January 29, 2020

3210 words 16 mins read

Paper Group ANR 637

On perfectness in Gaussian graphical models. Paradigm shift in electron-based crystallography via machine learning. An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script. The Challenges in Specifying and Explaining Synthesized Implementations of Reactive Systems. Deterministic tensor completion with hypergraph expa …

On perfectness in Gaussian graphical models


Title	On perfectness in Gaussian graphical models
Authors	Arash A. Amini, Bryon Aragam, Qing Zhou
Abstract	Knowing when a graphical model is perfect to a distribution is essential in order to relate separation in the graph to conditional independence in the distribution, and this is particularly important when performing inference from data. When the model is perfect, there is a one-to-one correspondence between conditional independence statements in the distribution and separation statements in the graph. Previous work has shown that almost all models based on linear directed acyclic graphs as well as Gaussian chain graphs are perfect, the latter of which subsumes Gaussian graphical models (i.e., the undirected Gaussian models) as a special case. However, the complexity of chain graph models leads to a proof of this result which is indirect and mired by the complications of parameterizing this general class. In this paper, we directly approach the problem of perfectness for the Gaussian graphical models, and provide a new proof, via a more transparent parametrization, that almost all such models are perfect. Our approach is based on, and substantially extends, a construction of Ln\v{e}ni\v{c}ka and Mat'u\v{s} showing the existence of a perfect Gaussian distribution for any graph.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01978v1
PDF	https://arxiv.org/pdf/1909.01978v1.pdf
PWC	https://paperswithcode.com/paper/on-perfectness-in-gaussian-graphical-models
Repo
Framework

Paradigm shift in electron-based crystallography via machine learning


Title	Paradigm shift in electron-based crystallography via machine learning
Authors	Kevin Kaufmann, Chaoyi Zhu, Alexander S. Rosengarten, Daniel Maryanovsky, Tyler J. Harrington, Eduardo Marin, Kenneth S. Vecchio
Abstract	Accurately determining the crystallographic structure of a material, organic or inorganic, is a critical primary step in material development and analysis. The most common practices involve analysis of diffraction patterns produced in laboratory XRD, TEM, and synchrotron X-ray sources. However, these techniques are slow, require careful sample preparation, can be difficult to access, and are prone to human error during analysis. This paper presents a newly developed methodology that represents a paradigm change in electron diffraction-based structure analysis techniques, with the potential to revolutionize multiple crystallography-related fields. A machine learning-based approach for rapid and autonomous identification of the crystal structure of metals and alloys, ceramics, and geological specimens, without any prior knowledge of the sample, is presented and demonstrated utilizing the electron backscatter diffraction (EBSD) technique. Electron backscatter diffraction patterns are collected from materials with well-known crystal structures, then a deep neural network model is constructed for classification to a specific Bravais lattice or point group. The applicability of this approach is evaluated on diffraction patterns from samples unknown to the computer without any human input or data filtering. This is in comparison to traditional Hough transform EBSD, which requires that you have already determined the phases present in your sample. The internal operations of the neural network are elucidated through visualizing the symmetry features learned by the convolutional neural network. It is determined that the model looks for the same features a crystallographer would use, even though it is not explicitly programmed to do so. This study opens the door to fully automated, high-throughput determination of crystal structures via several electron-based diffraction techniques.
Tasks
Published	2019-02-10
URL	http://arxiv.org/abs/1902.03682v1
PDF	http://arxiv.org/pdf/1902.03682v1.pdf
PWC	https://paperswithcode.com/paper/paradigm-shift-in-electron-based
Repo
Framework

