Paper Group ANR 750
FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI. A Strategy for Expert Recommendation From Open Data Available on the Lattes Platform. A Convolutional Network for Sleep Stages Classification. Neuralogram: A Deep Neural Network Based Representation for Audio Signals. Quadruply Stochastic Gr …
FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI
| Title | FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI |
| Authors | Santiago Estrada, Ran Lu, Sailesh Conjeti, Ximena Orozco-Ruiz, Joana Panos-Willuhn, Monique M. B Breteler, Martin Reuter |
| Abstract | Purpose: Development of a fast and fully automated deep learning pipeline (FatSegNet) to accurately identify, segment, and quantify abdominal adipose tissue on Dixon MRI from the Rhineland Study - a large prospective population-based study. Method: FatSegNet is composed of three stages: (i) consistent localization of the abdominal region using two 2D-Competitive Dense Fully Convolutional Networks (CDFNet), (ii) segmentation of adipose tissue on three views by independent CDFNets, and (iii) view aggregation. FatSegNet is trained with 33 manually annotated subjects, and validated by: 1) comparison of segmentation accuracy against a testingset covering a wide range of body mass index (BMI), 2) test-retest reliability, and 3) robustness in a large cohort study. Results: The CDFNet demonstrates increased robustness compared to traditional deep learning networks. FatSegNet dice score outperforms manual raters on the abdominal visceral adipose tissue (VAT, 0.828 vs. 0.788), and produces comparable results on subcutaneous adipose tissue (SAT, 0.973 vs. 0.982). The pipeline has very small test-retest absolute percentage difference and excellent agreement between scan sessions (VAT: APD = 2.957%, ICC=0.998 and SAT: APD= 3.254%, ICC=0.996). Conclusion: FatSegNet can reliably analyze a 3D Dixon MRI in1 min. It generalizes well to different body shapes, sensitively replicates known VAT and SAT volume effects in a large cohort study, and permits localized analysis of fat compartments. |
| Tasks | |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1904.02082v2 |
| https://arxiv.org/pdf/1904.02082v2.pdf | |
| PWC | https://paperswithcode.com/paper/fatsegnet-a-fully-automated-deep-learning |
| Repo | |
| Framework | |
A Strategy for Expert Recommendation From Open Data Available on the Lattes Platform
| Title | A Strategy for Expert Recommendation From Open Data Available on the Lattes Platform |
| Authors | Sérgio José de Sousa, Thiago Magela Rodrigues Dias, Adilson Luiz Pinto |
| Abstract | With the increasing volume of data and users of curriculum systems, the difficulty of finding specialists is increasing.This work proposes an open data extraction methodology of the Lattes Platform curricula, a treatment for this data and investigates a Recommendation Agent approach based on deep neural networks with autoencoder. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06437v1 |
| https://arxiv.org/pdf/1906.06437v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-strategy-for-expert-recommendation-from |
| Repo | |
| Framework | |
A Convolutional Network for Sleep Stages Classification
| Title | A Convolutional Network for Sleep Stages Classification |
| Authors | Isaac Fernández-Varela, Elena Hernández-Pereira, Diego Alvarez-Estevez, Vicente Moret-Bonillo |
| Abstract | Sleep stages classification is a crucial task in the context of sleep studies. It involves the simultaneous analysis of multiple signals recorded during sleep. However, it is complex and tedious, and even the trained expert can spend several hours scoring a single night recording. Multiple automatic methods have tried to solve these problems in the past, most of them by classifying a feature vector that is engineered for a specific dataset. In this work, we avoid this bias using a deep learning model that learns relevant features without human intervention. Particularly, we propose an ensemble of 5 convolutional networks that achieves a kappa index of 0.83 when classifying a dataset of 500 sleep recordings. |
| Tasks | |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05748v1 |
| http://arxiv.org/pdf/1902.05748v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-convolutional-network-for-sleep-stages |
| Repo | |
| Framework | |
Neuralogram: A Deep Neural Network Based Representation for Audio Signals
| Title | Neuralogram: A Deep Neural Network Based Representation for Audio Signals |
| Authors | Prateek Verma, Chris Chafe, Jonathan Berger |
| Abstract | We propose the Neuralogram – a deep neural network based representation for understanding audio signals which, as the name suggests, transforms an audio signal to a dense, compact representation based upon embeddings learned via a neural architecture. Through a series of probing signals, we show how our representation can encapsulate pitch, timbre and rhythm-based information, and other attributes. This representation suggests a method for revealing meaningful relationships in arbitrarily long audio signals that are not readily represented by existing algorithms. This has the potential for numerous applications in audio understanding, music recommendation, meta-data extraction to name a few. |
| Tasks | |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05073v1 |
