January 27, 2020

3085 words 15 mins read

Paper Group ANR 1180

BGrowth: an efficient approach for the segmentation of vertebral compression fractures in magnetic resonance imaging. Online Deep Learning for Improved Trajectory Tracking of Unmanned Aerial Vehicles Using Expert Knowledge. High-Dimensional Optimization in Adaptive Random Subspaces. End-to-End Jet Classification of Quarks and Gluons with the CMS Op …

BGrowth: an efficient approach for the segmentation of vertebral compression fractures in magnetic resonance imaging


Title	BGrowth: an efficient approach for the segmentation of vertebral compression fractures in magnetic resonance imaging
Authors	Jonathan S. Ramos, Carolina Y. V. Watanabe, Marcello H. Nogueira-Barbosa, Agma J. M. Traina
Abstract	Segmentation of medical images is a critical issue: several process of analysis and classification rely on this segmentation. With the growing number of people presenting back pain and problems related to it, the automatic or semi-automatic segmentation of fractured vertebral bodies became a challenging task. In general, those fractures present several regions with non-homogeneous intensities and the dark regions are quite similar to the structures nearby. Aimed at overriding this challenge, in this paper we present a semi-automatic segmentation method, called Balanced Growth (BGrowth). The experimental results on a dataset with 102 crushed and 89 normal vertebrae show that our approach significantly outperforms well-known methods from the literature. We have achieved an accuracy up to 95% while keeping acceptable processing time performance, that is equivalent to the state-of-the-artmethods. Moreover, BGrowth presents the best results even with a rough (sloppy) manual annotation (seed points).
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08620v2
PDF	https://arxiv.org/pdf/1906.08620v2.pdf
PWC	https://paperswithcode.com/paper/bgrowth-an-efficient-approach-for-the
Repo
Framework

Online Deep Learning for Improved Trajectory Tracking of Unmanned Aerial Vehicles Using Expert Knowledge


Title	Online Deep Learning for Improved Trajectory Tracking of Unmanned Aerial Vehicles Using Expert Knowledge
Authors	Andriy Sarabakha, Erdal Kayacan
Abstract	This work presents an online learning-based control method for improved trajectory tracking of unmanned aerial vehicles using both deep learning and expert knowledge. The proposed method does not require the exact model of the system to be controlled, and it is robust against variations in system dynamics as well as operational uncertainties. The learning is divided into two phases: offline (pre-)training and online (post-)training. In the former, a conventional controller performs a set of trajectories and, based on the input-output dataset, the deep neural network (DNN)-based controller is trained. In the latter, the trained DNN, which mimics the conventional controller, controls the system. Unlike the existing papers in the literature, the network is still being trained for different sets of trajectories which are not used in the training phase of DNN. Thanks to the rule-base, which contains the expert knowledge, the proposed framework learns the system dynamics and operational uncertainties in real-time. The experimental results show that the proposed online learning-based approach gives better trajectory tracking performance when compared to the only offline trained network.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10796v1
PDF	https://arxiv.org/pdf/1905.10796v1.pdf
PWC	https://paperswithcode.com/paper/online-deep-learning-for-improved-trajectory
Repo
Framework

High-Dimensional Optimization in Adaptive Random Subspaces


Title	High-Dimensional Optimization in Adaptive Random Subspaces
Authors	Jonathan Lacotte, Mert Pilanci, Marco Pavone
Abstract	We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly outperforms the oblivious sampling method, which is the common choice in the recent literature. The adaptive subspace can be efficiently generated by a correlated random matrix ensemble whose statistics mimic the input data. We prove that the improvement in the relative error of the solution can be tightly characterized in terms of the spectrum of the data matrix, and provide probabilistic upper-bounds. We then illustrate the consequences of our theory with data matrices of different spectral decay. Extensive experimental results show that the proposed approach offers significant speed ups in machine learning problems including logistic regression, kernel classification with random convolution layers and shallow neural networks with rectified linear units. Our analysis is based on convex analysis and Fenchel duality, and establishes connections to sketching and randomized matrix decomposition.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11809v4
PDF	https://arxiv.org/pdf/1906.11809v4.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-optimization-in-adaptive
Repo
Framework