An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script


Title	An Ensemble of Neural Networks for Non-Linear Segmentation of Overlapped Cursive Script
Authors	Amjad Rehman
Abstract	Precise character segmentation is the only solution towards higher Optical Character Recognition (OCR) accuracy. In cursive script, overlapped characters are serious issue in the process of character segmentations as characters are deprived from their discriminative parts using conventional linear segmentation strategy. Hence, non-linear segmentation is an utmost need to avoid loss of characters parts and to enhance character/script recognition accuracy. This paper presents an improved approach for non-linear segmentation of the overlapped characters in handwritten roman script. The proposed technique is composed of a sequence of heuristic rules based on geometrical features of characters to locate possible non-linear character boundaries in a cursive script word. However, to enhance efficiency, heuristic approach is integrated with trained ensemble neural network validation strategy for verification of character boundaries. Accordingly, correct boundaries are retained and incorrect are removed based on ensemble neural networks vote. Finally, based on verified valid segmentation points, characters are segmented non-linearly. For fair comparison CEDAR benchmark database is experimented. The experimental results are much better than conventional linear character segmentation techniques reported in the state of art. Ensemble neural network play vital role to enhance character segmentation accuracy as compared to individual neural networks.
Tasks	Optical Character Recognition
Published	2019-04-07
URL	http://arxiv.org/abs/1904.12592v1
PDF	http://arxiv.org/pdf/1904.12592v1.pdf
PWC	https://paperswithcode.com/paper/190412592
Repo
Framework

The Challenges in Specifying and Explaining Synthesized Implementations of Reactive Systems


Title	The Challenges in Specifying and Explaining Synthesized Implementations of Reactive Systems
Authors	Hadas Kress-Gazit, Hazem Torfah
Abstract	In formal synthesis of reactive systems an implementation of a system is automatically constructed from its formal specification. The great advantage of synthesis is that the resulting implementation is correct by construction; therefore there is no need for manual programming and tedious debugging tasks. Developers remain, nevertheless, hesitant to using automatic synthesis tools and still favor manually writing code. A common argument against synthesis is that the resulting implementation does not always give a clear picture on what decisions were made during the synthesis process. The outcome of synthesis tools is mostly unreadable and hinders the developer from understanding the functionality of the resulting implementation. Many attempts have been made in the last years to make the synthesis process more transparent to users. Either by structuring the outcome of synthesis tools or by providing additional automated support to help users with the specification process. In this paper we discuss the challenges in writing specifications for reactive systems and give a survey on what tools have been developed to guide users in specifying reactive systems and understanding the outcome of synthesis tools.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00591v1
PDF	http://arxiv.org/pdf/1901.00591v1.pdf
PWC	https://paperswithcode.com/paper/the-challenges-in-specifying-and-explaining
Repo
Framework

Deterministic tensor completion with hypergraph expanders


Title	Deterministic tensor completion with hypergraph expanders
Authors	Kameron Decker Harris, Yizhe Zhu
Abstract	We provide a novel analysis of low rank tensor completion based on hypergraph expanders. As a proxy for rank, we minimize the max-quasinorm of the tensor, introduced by Ghadermarzy, Plan, and Yilmaz (2018), which generalizes the max-norm for matrices. Our analysis is deterministic and shows that the number of samples required to recover an order-$t$ tensor with at most $n$ entries per dimension is linear in $n$, under the assumption that the rank and order of the tensor are $O(1)$. As steps in our proof, we find an improved expander mixing lemma for a $t$-partite, $t$-uniform regular hypergraph model and prove several new properties about tensor max-quasinorm. To the best of our knowledge, this is the first deterministic analysis of tensor completion.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10692v1
PDF	https://arxiv.org/pdf/1910.10692v1.pdf
PWC	https://paperswithcode.com/paper/deterministic-tensor-completion-with
Repo
Framework