| http://arxiv.org/pdf/1904.05073v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuralogram-a-deep-neural-network-based |
| Repo | |
| Framework | |
Quadruply Stochastic Gradients for Large Scale Nonlinear Semi-Supervised AUC Optimization
| Title | Quadruply Stochastic Gradients for Large Scale Nonlinear Semi-Supervised AUC Optimization |
| Authors | Wanli Shi, Bin Gu, Xiang Li, Xiang Geng, Heng Huang |
| Abstract | Semi-supervised learning is pervasive in real-world applications, where only a few labeled data are available and large amounts of instances remain unlabeled. Since AUC is an important model evaluation metric in classification, directly optimizing AUC in semi-supervised learning scenario has drawn much attention in the machine learning community. Recently, it has been shown that one could find an unbiased solution for the semi-supervised AUC maximization problem without knowing the class prior distribution. However, this method is hardly scalable for nonlinear classification problems with kernels. To address this problem, in this paper, we propose a novel scalable quadruply stochastic gradient algorithm (QSG-S2AUC) for nonlinear semi-supervised AUC optimization. In each iteration of the stochastic optimization process, our method randomly samples a positive instance, a negative instance, an unlabeled instance and their random features to compute the gradient and then update the model by using this quadruply stochastic gradient to approach the optimal solution. More importantly, we prove that QSG-S2AUC can converge to the optimal solution in O(1/t), where t is the iteration number. Extensive experimental results on a variety of benchmark datasets show that QSG-S2AUC is far more efficient than the existing state-of-the-art algorithms for semi-supervised AUC maximization while retaining the similar generalization performance. |
| Tasks | Stochastic Optimization |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12416v1 |
| https://arxiv.org/pdf/1907.12416v1.pdf | |
| PWC | https://paperswithcode.com/paper/quadruply-stochastic-gradients-for-large |
| Repo | |
| Framework | |
NaïveRole: Author-Contribution Extraction and Parsing from Biomedical Manuscripts
| Title | NaïveRole: Author-Contribution Extraction and Parsing from Biomedical Manuscripts |
| Authors | Dominika Tkaczyk, Andrew Collins, Joeran Beel |
| Abstract | Information about the contributions of individual authors to scientific publications is important for assessing authors’ achievements. Some biomedical publications have a short section that describes authors’ roles and contributions. It is usually written in natural language and hence author contributions cannot be trivially extracted in a machine-readable format. In this paper, we present 1) A statistical analysis of roles in author contributions sections, and 2) Na"iveRole, a novel approach to extract structured authors’ roles from author contribution sections. For the first part, we used co-clustering techniques, as well as Open Information Extraction, to semi-automatically discover the popular roles within a corpus of 2,000 contributions sections from PubMed Central. The discovered roles were used to automatically build a training set for Na"iveRole, our role extractor approach, based on Na"ive Bayes. Na"iveRole extracts roles with a micro-averaged precision of 0.68, recall of 0.48 and F1 of 0.57. It is, to the best of our knowledge, the first attempt to automatically extract author roles from research papers. This paper is an extended version of a previous poster published at JCDL 2018. |
| Tasks | Open Information Extraction |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.10170v1 |
| https://arxiv.org/pdf/1912.10170v1.pdf | |
| PWC | https://paperswithcode.com/paper/naiverole-author-contribution-extraction-and |
| Repo | |
| Framework | |
Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems
| Title | Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems |
| Authors | Sarik Ghazarian, Ralph Weischedel, Aram Galstyan, Nanyun Peng |
| Abstract | User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores; (2) conversation-level engagement scores can be predicted from properly aggregated utterance-level engagement scores. Furthermore, we show that the utterance-level engagement scores can be learned from data. These scores can improve automatic evaluation metrics for open-domain dialogue systems, as shown by correlation with human judgements. This suggests that predictive engagement can be used as a real-time feedback for training better dialogue models. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01456v2 |
| https://arxiv.org/pdf/1911.01456v2.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-engagement-an-efficient-metric-for |
| Repo | |
| Framework | |
Usage-Based Vehicle Insurance: Driving Style Factors of Accident Probability and Severity
| Title | Usage-Based Vehicle Insurance: Driving Style Factors of Accident Probability and Severity |
| Authors | Konstantin Korishchenko, Ivan Stankevich, Nikolay Pilnik, Daria Petrova |