End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data


Title	End-to-End Jet Classification of Quarks and Gluons with the CMS Open Data
Authors	Michael Andrews, John Alison, Sitong An, Patrick Bryant, Bjorn Burkle, Sergei Gleyzer, Meenakshi Narain, Manfred Paulini, Barnabas Poczos, Emanuele Usai
Abstract	We describe the construction of end-to-end jet image classifiers based on simulated low-level detector data to discriminate quark- vs. gluon-initiated jets with high-fidelity simulated CMS Open Data. We highlight the importance of precise spatial information and demonstrate competitive performance to existing state-of-the-art jet classifiers. We further generalize the end-to-end approach to event-level classification of quark vs. gluon di-jet QCD events. We compare the fully end-to-end approach to using hand-engineered features and demonstrate that the end-to-end algorithm is robust against the effects of underlying event and pile-up.
Tasks
Published	2019-02-21
URL	http://arxiv.org/abs/1902.08276v1
PDF	http://arxiv.org/pdf/1902.08276v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-jet-classification-of-quarks-and
Repo
Framework

A Comparative Study of Feature Selection Methods for Dialectal Arabic Sentiment Classification Using Support Vector Machine


Title	A Comparative Study of Feature Selection Methods for Dialectal Arabic Sentiment Classification Using Support Vector Machine
Authors	Omar Al-Harbi
Abstract	Unlike other languages, the Arabic language has a morphological complexity which makes the Arabic sentiment analysis is a challenging task. Moreover, the presence of the dialects in the Arabic texts have made the sentiment analysis task is more challenging, due to the absence of specific rules that govern the writing or speaking system. Generally, one of the problems of sentiment analysis is the high dimensionality of the feature vector. To resolve this problem, many feature selection methods have been proposed. In contrast to the dialectal Arabic language, these selection methods have been investigated widely for the English language. This work investigated the effect of feature selection methods and their combinations on dialectal Arabic sentiment classification. The feature selection methods are Information Gain (IG), Correlation, Support Vector Machine (SVM), Gini Index (GI), and Chi-Square. A number of experiments were carried out on dialectical Jordanian reviews with using an SVM classifier. Furthermore, the effect of different term weighting schemes, stemmers, stop words removal, and feature models on the performance were investigated. The experimental results showed that the best performance of the SVM classifier was obtained after the SVM and correlation feature selection methods had been combined with the uni-gram model.
Tasks	Arabic Sentiment Analysis, Feature Selection, Sentiment Analysis
Published	2019-02-17
URL	http://arxiv.org/abs/1902.06242v1
PDF	http://arxiv.org/pdf/1902.06242v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-of-feature-selection
Repo
Framework

Filtering Point Targets via Online Learning of Motion Models


Title	Filtering Point Targets via Online Learning of Motion Models
Authors	Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez
Abstract	Filtering point targets in highly cluttered and noisy data frames can be very challenging, especially for complex target motions. Fixed motion models can fail to provide accurate predictions, while learning based algorithm can be difficult to design (due to the variable number of targets), slow to train and dependent on separate train/test steps. To address these issues, this paper proposes a multi-target filtering algorithm which learns the motion models, on the fly, using a recurrent neural network with a long short-term memory architecture, as a regression block. The target state predictions are then corrected using a novel data association algorithm, with a low computational complexity. The proposed algorithm is evaluated over synthetic and real point target filtering scenarios, demonstrating a remarkable performance over highly cluttered data sequences.
Tasks
Published	2019-02-20
URL	http://arxiv.org/abs/1902.07630v1
PDF	http://arxiv.org/pdf/1902.07630v1.pdf
PWC	https://paperswithcode.com/paper/filtering-point-targets-via-online-learning
Repo
Framework

GFCN: A New Graph Convolutional Network Based on Parallel Flows


Title	GFCN: A New Graph Convolutional Network Based on Parallel Flows
Authors	Feng Ji, Jielong Yang, Qiang Zhang, Wee Peng Tay
Abstract	In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data. One major direction is based on spectral graph theory and graph signal processing. In this paper, we study the problem from a completely different perspective, by introducing parallel flow decomposition of graphs. The essential idea is to decompose a graph into families of non-intersecting one dimensional (1D) paths, after which, we may apply a 1D CNN along each family of paths. We demonstrate that the our method, which we call GraphFlow, is able to transfer CNN architectures to general graphs. To show the effectiveness of our approach, we test our method on the classical MNIST dataset, synthetic datasets on network information propagation and a news article classification dataset.
Tasks	Image Classification, Object Recognition
Published	2019-02-25
URL	https://arxiv.org/abs/1902.09173v4
PDF	https://arxiv.org/pdf/1902.09173v4.pdf
PWC	https://paperswithcode.com/paper/graphflow-a-new-graph-convolutional-network
Repo
Framework

Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning


Title	Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
Authors	Xiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, Zhi-Hong Deng
Abstract	We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an input-dependent subgraph to explicitly model a sequential reasoning process. Each subgraph is dynamically constructed, expanding itself selectively under a flow-style attention mechanism. In this way, we can not only construct graphical explanations to interpret prediction, but also prune message passing in Graph Neural Networks (GNNs) to scale with the size of graphs. We take the inspiration from the consciousness prior proposed by Bengio to design a two-GNN framework to encode global input-invariant graph-structured representation and learn local input-dependent one coordinated by an attention module. Experiments show the reasoning capability in our model that is providing a clear graphical explanation as well as predicting results accurately, outperforming most state-of-the-art methods in knowledge base completion tasks.
Tasks	Knowledge Base Completion
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11334v2
PDF	https://arxiv.org/pdf/1909.11334v2.pdf
PWC	https://paperswithcode.com/paper/dynamically-pruned-message-passing-networks
Repo
Framework

Learning Correlated Latent Representations with Adaptive Priors


Title	Learning Correlated Latent Representations with Adaptive Priors
Authors	Da Tang, Dawen Liang, Nicholas Ruozzi, Tony Jebara
Abstract	Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed Correlated Variational Auto-Encoders (CVAEs), which employ a structured mixture model as prior and a structured variational posterior for each mixture component to enforce that the learned latent representations follow the same correlation structure. However, as we demonstrate in this work, such a choice cannot guarantee that CVAEs capture all the correlations. Furthermore, it prevents us from obtaining a tractable joint and marginal variational distribution. To address these issues, we propose Adaptive Correlated Variational Auto-Encoders (ACVAEs), which apply an adaptive prior distribution that can be adjusted during training and can learn a tractable joint variational distribution. Its tractable form also enables further refinement with belief propagation. Experimental results on link prediction and hierarchical clustering show that ACVAEs significantly outperform CVAEs among other benchmarks.
Tasks	Link Prediction
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06419v5
PDF	https://arxiv.org/pdf/1906.06419v5.pdf
PWC	https://paperswithcode.com/paper/learning-correlated-latent-representations
Repo
Framework

Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs


Title	Real-time Facial Surface Geometry from Monocular Video on Mobile GPUs
Authors	Yury Kartynnik, Artsiom Ablavatski, Ivan Grishchenko, Matthias Grundmann
Abstract	We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects. The proposed model demonstrates super-realtime inference speed on mobile GPUs (100-1000+ FPS, depending on the device and model variant) and a high prediction quality that is comparable to the variance in manual annotations of the same image.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06724v1
PDF	https://arxiv.org/pdf/1907.06724v1.pdf
PWC	https://paperswithcode.com/paper/real-time-facial-surface-geometry-from
Repo
Framework

Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies


Title	Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies
Authors	Stefan G. Stark, Stephanie L. Hyland, Melanie F. Pradier, Kjong Lehmann, Andreas Wicki, Fernando Perez Cruz, Julia E. Vogt, Gunnar Rätsch
Abstract	The recent adoption of Electronic Health Records (EHRs) by health care providers has introduced an important source of data that provides detailed and highly specific insights into patient phenotypes over large cohorts. These datasets, in combination with machine learning and statistical approaches, generate new opportunities for research and clinical care. However, many methods require the patient representations to be in structured formats, while the information in the EHR is often locked in unstructured texts designed for human readability. In this work, we develop the methodology to automatically extract clinical features from clinical narratives from large EHR corpora without the need for prior knowledge. We consider medical terms and sentences appearing in clinical narratives as atomic information units. We propose an efficient clustering strategy suitable for the analysis of large text corpora and to utilize the clusters to represent information about the patient compactly. To demonstrate the utility of our approach, we perform an association study of clinical features with somatic mutation profiles from 4,007 cancer patients and their tumors. We apply the proposed algorithm to a dataset consisting of about 65 thousand documents with a total of about 3.2 million sentences. We identify 341 significant statistical associations between the presence of somatic mutations and clinical features. We annotated these associations according to their novelty, and report several known associations. We also propose 32 testable hypotheses where the underlying biological mechanism does not appear to be known but plausible. These results illustrate that the automated discovery of clinical features is possible and the joint analysis of clinical and genetic datasets can generate appealing new hypotheses.
Tasks
Published	2019-04-29
URL	https://arxiv.org/abs/1904.12973v2
PDF	https://arxiv.org/pdf/1904.12973v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-extraction-of-phenotypes-from
Repo
Framework

