July 27, 2019

3177 words 15 mins read

Paper Group ANR 513

The Static and Stochastic VRPTW with both random Customers and Reveal Times: algorithms and recourse strategies. Photo-realistic Facial Texture Transfer. UmUTracker: A versatile MATLAB program for automated particle tracking of 2D light microscopy or 3D digital holography data. Annealed Generative Adversarial Networks. Dual Based DSP Bidding Strate …

The Static and Stochastic VRPTW with both random Customers and Reveal Times: algorithms and recourse strategies


Title	The Static and Stochastic VRPTW with both random Customers and Reveal Times: algorithms and recourse strategies
Authors	Michael Saint-Guillain, Christine Solnon, Yves Deville
Abstract	Unlike its deterministic counterpart, static and stochastic vehicle routing problems (SS-VRP) aim at modeling and solving real-life operational problems by considering uncertainty on data. We consider the SS-VRPTW-CR introduced in Saint-Guillain et al. (2017). Like the SS-VRP introduced by Bertsimas (1992), we search for optimal first stage routes for a fleet of vehicles to handle a set of stochastic customer demands, i.e., demands are uncertain and we only know their probabilities. In addition to capacity constraints, customer demands are also constrained by time windows. Unlike all SS-VRP variants, the SS-VRPTW-CR does not make any assumption on the time at which a stochastic demand is revealed, i.e., the reveal time is stochastic as well. To handle this new problem, we introduce waiting locations: Each vehicle is assigned a sequence of waiting locations from which it may serve some associated demands, and the objective is to minimize the expected number of demands that cannot be satisfied in time. In this paper, we propose two new recourse strategies for the SS-VRPTW-CR, together with their closed-form expressions for efficiently computing their expectations: The first one allows us to take vehicle capacities into account; The second one allows us to optimize routes by avoiding some useless trips. We propose two algorithms for searching for routes with optimal expected costs: The first one is an extended branch-and-cut algorithm, based on a stochastic integer formulation, and the second one is a local search based heuristic method. We also introduce a new public benchmark for the SS-VRPTW-CR, based on real-world data coming from the city of Lyon. We evaluate our two algorithms on this benchmark and empirically demonstrate the expected superiority of the SS-VRPTW-CR anticipative actions over a basic “wait-and-serve” policy.
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03151v1
PDF	http://arxiv.org/pdf/1708.03151v1.pdf
PWC	https://paperswithcode.com/paper/the-static-and-stochastic-vrptw-with-both
Repo
Framework

Photo-realistic Facial Texture Transfer


Title	Photo-realistic Facial Texture Transfer
Authors	Parneet Kaur, Hang Zhang, Kristin J. Dana
Abstract	Style transfer methods have achieved significant success in recent years with the use of convolutional neural networks. However, many of these methods concentrate on artistic style transfer with few constraints on the output image appearance. We address the challenging problem of transferring face texture from a style face image to a content face image in a photorealistic manner without changing the identity of the original content image. Our framework for face texture transfer (FaceTex) augments the prior work of MRF-CNN with a novel facial semantic regularization that incorporates a face prior regularization smoothly suppressing the changes around facial meso-structures (e.g eyes, nose and mouth) and a facial structure loss function which implicitly preserves the facial structure so that face texture can be transferred without changing the original identity. We demonstrate results on face images and compare our approach with recent state-of-the-art methods. Our results demonstrate superior texture transfer because of the ability to maintain the identity of the original face image.
Tasks	Style Transfer
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04306v1
PDF	http://arxiv.org/pdf/1706.04306v1.pdf
PWC	https://paperswithcode.com/paper/photo-realistic-facial-texture-transfer
Repo
Framework

UmUTracker: A versatile MATLAB program for automated particle tracking of 2D light microscopy or 3D digital holography data