Deep generative model-driven multimodal prostate segmentation in radiotherapy


Title	Deep generative model-driven multimodal prostate segmentation in radiotherapy
Authors	Kibrom Berihu Girum, Gilles Créhange, Raabid Hussain, Paul Michael Walker, Alain Lalande
Abstract	Deep learning has shown unprecedented success in a variety of applications, such as computer vision and medical image analysis. However, there is still potential to improve segmentation in multimodal images by embedding prior knowledge via learning-based shape modeling and registration to learn the modality invariant anatomical structure of organs. For example, in radiotherapy automatic prostate segmentation is essential in prostate cancer diagnosis, therapy, and post-therapy assessment from T2-weighted MR or CT images. In this paper, we present a fully automatic deep generative model-driven multimodal prostate segmentation method using convolutional neural network (DGMNet). The novelty of our method comes with its embedded generative neural network for learning-based shape modeling and its ability to adapt for different imaging modalities via learning-based registration. The proposed method includes a multi-task learning framework that combines a convolutional feature extraction and an embedded regression and classification based shape modeling. This enables the network to predict the deformable shape of an organ. We show that generative neural networkbased shape modeling trained on a reliable contrast imaging modality (such as MRI) can be directly applied to low contrast imaging modality (such as CT) to achieve accurate prostate segmentation. The method was evaluated on MRI and CT datasets acquired from different clinical centers with large variations in contrast and scanning protocols. Experimental results reveal that our method can be used to automatically and accurately segment the prostate gland in different imaging modalities.
Tasks	Multi-Task Learning
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10542v1
PDF	https://arxiv.org/pdf/1910.10542v1.pdf
PWC	https://paperswithcode.com/paper/deep-generative-model-driven-multimodal
Repo
Framework

DDI-100: Dataset for Text Detection and Recognition


Title	DDI-100: Dataset for Text Detection and Recognition
Authors	Ilia Zharikov, Filipp Nikitin, Ilia Vasiliev, Vladimir Dokholyan
Abstract	Nowadays document analysis and recognition remain challenging tasks. However, only a few datasets designed for text detection (TD) and optical character recognition (OCR) problems exist. In this paper we present Distorted Document Images dataset (DDI-100) and demonstrate its usefulness in a wide range of document analysis problems. DDI-100 dataset is a synthetic dataset based on 7000 real unique document pages and consists of more than 100000 augmented images. Ground truth comprises text and stamp masks, text and characters bounding boxes with relevant annotations. Validation of DDI-100 dataset was conducted using several TD and OCR models that show high-quality performance on real data.
Tasks	Optical Character Recognition
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11658v1
PDF	https://arxiv.org/pdf/1912.11658v1.pdf
PWC	https://paperswithcode.com/paper/ddi-100-dataset-for-text-detection-and
Repo
Framework

Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering


Title	Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
Authors	Victor Zhong, Caiming Xiong, Nitish Shirish Keskar, Richard Socher
Abstract	End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In this work, we propose the Coarse-grain Fine-grain Coattention Network (CFC), a new question answering model that combines information from evidence across multiple documents. The CFC consists of a coarse-grain module that interprets documents with respect to the query then finds a relevant answer, and a fine-grain module which scores each candidate answer by comparing its occurrences across all of the documents with the query. We design these modules using hierarchies of coattention and self-attention, which learn to emphasize different parts of the input. On the Qangaroo WikiHop multi-evidence question answering task, the CFC obtains a new state-of-the-art result of 70.6% on the blind test set, outperforming the previous best by 3% accuracy despite not using pretrained contextual encoders.
Tasks	Question Answering
Published	2019-01-03
URL	https://arxiv.org/abs/1901.00603v2
PDF	https://arxiv.org/pdf/1901.00603v2.pdf
PWC	https://paperswithcode.com/paper/coarse-grain-fine-grain-coattention-network
Repo
Framework

swCaffe: a Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight


Title	swCaffe: a Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight
Authors	Jiarui Fang, Liandeng Li, Haohuan Fu, Jinlei Jiang, Wenlai Zhao, Conghui He, Xin You, Guangwen Yang
Abstract	This paper reports our efforts on swCaffe, a highly efficient parallel framework for accelerating deep neural networks (DNNs) training on Sunway TaihuLight, the current fastest supercomputer in the world that adopts a unique many-core heterogeneous architecture, with 40,960 SW26010 processors connected through a customized communication network. First, we point out some insightful principles to fully exploit the performance of the innovative many-core architecture. Second, we propose a set of optimization strategies for redesigning a variety of neural network layers based on Caffe. Third, we put forward a topology-aware parameter synchronization scheme to scale the synchronous Stochastic Gradient Descent (SGD) method to multiple processors efficiently. We evaluate our framework by training a variety of widely used neural networks with the ImageNet dataset. On a single node, swCaffe can achieve 23%~{}119% overall performance compared with Caffe running on K40m GPU. As compared with the Caffe on CPU, swCaffe runs 3.04~{}7.84x faster on all the networks. Finally, we present the scalability of swCaffe for the training of ResNet-50 and AlexNet on the scale of 1024 nodes.
Tasks
Published	2019-03-16
URL	http://arxiv.org/abs/1903.06934v1
PDF	http://arxiv.org/pdf/1903.06934v1.pdf
PWC	https://paperswithcode.com/paper/swcaffe-a-parallel-framework-for-accelerating
Repo
Framework