Few Shot Network Compression via Cross Distillation


Title	Few Shot Network Compression via Cross Distillation
Authors	Haoli Bai, Jiaxiang Wu, Irwin King, Michael Lyu
Abstract	Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and security issues. As a compromise between privacy and performance, in this paper we investigate few shot network compression: given few samples per class, how can we effectively compress the network with negligible performance drop? The core challenge of few shot network compression lies in high estimation errors from the original network during inference, since the compressed network can easily over-fits on the few training instances. The estimation errors could propagate and accumulate layer-wisely and finally deteriorate the network output. To address the problem, we propose cross distillation, a novel layer-wise knowledge distillation approach. By interweaving hidden layers of teacher and student network, layer-wisely accumulated estimation errors can be effectively reduced.The proposed method offers a general framework compatible with prevalent network compression techniques such as pruning. Extensive experiments on benchmark datasets demonstrate that cross distillation can significantly improve the student network’s accuracy when only a few training instances are available.
Tasks	Model Compression
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09450v1
PDF	https://arxiv.org/pdf/1911.09450v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-network-compression-via-cross
Repo
Framework

Transfer Learning for Clinical Time Series Analysis using Deep Neural Networks


Title	Transfer Learning for Clinical Time Series Analysis using Deep Neural Networks
Authors	Priyanka Gupta, Pankaj Malhotra, Jyoti Narwariya, Lovekesh Vig, Gautam Shroff
Abstract	Deep neural networks have shown promising results for various clinical prediction tasks. However, training deep networks such as those based on Recurrent Neural Networks (RNNs) requires large labeled data, significant hyper-parameter tuning effort and expertise, and high computational resources. In this work, we investigate as to what extent can transfer learning address these issues when using deep RNNs to model multivariate clinical time series. We consider two scenarios for transfer learning using RNNs: i) domain-adaptation, i.e., leveraging a deep RNN - namely, TimeNet - pre-trained for feature extraction on time series from diverse domains, and adapting it for feature extraction and subsequent target tasks in healthcare domain, ii) task-adaptation, i.e., pre-training a deep RNN - namely, HealthNet - on diverse tasks in healthcare domain, and adapting it to new target tasks in the same domain. We evaluate the above approaches on publicly available MIMIC-III benchmark dataset, and demonstrate that (a) computationally-efficient linear models trained using features extracted via pre-trained RNNs outperform or, in the worst case, perform as well as deep RNNs and statistical hand-crafted features based models trained specifically for target task; (b) models obtained by adapting pre-trained models for target tasks are significantly more robust to the size of labeled data compared to task-specific RNNs, while also being computationally efficient. We, therefore, conclude that pre-trained deep models like TimeNet and HealthNet allow leveraging the advantages of deep learning for clinical time series analysis tasks, while also minimize dependence on hand-crafted features, deal robustly with scarce labeled training data scenarios without overfitting, as well as reduce dependence on expertise and resources required to train deep networks from scratch.
Tasks	Domain Adaptation, Time Series, Time Series Analysis, Transfer Learning
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00655v1
PDF	http://arxiv.org/pdf/1904.00655v1.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-for-clinical-time-series-1
Repo
Framework

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders


Title	Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders
Authors	Hebi Li, Qi Xiao, Shixin Tian, Jin Tian
Abstract	Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time a model needs to be protected, such expensive training scheme needs to be performed. In this paper, we propose to apply iterative adversarial training scheme to an external auto-encoder, which once trained can be used to protect other models directly. We empirically show that our model outperforms other purifying-based methods against white-box attacks, and transfers well to directly protect other base models with different architectures.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10729v1
PDF	https://arxiv.org/pdf/1905.10729v1.pdf
PWC	https://paperswithcode.com/paper/purifying-adversarial-perturbation-with
Repo
Framework

Adaptive Composition GAN towards Realistic Image Synthesis


Title	Adaptive Composition GAN towards Realistic Image Synthesis
Authors	Fangneng Zhan, Jiaxing Huang, Shijian Lu
Abstract	Despite the rapid progress of generative adversarial networks (GANs) in image synthesis in recent years, current approaches work in either geometry domain or appearance domain which tend to introduce various synthesis artifacts. This paper presents an innovative Adaptive Composition GAN (AC-GAN) that incorporates image synthesis in geometry and appearance domains into an end-to-end trainable network and achieves synthesis realism in both domains simultaneously. An innovative hierarchical synthesis mechanism is designed which is capable of generating realistic geometry and composition when multiple foreground objects with or without occlusions are involved in synthesis. In addition, a novel attention mask is introduced to guide the appearance adaptation to the embedded foreground objects which helps preserve image details and resolution and also provide better reference for synthesis in geometry domain. Extensive experiments on scene text image synthesis, automated portrait editing and indoor rendering tasks show that the proposed AC-GAN achieves superior synthesis performance qualitatively and quantitatively.
Tasks	Image Generation
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04693v2
PDF	https://arxiv.org/pdf/1905.04693v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-composition-gan-towards-realistic
Repo
Framework