| Abstract | The paper introduces an approach to telematics devices data application in automotive insurance. We conduct a comparative analysis of different types of devices that collect information on vehicle utilization and driving style of its driver, describe advantages and disadvantages of these devices and indicate the most efficient from the insurer point of view. The possible formats of telematics data are described and methods of their processing to a format convenient for modelling are proposed. We also introduce an approach to classify the accidents strength. Using all the available information, we estimate accident probability models for different types of accidents and identify an optimal set of factors for each of the models. We assess the quality of resulting models using both in-sample and out-of-sample estimates. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00460v2 |
| https://arxiv.org/pdf/1910.00460v2.pdf | |
| PWC | https://paperswithcode.com/paper/usage-based-vehicle-insurance-driving-style |
| Repo | |
| Framework | |
Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation
| Title | Concentration bounds for linear Monge mapping estimation and optimal transport domain adaptation |
| Authors | Rémi Flamary, Karim Lounici, André Ferrari |
| Abstract | This article investigates the quality of the estimator of the linear Monge mapping between distributions. We provide the first concentration result on the linear mapping operator and prove a sample complexity of $n^{-1/2}$ when using empirical estimates of first and second order moments. This result is then used to derive a generalization bound for domain adaptation with optimal transport. As a consequence, this method approaches the performance of theoretical Bayes predictor under mild conditions on the covariance structure of the problem. We also discuss the computational complexity of the linear mapping estimation and show that when the source and target are stationary the mapping is a convolution that can be estimated very efficiently using fast Fourier transforms. Numerical experiments reproduce the behavior of the proven bounds on simulated and real data for mapping estimation and domain adaptation on images. |
| Tasks | Domain Adaptation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10155v1 |
| https://arxiv.org/pdf/1905.10155v1.pdf | |
| PWC | https://paperswithcode.com/paper/concentration-bounds-for-linear-monge-mapping |
| Repo | |
| Framework | |
Event extraction based on open information extraction and ontology
| Title | Event extraction based on open information extraction and ontology |
| Authors | Sihem Sahnoun |
| Abstract | The work presented in this master thesis consists of extracting a set of events from texts written in natural language. For this purpose, we have based ourselves on the basic notions of the information extraction as well as the open information extraction. First, we applied an open information extraction(OIE) system for the relationship extraction, to highlight the importance of OIEs in event extraction, and we used the ontology to the event modeling. We tested the results of our approach with test metrics. As a result, the two-level event extraction approach has shown good performance results but requires a lot of expert intervention in the construction of classifiers and this will take time. In this context we have proposed an approach that reduces the expert intervention in the relation extraction, the recognition of entities and the reasoning which are automatic and based on techniques of adaptation and correspondence. Finally, to prove the relevance of the extracted results, we conducted a set of experiments using different test metrics as well as a comparative study. |
| Tasks | Open Information Extraction, Relation Extraction |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1907.00692v1 |
| https://arxiv.org/pdf/1907.00692v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-extraction-based-on-open-information |
| Repo | |
| Framework | |
Particle Swarm Optimization for Great Enhancement in Semi-Supervised Retinal Vessel Segmentation with Generative Adversarial Networks
| Title | Particle Swarm Optimization for Great Enhancement in Semi-Supervised Retinal Vessel Segmentation with Generative Adversarial Networks |
| Authors | Qiang Huo |
| Abstract | Retinal vessel segmentation based on deep learning requires a lot of manual labeled data. That is time-consuming, laborious and professional. What is worse, the acquisition of abundant fundus images is difficult. These problems are more serious due to the presence of abnormalities, varying size and shape of the vessels, non-uniform illumination and anatomical changes. In this paper, we propose a data-efficient semi-supervised learning framework, which effectively combines the existing deep learning network with GAN and self-training ideas. In view of the difficulty of tuning hyper-parameters of semi-supervised learning, we propose a method for hyper-parameters selection based on particle swarm optimization algorithm. To the best of our knowledge, this work is the first demonstration that combines intelligent optimization with semi-supervised learning for achieving the best performance. Under the collaboration of adversarial learning, self-training and PSO to select optimal hyper-parameters, we obtain the performance of retinal vessel segmentation approximate to or even better than representative supervised learning using only one tenth of the labeled data from DRIVE. |
| Tasks | Retinal Vessel Segmentation |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.07084v2 |
