July 28, 2019

2918 words 14 mins read

Paper Group ANR 205

Bipartite Graph Matching for Keyframe Summary Evaluation. A recommender system to restore images with impulse noise. Warped-Linear Models for Time Series Classification. Semi-analytical approximations to statistical moments of sigmoid and softmax mappings of normal variables. On Learning Mixtures of Well-Separated Gaussians. Fiber-Flux Diffusion De …

Bipartite Graph Matching for Keyframe Summary Evaluation


Title	Bipartite Graph Matching for Keyframe Summary Evaluation
Authors	Iain A. D. Gunn, Ludmila I. Kuncheva, Paria Yousefi
Abstract	A keyframe summary, or “static storyboard”, is a collection of frames from a video designed to summarise its semantic content. Many algorithms have been proposed to extract such summaries automatically. How best to evaluate these outputs is an important but little-discussed question. We review the current methods for matching frames between two summaries in the formalism of graph theory. Our analysis revealed different behaviours of these methods, which we illustrate with a number of case studies. Based on the results, we recommend a greedy matching algorithm due to Kannappan et al.
Tasks	Graph Matching
Published	2017-12-19
URL	http://arxiv.org/abs/1712.06914v1
PDF	http://arxiv.org/pdf/1712.06914v1.pdf
PWC	https://paperswithcode.com/paper/bipartite-graph-matching-for-keyframe-summary
Repo
Framework

A recommender system to restore images with impulse noise


Title	A recommender system to restore images with impulse noise
Authors	Alfredo Nava-Tudela
Abstract	We build a collaborative filtering recommender system to restore images with impulse noise for which the noisy pixels have been previously identified. We define this recommender system in terms of a new color image representation using three matrices that depend on the noise-free pixels of the image to restore, and two parameters: $k$, the number of features; and $\lambda$, the regularization factor. We perform experiments on a well known image database to test our algorithm and we provide image quality statistics for the results obtained. We discuss the roles of bias and variance in the performance of our algorithm as determined by the values of $k$ and $\lambda$, and provide guidance on how to choose the values of these parameters. Finally, we discuss the possibility of using our collaborative filtering recommender system to perform image inpainting and super-resolution.
Tasks	Image Inpainting, Recommendation Systems, Super-Resolution
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07679v1
PDF	http://arxiv.org/pdf/1702.07679v1.pdf
PWC	https://paperswithcode.com/paper/a-recommender-system-to-restore-images-with
Repo
Framework

Warped-Linear Models for Time Series Classification


Title	Warped-Linear Models for Time Series Classification
Authors	Brijnesh J. Jain
Abstract	This article proposes and studies warped-linear models for time series classification. The proposed models are time-warp invariant analogues of linear models. Their construction is in line with time series averaging and extensions of k-means and learning vector quantization to dynamic time warping (DTW) spaces. The main theoretical result is that warped-linear models correspond to polyhedral classifiers in Euclidean spaces. This result simplifies the analysis of time-warp invariant models by reducing to max-linear functions. We exploit this relationship and derive solutions to the label-dependency problem and the problem of learning warped-linear models. Empirical results on time series classification suggest that warped-linear functions better trade solution quality against computation time than nearest-neighbor and prototype-based methods.
Tasks	Quantization, Time Series, Time Series Averaging, Time Series Classification
Published	2017-11-24
URL	http://arxiv.org/abs/1711.09156v1
PDF	http://arxiv.org/pdf/1711.09156v1.pdf
PWC	https://paperswithcode.com/paper/warped-linear-models-for-time-series
Repo
Framework

Semi-analytical approximations to statistical moments of sigmoid and softmax mappings of normal variables