Speech enhancement with variational autoencoders and alpha-stable distributions


Title	Speech enhancement with variational autoencoders and alpha-stable distributions
Authors	Simon Leglaive, Umut Simsekli, Antoine Liutkus, Laurent Girin, Radu Horaud
Abstract	This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not assume prior knowledge of the noisy recording environment. In this context, our contribution is to propose a noise model based on alpha-stable distributions, instead of the more conventional Gaussian non-negative matrix factorization approach found in previous studies. We develop a Monte Carlo expectation-maximization algorithm for estimating the model parameters at test time. Experimental results show the superiority of the proposed approach both in terms of perceptual quality and intelligibility of the enhanced speech signal.
Tasks	Speech Enhancement
Published	2019-02-08
URL	http://arxiv.org/abs/1902.03926v1
PDF	http://arxiv.org/pdf/1902.03926v1.pdf
PWC	https://paperswithcode.com/paper/speech-enhancement-with-variational
Repo
Framework

Fast Fitting of Reflectivity Data of Growing Thin Films Using Neural Networks


Title	Fast Fitting of Reflectivity Data of Growing Thin Films Using Neural Networks
Authors	Alessandro Greco, Vladimir Starostin, Christos Karapanagiotis, Alexander Hinderhofer, Alexander Gerlach, Linus Pithan, Sascha Liehr, Frank Schreiber, Stefan Kowarik
Abstract	X-ray reflectivity (XRR) is a powerful and popular scattering technique that can give valuable insight into the growth behavior of thin films. In this study, we show how a simple artificial neural network model can be used to predict the thickness, roughness and density of thin films of different organic semiconductors (diindenoperylene, copper(II) phthalocyanine and $\alpha$-sexithiophene) on silica from their XRR data with millisecond computation time and with minimal user input or a priori knowledge. For a large experimental dataset of 372 XRR curves, we show that a simple fully connected model can already provide good predictions with a mean absolute percentage error of 8-18 % when compared to the results obtained by a genetic least mean squares fit using the classical Parratt formalism. Furthermore, current drawbacks and prospects for improvement are discussed.
Tasks
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02898v1
PDF	https://arxiv.org/pdf/1910.02898v1.pdf
PWC	https://paperswithcode.com/paper/fast-fitting-of-reflectivity-data-of-growing
Repo
Framework

Deep learning enabled laser speckle wavemeter with a high dynamic range


Title	Deep learning enabled laser speckle wavemeter with a high dynamic range
Authors	Roopam K. Gupta, Graham D. Bruce, Simon J. Powis, Kishan Dholakia
Abstract	The speckle pattern produced when a laser is scattered by a disordered medium has recently been shown to give a surprisingly accurate or broadband measurement of wavelength. Here we show that deep learning is an ideal approach to analyse wavelength variations using a speckle wavemeter due to its ability to identify trends and overcome low signal to noise ratio in complex datasets. This combination enables wavelength measurement at high resolution and over a broad operating range in a single step, which has not been possible with previous approaches. We demonstrate attometre-scale wavelength resolution over an operating range from 488 nm to 976 nm. This dynamic range is six orders of magnitude beyond the state of the art.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10702v1
PDF	https://arxiv.org/pdf/1910.10702v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-enabled-laser-speckle-wavemeter
Repo
Framework

Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints


Title	Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints
Authors	Felix Sattler, Klaus-Robert Müller, Wojciech Samek
Abstract	Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it’s popularity, it has been observed that Federated Learning yields suboptimal results if the local clients’ data distributions diverge. To address this issue, we present Clustered Federated Learning (CFL), a novel Federated Multi-Task Learning (FMTL) framework, which exploits geometric properties of the FL loss surface, to group the client population into clusters with jointly trainable data distributions. In contrast to existing FMTL approaches, CFL does not require any modifications to the FL communication protocol to be made, is applicable to general non-convex objectives (in particular deep neural networks) and comes with strong mathematical guarantees on the clustering quality. CFL is flexible enough to handle client populations that vary over time and can be implemented in a privacy preserving way. As clustering is only performed after Federated Learning has converged to a stationary point, CFL can be viewed as a post-processing method that will always achieve greater or equal performance than conventional FL by allowing clients to arrive at more specialized models. We verify our theoretical analysis in experiments with deep convolutional and recurrent neural networks on commonly used Federated Learning datasets.
Tasks	Multi-Task Learning
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01991v1
PDF	https://arxiv.org/pdf/1910.01991v1.pdf
PWC	https://paperswithcode.com/paper/clustered-federated-learning-model-agnostic
Repo
Framework

Learning Wavefront Coding for Extended Depth of Field Imaging


Title	Learning Wavefront Coding for Extended Depth of Field Imaging
Authors	Ugur Akpinar, Erdem Sahin, Atanas Gotchev
Abstract	The depth of field constitutes an important quality factor of imaging systems that highly affects the content of the acquired spatial information in the captured images. Extended depth of field (EDoF) imaging is a challenging problem due to its highly ill-posed nature, hence it has been extensively addressed in the literature. We propose a computational imaging approach for EDoF, where we employ wavefront coding via a diffractive optical element (DOE) and we achieve deblurring through a convolutional neural network. Thanks to the end-to-end differentiable modeling of optical image formation and computational post-processing, we jointly optimize the optical design, i.e., DOE, and the deblurring through standard gradient descent methods. Based on the properties of the underlying refractive lens and the desired EDoF range, we provide an analytical expression for the search space of the DOE, which helps in the convergence of the end-to-end network. We achieve superior EDoF imaging performance compared to state of the art, where we demonstrate results with minimal artifacts in various scenarios, including deep 3D scenes and broadband imaging.
Tasks	Deblurring
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13423v1
PDF	https://arxiv.org/pdf/1912.13423v1.pdf
PWC	https://paperswithcode.com/paper/learning-wavefront-coding-for-extended-depth
Repo
Framework

Explainable Ordinal Factorization Model: Deciphering the Effects of Attributes by Piece-wise Linear Approximation


Title	Explainable Ordinal Factorization Model: Deciphering the Effects of Attributes by Piece-wise Linear Approximation
Authors	Mengzhuo Guo, Zhongzhi Xu, Qingpeng Zhang, Xiuwu Liao, Jiapeng Liu
Abstract	Ordinal regression predicts the objects’ labels that exhibit a natural ordering, which is important to many managerial problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the attributes affect the prediction is critical to users. However, most, if not all, existing ordinal regression models simplify such explanation in the form of constant coefficients for the main and interaction effects of individual attributes. Such explanation cannot characterize the contributions of attributes at different value scales. To address this challenge, we propose a new explainable ordinal regression model, namely, the Explainable Ordinal Factorization Model (XOFM). XOFM uses the piece-wise linear functions to approximate the actual contributions of individual attributes and their interactions. Moreover, XOFM introduces a novel ordinal transformation process to assign each object the probabilities of belonging to multiple relevant classes, instead of fixing boundaries to differentiate classes. XOFM is based on the Factorization Machines to handle the potential sparsity problem as a result of discretizing the attribute scales. Comprehensive experiments with benchmark datasets and baseline models demonstrate that the proposed XOFM exhibits superior explainability and leads to state-of-the-art prediction accuracy.
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.05909v1
PDF	https://arxiv.org/pdf/1911.05909v1.pdf
PWC	https://paperswithcode.com/paper/explainable-ordinal-factorization-model
Repo
Framework