| https://arxiv.org/pdf/1906.07084v2.pdf | |
| PWC | https://paperswithcode.com/paper/particle-swarm-optimization-for-great |
| Repo | |
| Framework | |
GAN Augmented Text Anomaly Detection with Sequences of Deep Statistics
| Title | GAN Augmented Text Anomaly Detection with Sequences of Deep Statistics |
| Authors | Mariem Ben Fadhel, Kofi Nyarko |
| Abstract | Anomaly detection is the process of finding data points that deviate from a baseline. In a real-life setting, anomalies are usually unknown or extremely rare. Moreover, the detection must be accomplished in a timely manner or the risk of corrupting the system might grow exponentially. In this work, we propose a two level framework for detecting anomalies in sequences of discrete elements. First, we assess whether we can obtain enough information from the statistics collected from the discriminator’s layers to discriminate between out of distribution and in distribution samples. We then build an unsupervised anomaly detection module based on these statistics. As to augment the data and keep track of classes of known data, we lean toward a semi-supervised adversarial learning applied to discrete elements. |
| Tasks | Anomaly Detection, Unsupervised Anomaly Detection |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.11094v1 |
| http://arxiv.org/pdf/1904.11094v1.pdf | |
| PWC | https://paperswithcode.com/paper/gan-augmented-text-anomaly-detection-with |
| Repo | |
| Framework | |
Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
| Title | Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks |
| Authors | Jirong Yi, Hui Xie, Leixin Zhou, Xiaodong Wu, Weiyu Xu, Raghuraman Mudumbai |
| Abstract | Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations. Drawing on ideas from information and coding theory, we propose a general class of defenses for detecting classifier errors caused by abnormally small input perturbations. We further show theoretical guarantees for the performance of this detection method. We present experimental results with (a) a voice recognition system, and (b) a digit recognition system using the MNIST database, to demonstrate the effectiveness of the proposed defense methods. The ideas in this paper are motivated by a simple analogy between AI classifiers and the standard Shannon model of a communication system. |
| Tasks | |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.11381v1 |
| https://arxiv.org/pdf/1905.11381v1.pdf | |
| PWC | https://paperswithcode.com/paper/190511381 |
| Repo | |
| Framework | |
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
| Title | Robust Subspace Recovery Layer for Unsupervised Anomaly Detection |
| Authors | Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman |
| Abstract | We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace. It is used within an autoencoder. The encoder maps the data into a latent space, from which the RSR layer extracts the subspace. The decoder then smoothly maps back the underlying subspace to a “manifold” close to the original inliers. Inliers and outliers are distinguished according to the distances between the original and mapped positions (small for inliers and large for outliers). Extensive numerical experiments with both image and document datasets demonstrate state-of-the-art precision and recall. |
| Tasks | Anomaly Detection, Unsupervised Anomaly Detection |
| Published | 2019-03-30 |
| URL | https://arxiv.org/abs/1904.00152v2 |
| https://arxiv.org/pdf/1904.00152v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-subspace-recovery-layer-for |
| Repo | |
| Framework | |
Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech
| Title | Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech |
| Authors | Tobias Menne, Ilya Sklyar, Ralf Schlüter, Hermann Ney |
| Abstract | Significant performance degradation of automatic speech recognition (ASR) systems is observed when the audio signal contains cross-talk. One of the recently proposed approaches to solve the problem of multi-speaker ASR is the deep clustering (DPCL) approach. Combining DPCL with a state-of-the-art hybrid acoustic model, we obtain a word error rate (WER) of 16.5 % on the commonly used wsj0-2mix dataset, which is the best performance reported thus far to the best of our knowledge. The wsj0-2mix dataset contains simulated cross-talk where the speech of multiple speakers overlaps for almost the entire utterance. In a more realistic ASR scenario the audio signal contains significant portions of single-speaker speech and only part of the signal contains speech of multiple competing speakers. This paper investigates obstacles of applying DPCL as a preprocessing method for ASR in such a scenario of sparsely overlapping speech. To this end we present a data simulation approach, closely related to the wsj0-2mix dataset, generating sparsely overlapping speech datasets of arbitrary overlap ratio. The analysis of applying DPCL to sparsely overlapping speech is an important interim step between the fully overlapping datasets like wsj0-2mix and more realistic ASR datasets, such as CHiME-5 or AMI. |
| Tasks | Speech Recognition |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03500v2 |
| https://arxiv.org/pdf/1905.03500v2.pdf | |
| PWC | https://paperswithcode.com/paper/190503500 |
| Repo | |
| Framework | |