Title	Semi-analytical approximations to statistical moments of sigmoid and softmax mappings of normal variables
Authors	Jean Daunizeau
Abstract	This note is concerned with accurate and computationally efficient approximations of moments of Gaussian random variables passed through sigmoid or softmax mappings. These approximations are semi-analytical (i.e. they involve the numerical adjustment of parametric forms) and highly accurate (they yield 5% error at most). We also highlight a few niche applications of these approximations, which arise in the context of, e.g., drift-diffusion models of decision making or non-parametric data clustering approaches. We provide these as examples of efficient alternatives to more tedious derivations that would be needed if one was to approach the underlying mathematical issues in a more formal way. We hope that this technical note will be helpful to modellers facing similar mathematical issues, although maybe stemming from different academic prospects.
Tasks	Decision Making
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00091v2
PDF	http://arxiv.org/pdf/1703.00091v2.pdf
PWC	https://paperswithcode.com/paper/semi-analytical-approximations-to-statistical
Repo
Framework

On Learning Mixtures of Well-Separated Gaussians


Title	On Learning Mixtures of Well-Separated Gaussians
Authors	Oded Regev, Aravindan Vijayaraghavan
Abstract	We consider the problem of efficiently learning mixtures of a large number of spherical Gaussians, when the components of the mixture are well separated. In the most basic form of this problem, we are given samples from a uniform mixture of $k$ standard spherical Gaussians, and the goal is to estimate the means up to accuracy $\delta$ using $poly(k,d, 1/\delta)$ samples. In this work, we study the following question: what is the minimum separation needed between the means for solving this task? The best known algorithm due to Vempala and Wang [JCSS 2004] requires a separation of roughly $\min{k,d}^{1/4}$. On the other hand, Moitra and Valiant [FOCS 2010] showed that with separation $o(1)$, exponentially many samples are required. We address the significant gap between these two bounds, by showing the following results. 1. We show that with separation $o(\sqrt{\log k})$, super-polynomially many samples are required. In fact, this holds even when the $k$ means of the Gaussians are picked at random in $d=O(\log k)$ dimensions. 2. We show that with separation $\Omega(\sqrt{\log k})$, $poly(k,d,1/\delta)$ samples suffice. Note that the bound on the separation is independent of $\delta$. This result is based on a new and efficient “accuracy boosting” algorithm that takes as input coarse estimates of the true means and in time $poly(k,d, 1/\delta)$ outputs estimates of the means up to arbitrary accuracy $\delta$ assuming the separation between the means is $\Omega(\min{\sqrt{\log k},\sqrt{d}})$ (independently of $\delta$). We also present a computationally efficient algorithm in $d=O(1)$ dimensions with only $\Omega(\sqrt{d})$ separation. These results together essentially characterize the optimal order of separation between components that is needed to learn a mixture of $k$ spherical Gaussians with polynomial samples.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11592v1
PDF	http://arxiv.org/pdf/1710.11592v1.pdf
PWC	https://paperswithcode.com/paper/on-learning-mixtures-of-well-separated
Repo
Framework

Fiber-Flux Diffusion Density for White Matter Tracts Analysis: Application to Mild Anomalies Localization in Contact Sports Players


Title	Fiber-Flux Diffusion Density for White Matter Tracts Analysis: Application to Mild Anomalies Localization in Contact Sports Players
Authors	Itay Benou, Ronel Veksler, Alon Friedman, Tammy Riklin Raviv
Abstract	We present the concept of fiber-flux density for locally quantifying white matter (WM) fiber bundles. By combining scalar diffusivity measures (e.g., fractional anisotropy) with fiber-flux measurements, we define new local descriptors called Fiber-Flux Diffusion Density (FFDD) vectors. Applying each descriptor throughout fiber bundles allows along-tract coupling of a specific diffusion measure with geometrical properties, such as fiber orientation and coherence. A key step in the proposed framework is the construction of an FFDD dissimilarity measure for sub-voxel alignment of fiber bundles, based on the fast marching method (FMM). The obtained aligned WM tract-profiles enable meaningful inter-subject comparisons and group-wise statistical analysis. We demonstrate our method using two different datasets of contact sports players. Along-tract pairwise comparison as well as group-wise analysis, with respect to non-player healthy controls, reveal significant and spatially-consistent FFDD anomalies. Comparing our method with along-tract FA analysis shows improved sensitivity to subtle structural anomalies in football players over standard FA measurements.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06122v1
PDF	http://arxiv.org/pdf/1709.06122v1.pdf
PWC	https://paperswithcode.com/paper/fiber-flux-diffusion-density-for-white-matter
Repo
Framework