Title	UmUTracker: A versatile MATLAB program for automated particle tracking of 2D light microscopy or 3D digital holography data
Authors	Hanqing Zhang, Tim Stangner, Krister Wiklund, Alvaro Rodriguez, Magnus Andersson
Abstract	We present a versatile and fast MATLAB program (UmUTracker) that automatically detects and tracks particles by analyzing video sequences acquired by either light microscopy or digital in-line holographic microscopy. Our program detects the 2D lateral positions of particles with an algorithm based on the isosceles triangle transform, and reconstructs their 3D axial positions by a fast implementation of the Rayleigh-Sommerfeld model using a radial intensity profile. To validate the accuracy and performance of our program, we first track the 2D position of polystyrene particles using bright field and digital holographic microscopy. Second, we determine the 3D particle position by analyzing synthetic and experimentally acquired holograms. Finally, to highlight the full program features, we profile the microfluidic flow in a 100 micrometer high flow chamber. This result agrees with computational fluid dynamic simulations. On a regular desktop computer UmUTracker can detect, analyze, and track multiple particles at 5 frames per second for a template size of 201 x 201 in a 1024 x 1024 image. To enhance usability and to make it easy to implement new functions we used object-oriented programming. UmUTracker is suitable for studies related to: particle dynamics, cell localization, colloids and microfluidic flow measurement.
Tasks
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08025v2
PDF	http://arxiv.org/pdf/1701.08025v2.pdf
PWC	https://paperswithcode.com/paper/umutracker-a-versatile-matlab-program-for
Repo
Framework

Annealed Generative Adversarial Networks


Title	Annealed Generative Adversarial Networks
Authors	Arash Mehrjou, Bernhard Schölkopf, Saeed Saremi
Abstract	We introduce a novel framework for adversarial training where the target distribution is annealed between the uniform distribution and the data distribution. We posited a conjecture that learning under continuous annealing in the nonparametric regime is stable irrespective of the divergence measures in the objective function and proposed an algorithm, dubbed {\ss}-GAN, in corollary. In this framework, the fact that the initial support of the generative network is the whole ambient space combined with annealing are key to balancing the minimax game. In our experiments on synthetic data, MNIST, and CelebA, {\ss}-GAN with a fixed annealing schedule was stable and did not suffer from mode collapse.
Tasks
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07505v1
PDF	http://arxiv.org/pdf/1705.07505v1.pdf
PWC	https://paperswithcode.com/paper/annealed-generative-adversarial-networks
Repo
Framework

Dual Based DSP Bidding Strategy and its Application


Title	Dual Based DSP Bidding Strategy and its Application
Authors	Huahui Liu, Mingrui Zhu, Xiaonan Meng, Yi Hu, Hao Wang
Abstract	In recent years, RTB(Real Time Bidding) becomes a popular online advertisement trading method. During the auction, each DSP(Demand Side Platform) is supposed to evaluate current opportunity and respond with an ad and corresponding bid price. It’s essential for DSP to find an optimal ad selection and bid price determination strategy which maximizes revenue or performance under budget and ROI(Return On Investment) constraints in P4P(Pay For Performance) or P4U(Pay For Usage) mode. We solve this problem by 1) formalizing the DSP problem as a constrained optimization problem, 2) proposing the augmented MMKP(Multi-choice Multi-dimensional Knapsack Problem) with general solution, 3) and demonstrating the DSP problem is a special case of the augmented MMKP and deriving specialized strategy. Our strategy is verified through simulation and outperforms state-of-the-art strategies in real application. To the best of our knowledge, our solution is the first dual based DSP bidding framework that is derived from strict second price auction assumption and generally applicable to the multiple ads scenario with various objectives and constraints.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09416v2
PDF	http://arxiv.org/pdf/1705.09416v2.pdf
PWC	https://paperswithcode.com/paper/dual-based-dsp-bidding-strategy-and-its
Repo
Framework

