv   pre-print
That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift.  ...  approaches and evidential deep learning.  ...  to be uncertainty-aware.  ... 
arXiv:2012.10923v2 fatcat:gsjqr5exqbffvigwy7jzowlwcm

Uncertainty-Aware Training for Cardiac Resynchronisation Therapy Response Prediction [article]

Tareen Dawood, Chen Chen, Robin Andlauer, Baldeep S. Sidhu, Bram Ruijsink, Justin Gould, Bradley Porter, Mark Elliott, Vishal Mehta, C. Aldo Rinaldi, Esther Puyol-Antón, Reza Razavi (+1 others)
2021 arXiv   pre-print
(ii) propose and perform a preliminary investigation of an uncertainty-aware loss function that can be used to retrain an existing DL image-based classification model to encourage confidence in correct  ...  Evaluation of predictive deep learning (DL) models beyond conventional performance metrics has become increasingly important for applications in sensitive environments like healthcare.  ...  This research has been conducted using the UK Biobank Resource under Application Number 17806.The work was also supported by the EPSRC through the SmartHeart Programme Grant(EP/P001009/1).  ... 
arXiv:2109.10641v1 fatcat:gjbbgbh3dnh5lorp75q2g5tmma

Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning [article]

Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, T. Yong-Jin Han
2020 arXiv   pre-print
Several uncertainty-aware models, such as Bayesian Neural Network (BNNs) and Deep Ensembles have been proposed in the literature for quantifying predictive uncertainty.  ...  Our approach enables deep kNN classifier to accurately quantify underlying uncertainties in its prediction.  ...  (a) All models correctly classify in-distribution data from [6] , (b) Uncertainty-aware models (BNN, and our model PNCA) perform better than DNN when test data is from a different source [4] , (c) As  ... 
arXiv:2007.10800v1 fatcat:nownqtyilvd27dcgr2jguq26am

Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection [article]

Biraja Ghoshal, Allan Tucker
2020 arXiv   pre-print
We believe that the availability of uncertainty-aware deep learning solution will enable a wider adoption of Artificial Intelligence (AI) in a clinical setting.  ...  team using publicly available COVID-19 chest X-ray dataset and show that the uncertainty in prediction is highly correlates with accuracy of prediction.  ...  Conclusion and Future work In this work, Bayesian Deep Learning classifier has been trained using transfer learning method on COVID-19 X-Ray images to estimate model uncertainty.  ... 
arXiv:2003.10769v2 fatcat:7xuiad3rxbgjjcppzu3jhlinsa

IDK Cascades: Fast Deep Learning by Learning not to Overthink [article]

Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez
2018 arXiv   pre-print
We conjecture that fora majority of real-world inputs, the recent advances in deep learning have created models that effectively "overthink" on simple inputs.  ...  We introduce the "I Don't Know"(IDK) prediction cascades framework, a general framework to systematically compose a set of pre-trained models to accelerate inference without a loss in prediction accuracy  ...  Entropy+Cost: Entropy based IDK classifier with cost-aware objective. Oracle: Using ground truth correctness labels as IDK classifier.  ... 
arXiv:1706.00885v4 fatcat:d34s54tttred7ps4wtwhctgsx4

Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprints [article]

Indu Joshi and Ayush Utkarsh and Riya Kothari and Vinod K Kurmi and Antitza Dantcheva and Sumantra Dutta Roy and Prem Kumar Kalra
2021 arXiv   pre-print
Towards this, we propose a data uncertainty-based framework which enables the state-of-the-art fingerprint preprocessing models to quantify noise present in the input image and identify fingerprint regions  ...  Quantification of noise helps the model two folds: firstly, it makes the objective function adaptive to the noise in a particular input fingerprint and consequently, helps to achieve robust performance  ...  ACKNOWLEDGMENT Authors thank the HPC facility of Inria Sophia Antipolis and IIT Delhi for computational resources used in this research.  ... 
arXiv:2107.01248v1 fatcat:b6qedhhxm5gfhkj6ky4kqavtoe

Uncertainty-Aware Few-Shot Image Classification [article]

Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Shih-Fu Chang
2021 arXiv   pre-print
In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization.  ...  Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization.  ...  Uncertainty in Deep Learning For deep neural network, there are two main types of uncertainty that can be modeled: aleatoric uncertainty, and epistemic uncertainty (Kendall and Gal 2017; Gal 2016; Kendall  ... 
arXiv:2010.04525v2 fatcat:fjfzjvrrurf3xfp2mz4czsmlwq

Confidence Aware Neural Networks for Skin Cancer Detection [article]

Donya Khaledyan, AmirReza Tajally, Ali Sarkhosh, Afshar Shamsi, Hamzeh Asgharnezhad, Abbas Khosravi, Saeid Nahavandi
2021 arXiv   pre-print
Deep learning (DL) models have received particular attention in medical imaging due to their promising pattern recognition capabilities.  ...  It also comprehensively evaluates and compares performance of these DNNs using novel uncertainty-related metrics.  ...  of 0 .Figure ( 7 ) 07 25 is used for model development using three uncertainty quantification methods.  ... 
arXiv:2107.09118v2 fatcat:yxwowuasivewxkdxp5uo3oexwq
« Previous Showing results 1 — 15 out of 60,276 results