The Riemannian Geometry of Deep Generative Models


Title	The Riemannian Geometry of Deep Generative Models
Authors	Hang Shao, Abhishek Kumar, P. Thomas Fletcher
Abstract	Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate the Riemannian geometry of these generated manifolds. First, we develop efficient algorithms for computing geodesic curves, which provide an intrinsic notion of distance between points on the manifold. Second, we develop an algorithm for parallel translation of a tangent vector along a path on the manifold. We show how parallel translation can be used to generate analogies, i.e., to transport a change in one data point into a semantically similar change of another data point. Our experiments on real image data show that the manifolds learned by deep generative models, while nonlinear, are surprisingly close to zero curvature. The practical implication is that linear paths in the latent space closely approximate geodesics on the generated manifold. However, further investigation into this phenomenon is warranted, to identify if there are other architectures or datasets where curvature plays a more prominent role. We believe that exploring the Riemannian geometry of deep generative models, using the tools developed in this paper, will be an important step in understanding the high-dimensional, nonlinear spaces these models learn.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.08014v1
PDF	http://arxiv.org/pdf/1711.08014v1.pdf
PWC	https://paperswithcode.com/paper/the-riemannian-geometry-of-deep-generative
Repo
Framework

A Linear Extrinsic Calibration of Kaleidoscopic Imaging System from Single 3D Point


Title	A Linear Extrinsic Calibration of Kaleidoscopic Imaging System from Single 3D Point
Authors	Kosuke Takahashi, Akihiro Miyata, Shohei Nobuhara, Takashi Matsuyama
Abstract	This paper proposes a new extrinsic calibration of kaleidoscopic imaging system by estimating normals and distances of the mirrors. The problem to be solved in this paper is a simultaneous estimation of all mirror parameters consistent throughout multiple reflections. Unlike conventional methods utilizing a pair of direct and mirrored images of a reference 3D object to estimate the parameters on a per-mirror basis, our method renders the simultaneous estimation problem into solving a linear set of equations. The key contribution of this paper is to introduce a linear estimation of multiple mirror parameters from kaleidoscopic 2D projections of a single 3D point of unknown geometry. Evaluations with synthesized and real images demonstrate the performance of the proposed algorithm in comparison with conventional methods.
Tasks	Calibration
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02826v3
PDF	http://arxiv.org/pdf/1703.02826v3.pdf
PWC	https://paperswithcode.com/paper/a-linear-extrinsic-calibration-of
Repo
Framework

A Practical Method for Solving Contextual Bandit Problems Using Decision Trees


Title	A Practical Method for Solving Contextual Bandit Problems Using Decision Trees
Authors	Adam N. Elmachtoub, Ryan McNellis, Sechan Oh, Marek Petrik
Abstract	Many efficient algorithms with strong theoretical guarantees have been proposed for the contextual multi-armed bandit problem. However, applying these algorithms in practice can be difficult because they require domain expertise to build appropriate features and to tune their parameters. We propose a new method for the contextual bandit problem that is simple, practical, and can be applied with little or no domain expertise. Our algorithm relies on decision trees to model the context-reward relationship. Decision trees are non-parametric, interpretable, and work well without hand-crafted features. To guide the exploration-exploitation trade-off, we use a bootstrapping approach which abstracts Thompson sampling to non-Bayesian settings. We also discuss several computational heuristics and demonstrate the performance of our method on several datasets.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04687v2
PDF	http://arxiv.org/pdf/1706.04687v2.pdf
PWC	https://paperswithcode.com/paper/a-practical-method-for-solving-contextual
Repo
Framework

$ν$-net: Deep Learning for Generalized Biventricular Cardiac Mass and Function Parameters