Improving Heterogeneous Face Recognition with Conditional Adversarial Networks


Title	Improving Heterogeneous Face Recognition with Conditional Adversarial Networks
Authors	Wuming Zhang, Zhixin Shu, Dimitris Samaras, Liming Chen
Abstract	Heterogeneous face recognition between color image and depth image is a much desired capacity for real world applications where shape information is looked upon as merely involved in gallery. In this paper, we propose a cross-modal deep learning method as an effective and efficient workaround for this challenge. Specifically, we begin with learning two convolutional neural networks (CNNs) to extract 2D and 2.5D face features individually. Once trained, they can serve as pre-trained models for another two-way CNN which explores the correlated part between color and depth for heterogeneous matching. Compared with most conventional cross-modal approaches, our method additionally conducts accurate depth image reconstruction from single color image with Conditional Generative Adversarial Nets (cGAN), and further enhances the recognition performance by fusing multi-modal matching results. Through both qualitative and quantitative experiments on benchmark FRGC 2D/3D face database, we demonstrate that the proposed pipeline outperforms state-of-the-art performance on heterogeneous face recognition and ensures a drastically efficient on-line stage.
Tasks	Face Recognition, Heterogeneous Face Recognition, Image Reconstruction
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02848v2
PDF	http://arxiv.org/pdf/1709.02848v2.pdf
PWC	https://paperswithcode.com/paper/improving-heterogeneous-face-recognition-with
Repo
Framework

TasNet: time-domain audio separation network for real-time, single-channel speech separation


Title	TasNet: time-domain audio separation network for real-time, single-channel speech separation
Authors	Yi Luo, Nima Mesgarani
Abstract	Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short latency applications. Most methods attempt to construct a mask for each source in time-frequency representation of the mixture signal which is not necessarily an optimal representation for speech separation. In addition, time-frequency decomposition results in inherent problems such as phase/magnitude decoupling and long time window which is required to achieve sufficient frequency resolution. We propose Time-domain Audio Separation Network (TasNet) to overcome these limitations. We directly model the signal in the time-domain using an encoder-decoder framework and perform the source separation on nonnegative encoder outputs. This method removes the frequency decomposition step and reduces the separation problem to estimation of source masks on encoder outputs which is then synthesized by the decoder. Our system outperforms the current state-of-the-art causal and noncausal speech separation algorithms, reduces the computational cost of speech separation, and significantly reduces the minimum required latency of the output. This makes TasNet suitable for applications where low-power, real-time implementation is desirable such as in hearable and telecommunication devices.
Tasks	Speech Separation
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00541v2
PDF	http://arxiv.org/pdf/1711.00541v2.pdf
PWC	https://paperswithcode.com/paper/tasnet-time-domain-audio-separation-network
Repo
Framework

Compressive Online Robust Principal Component Analysis with Optical Flow for Video Foreground-Background Separation


Title	Compressive Online Robust Principal Component Analysis with Optical Flow for Video Foreground-Background Separation
Authors	Srivatsa Prativadibhayankaram, Huynh Van Luong, Thanh-Ha Le, Andre Kaup
Abstract	In the context of online Robust Principle Component Analysis (RPCA) for the video foreground-background separation, we propose a compressive online RPCA with optical flow that separates recursively a sequence of frames into sparse (foreground) and low-rank (background) components. Our method considers a small set of measurements taken per data vector (frame), which is different from conventional batch RPCA, processing all the data directly. The proposed method also incorporates multiple prior information, namely previous foreground and background frames, to improve the separation and then updates the prior information for the next frame. Moreover, the foreground prior frames are improved by estimating motions between the previous foreground frames using optical flow and compensating the motions to achieve higher quality foreground prior. The proposed method is applied to online video foreground and background separation from compressive measurements. The visual and quantitative results show that our method outperforms the existing methods.
Tasks	Optical Flow Estimation
Published	2017-10-25
URL	http://arxiv.org/abs/1710.09160v1
PDF	http://arxiv.org/pdf/1710.09160v1.pdf
PWC	https://paperswithcode.com/paper/compressive-online-robust-principal-component
Repo
Framework

Multiresolution and Hierarchical Analysis of Astronomical Spectroscopic Cubes using 3D Discrete Wavelet Transform