Title	$ν$-net: Deep Learning for Generalized Biventricular Cardiac Mass and Function Parameters
Authors	Hinrich B Winther, Christian Hundt, Bertil Schmidt, Christoph Czerner, Johann Bauersachs, Frank Wacker, Jens Vogel-Claussen
Abstract	Background: Cardiac MRI derived biventricular mass and function parameters, such as end-systolic volume (ESV), end-diastolic volume (EDV), ejection fraction (EF), stroke volume (SV), and ventricular mass (VM) are clinically well established. Image segmentation can be challenging and time-consuming, due to the complex anatomy of the human heart. Objectives: This study introduces $\nu$-net (/nju:n$\varepsilon$t/) – a deep learning approach allowing for fully-automated high quality segmentation of right (RV) and left ventricular (LV) endocardium and epicardium for extraction of cardiac function parameters. Methods: A set consisting of 253 manually segmented cases has been used to train a deep neural network. Subsequently, the network has been evaluated on 4 different multicenter data sets with a total of over 1000 cases. Results: For LV EF the intraclass correlation coefficient (ICC) is 98, 95, and 80 % (95 %), and for RV EF 96, and 87 % (80 %) on the respective data sets (human expert ICCs reported in parenthesis). The LV VM ICC is 95, and 94 % (84 %), and the RV VM ICC is 83, and 83 % (54 %). This study proposes a simple adjustment procedure, allowing for the adaptation to distinct segmentation philosophies. $\nu$-net exhibits state of-the-art performance in terms of dice coefficient. Conclusions: Biventricular mass and function parameters can be determined reliably in high quality by applying a deep neural network for cardiac MRI segmentation, especially in the anatomically complex right ventricle. Adaption to individual segmentation styles by applying a simple adjustment procedure is viable, allowing for the processing of novel data without time-consuming additional training.
Tasks	Semantic Segmentation
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04397v1
PDF	http://arxiv.org/pdf/1706.04397v1.pdf
PWC	https://paperswithcode.com/paper/-net-deep-learning-for-generalized
Repo
Framework

Embedding Knowledge Graphs Based on Transitivity and Antisymmetry of Rules


Title	Embedding Knowledge Graphs Based on Transitivity and Antisymmetry of Rules
Authors	Mengya Wang, Hankui Zhuo, Huiling Zhu
Abstract	Representation learning of knowledge graphs encodes entities and relation types into a continuous low-dimensional vector space, learns embeddings of entities and relation types. Most existing methods only concentrate on knowledge triples, ignoring logic rules which contain rich background knowledge. Although there has been some work aiming at leveraging both knowledge triples and logic rules, they ignore the transitivity and antisymmetry of logic rules. In this paper, we propose a novel approach to learn knowledge representations with entities and ordered relations in knowledges and logic rules. The key idea is to integrate knowledge triples and logic rules, and approximately order the relation types in logic rules to utilize the transitivity and antisymmetry of logic rules. All entries of the embeddings of relation types are constrained to be non-negative. We translate the general constrained optimization problem into an unconstrained optimization problem to solve the non-negative matrix factorization. Experimental results show that our model significantly outperforms other baselines on knowledge graph completion task. It indicates that our model is capable of capturing the transitivity and antisymmetry information, which is significant when learning embeddings of knowledge graphs.
Tasks	Knowledge Graph Completion, Knowledge Graphs, Representation Learning
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07543v2
PDF	http://arxiv.org/pdf/1702.07543v2.pdf
PWC	https://paperswithcode.com/paper/embedding-knowledge-graphs-based-on
Repo
Framework

Recurrent Models for Situation Recognition


Title	Recurrent Models for Situation Recognition
Authors	Arun Mallya, Svetlana Lazebnik
Abstract	This work proposes Recurrent Neural Network (RNN) models to predict structured ‘image situations’ – actions and noun entities fulfilling semantic roles related to the action. In contrast to prior work relying on Conditional Random Fields (CRFs), we use a specialized action prediction network followed by an RNN for noun prediction. Our system obtains state-of-the-art accuracy on the challenging recent imSitu dataset, beating CRF-based models, including ones trained with additional data. Further, we show that specialized features learned from situation prediction can be transferred to the task of image captioning to more accurately describe human-object interactions.
Tasks	Human-Object Interaction Detection, Image Captioning
Published	2017-03-18
URL	http://arxiv.org/abs/1703.06233v2
PDF	http://arxiv.org/pdf/1703.06233v2.pdf
PWC	https://paperswithcode.com/paper/recurrent-models-for-situation-recognition
Repo
Framework

Fixed-point optimization of deep neural networks with adaptive step size retraining


Title	Fixed-point optimization of deep neural networks with adaptive step size retraining
Authors	Sungho Shin, Yoonho Boo, Wonyong Sung
Abstract	Fixed-point optimization of deep neural networks plays an important role in hardware based design and low-power implementations. Many deep neural networks show fairly good performance even with 2- or 3-bit precision when quantized weights are fine-tuned by retraining. We propose an improved fixedpoint optimization algorithm that estimates the quantization step size dynamically during the retraining. In addition, a gradual quantization scheme is also tested, which sequentially applies fixed-point optimizations from high- to low-precision. The experiments are conducted for feed-forward deep neural networks (FFDNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).
Tasks	Quantization
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08171v1
PDF	http://arxiv.org/pdf/1702.08171v1.pdf
PWC	https://paperswithcode.com/paper/fixed-point-optimization-of-deep-neural
Repo
Framework

Characterizing Sparse Connectivity Patterns in Neural Networks


Title	Characterizing Sparse Connectivity Patterns in Neural Networks
Authors	Sourya Dey, Kuan-Wen Huang, Peter A. Beerel, Keith M. Chugg
Abstract	We propose a novel way of reducing the number of parameters in the storage-hungry fully connected layers of a neural network by using pre-defined sparsity, where the majority of connections are absent prior to starting training. Our results indicate that convolutional neural networks can operate without any loss of accuracy at less than half percent classification layer connection density, or less than 5 percent overall network connection density. We also investigate the effects of pre-defining the sparsity of networks with only fully connected layers. Based on our sparsifying technique, we introduce the `scatter’ metric to characterize the quality of a particular connection pattern. As proof of concept, we show results on CIFAR, MNIST and a new dataset on classifying Morse code symbols, which highlights some interesting trends and limits of sparse connection patterns. \|
Tasks
Published	2017-11-06
URL	http://arxiv.org/abs/1711.02131v5
PDF	http://arxiv.org/pdf/1711.02131v5.pdf
PWC	https://paperswithcode.com/paper/characterizing-sparse-connectivity-patterns
Repo
Framework

Information Design in Crowdfunding under Thresholding Policies


Title	Information Design in Crowdfunding under Thresholding Policies
Authors	Wen Shen, Jacob W. Crandall, Ke Yan, Cristina V. Lopes
Abstract	Crowdfunding has emerged as a prominent way for entrepreneurs to secure funding without sophisticated intermediation. In crowdfunding, an entrepreneur often has to decide how to disclose the campaign status in order to collect as many contributions as possible. Such decisions are difficult to make primarily due to incomplete information. We propose information design as a tool to help the entrepreneur to improve revenue by influencing backers’ beliefs. We introduce a heuristic algorithm to dynamically compute information-disclosure policies for the entrepreneur, followed by an empirical evaluation to demonstrate its competitiveness over the widely-adopted immediate-disclosure policy. Our results demonstrate that the immediate-disclosure policy is not optimal when backers follow thresholding policies despite its ease of implementation. With appropriate heuristics, an entrepreneur can benefit from dynamic information disclosure. Our work sheds light on information design in a dynamic setting where agents make decisions using thresholding policies.
Tasks
Published	2017-09-12
URL	http://arxiv.org/abs/1709.04049v5
PDF	http://arxiv.org/pdf/1709.04049v5.pdf
PWC	https://paperswithcode.com/paper/information-design-in-crowdfunding-under
Repo
Framework