Title	Multiresolution and Hierarchical Analysis of Astronomical Spectroscopic Cubes using 3D Discrete Wavelet Transform
Authors	Martín Villanueva, Mauricio Araya
Abstract	The intrinsically hierarchical and blended structure of interstellar molecular clouds, plus the always increasing resolution of astronomical instruments, demand advanced and automated pattern recognition techniques for identifying and connecting source components in spectroscopic cubes. We extend the work done in multiresolution analysis using Wavelets for astronomical 2D images to 3D spectroscopic cubes, combining the results with the Dendrograms approach to offer a hierarchical representation of connections between sources at different scale levels. We test our approach in real data from the ALMA observatory, exploring different Wavelet families and assessing the main parameter for source identification (i.e., RMS) at each level. Our approach shows that is feasible to perform multiresolution analysis for the spatial and frequency domains simultaneously rather than analyzing each spectral channel independently.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06663v2
PDF	http://arxiv.org/pdf/1711.06663v2.pdf
PWC	https://paperswithcode.com/paper/multiresolution-and-hierarchical-analysis-of
Repo
Framework

Argument-based Belief in Topological Structures


Title	Argument-based Belief in Topological Structures
Authors	Chenwei Shi, Sonja Smets, Fernando R. Velázquez-Quesada
Abstract	This paper combines two studies: a topological semantics for epistemic notions and abstract argumentation theory. In our combined setting, we use a topological semantics to represent the structure of an agent’s collection of evidence, and we use argumentation theory to single out the relevant sets of evidence through which a notion of beliefs grounded on arguments is defined. We discuss the formal properties of this newly defined notion, providing also a formal language with a matching modality together with a sound and complete axiom system for it. Despite the fact that our agent can combine her evidence in a ‘rational’ way (captured via the topological structure), argument-based beliefs are not closed under conjunction. This illustrates the difference between an agent’s reasoning abilities (i.e. the way she is able to combine her available evidence) and the closure properties of her beliefs. We use this point to argue for why the failure of closure under conjunction of belief should not bear the burden of the failure of rationality.
Tasks	Abstract Argumentation
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08762v1
PDF	http://arxiv.org/pdf/1707.08762v1.pdf
PWC	https://paperswithcode.com/paper/argument-based-belief-in-topological
Repo
Framework

Low-resource bilingual lexicon extraction using graph based word embeddings


Title	Low-resource bilingual lexicon extraction using graph based word embeddings
Authors	Ximena Gutierrez-Vasques, Victor Mijangos
Abstract	In this work we focus on the task of automatically extracting bilingual lexicon for the language pair Spanish-Nahuatl. This is a low-resource setting where only a small amount of parallel corpus is available. Most of the downstream methods do not work well under low-resources conditions. This is specially true for the approaches that use vectorial representations like Word2Vec. Our proposal is to construct bilingual word vectors from a graph. This graph is generated using translation pairs obtained from an unsupervised word alignment method. We show that, in a low-resource setting, these type of vectors are successful in representing words in a bilingual semantic space. Moreover, when a linear transformation is applied to translate words from one language to another, our graph based representations considerably outperform the popular setting that uses Word2Vec.
Tasks	Word Alignment, Word Embeddings
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02569v1
PDF	http://arxiv.org/pdf/1710.02569v1.pdf
PWC	https://paperswithcode.com/paper/low-resource-bilingual-lexicon-extraction
Repo
Framework

ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids


Title	ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids
Authors	Dinesh Jayaraman, Ruohan Gao, Kristen Grauman
Abstract	We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen views of the object to be predictable from learned features. We implement this idea as an encoder-decoder convolutional neural network. The network maps an input image of an unknown category and unknown viewpoint to a latent space, from which a deconvolutional decoder can best “lift” the image to its complete viewgrid showing the object from all viewing angles. Our class-agnostic training procedure encourages the representation to capture fundamental shape primitives and semantic regularities in a data-driven manner—without manual semantic labels. Our results on two widely-used shape datasets show 1) our approach successfully learns to perform “mental rotation” even for objects unseen during training, and 2) the learned latent space is a powerful representation for object recognition, outperforming several existing unsupervised feature learning methods.
Tasks	Object Recognition
Published	2017-09-01
URL	http://arxiv.org/abs/1709.00505v4
PDF	http://arxiv.org/pdf/1709.00505v4.pdf
PWC	https://paperswithcode.com/paper/shapecodes-self-supervised-feature-learning
Repo
Framework

PPMF: A Patient-based Predictive Modeling Framework for Early ICU Mortality Prediction


Title	PPMF: A Patient-based Predictive Modeling Framework for Early ICU Mortality Prediction
Authors	Mohammad Amin Morid, Olivia R. Liu Sheng, Samir Abdelrahman
Abstract	To date, developing a good model for early intensive care unit (ICU) mortality prediction is still challenging. This paper presents a patient based predictive modeling framework (PPMF) to improve the performance of ICU mortality prediction using data collected during the first 48 hours of ICU admission. PPMF consists of three main components verifying three related research hypotheses. The first component captures dynamic changes of patients status in the ICU using their time series data (e.g., vital signs and laboratory tests). The second component is a local approximation algorithm that classifies patients based on their similarities. The third component is a Gradient Decent wrapper that updates feature weights according to the classification feedback. Experiments using data from MIMICIII show that PPMF significantly outperforms: (1) the severity score systems, namely SASP III, APACHE IV, and MPM0III, (2) the aggregation based classifiers that utilize summarized time series, and (3) baseline feature selection methods.
Tasks	Feature Selection, Mortality Prediction, Time Series
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07499v1
PDF	http://arxiv.org/pdf/1704.07499v1.pdf
PWC	https://paperswithcode.com/paper/ppmf-a-patient-based-predictive-modeling
Repo
Framework

On Connecting Stochastic Gradient MCMC and Differential Privacy


Title	On Connecting Stochastic Gradient MCMC and Differential Privacy
Authors	Bai Li, Changyou Chen, Hao Liu, Lawrence Carin
Abstract	Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues. Differential privacy provides a principled and rigorous privacy guarantee on machine learning models. While it is common to design a model satisfying a required differential-privacy property by injecting noise, it is generally hard to balance the trade-off between privacy and utility. We show that stochastic gradient Markov chain Monte Carlo (SG-MCMC) – a class of scalable Bayesian posterior sampling algorithms proposed recently – satisfies strong differential privacy with carefully chosen step sizes. We develop theory on the performance of the proposed differentially-private SG-MCMC method. We conduct experiments to support our analysis and show that a standard SG-MCMC sampler without any modification (under a default setting) can reach state-of-the-art performance in terms of both privacy and utility on Bayesian learning.
Tasks
Published	2017-12-25
URL	http://arxiv.org/abs/1712.09097v1
PDF	http://arxiv.org/pdf/1712.09097v1.pdf
PWC	https://paperswithcode.com/paper/on-connecting-stochastic-gradient-mcmc-and
Repo
Framework

Hardening Quantum Machine Learning Against Adversaries


Title	Hardening Quantum Machine Learning Against Adversaries
Authors	Nathan Wiebe, Ram Shankar Siva Kumar
Abstract	Security for machine learning has begun to become a serious issue for present day applications. An important question remaining is whether emerging quantum technologies will help or hinder the security of machine learning. Here we discuss a number of ways that quantum information can be used to help make quantum classifiers more secure or private. In particular, we demonstrate a form of robust principal component analysis that, under some circumstances, can provide an exponential speedup relative to robust methods used at present. To demonstrate this approach we introduce a linear combinations of unitaries Hamiltonian simulation method that we show functions when given an imprecise Hamiltonian oracle, which may be of independent interest. We also introduce a new quantum approach for bagging and boosting that can use quantum superposition over the classifiers or splits of the training set to aggregate over many more models than would be possible classically. Finally, we provide a private form of $k$–means clustering that can be used to prevent an all powerful adversary from learning more than a small fraction of a bit from any user. These examples show the role that quantum technologies can play in the security of ML and vice versa. This illustrates that quantum computing can provide useful advantages to machine learning apart from speedups.
Tasks	Quantum Machine Learning
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06652v1
PDF	http://arxiv.org/pdf/1711.06652v1.pdf
PWC	https://paperswithcode.com/paper/hardening-quantum-machine-learning-against
Repo
Framework