July 28, 2019

2858 words 14 mins read

Paper Group ANR 194

Structural Learning and Integrative Decomposition of Multi-View Data. Communication-efficient Algorithm for Distributed Sparse Learning via Two-way Truncation. Learning to Synthesize a 4D RGBD Light Field from a Single Image. Multi-Resolution Dual-Tree Wavelet Scattering Network for Signal Classification. Balanced Quantization: An Effective and Eff …

Structural Learning and Integrative Decomposition of Multi-View Data


Title	Structural Learning and Integrative Decomposition of Multi-View Data
Authors	Irina Gaynanova, Gen Li
Abstract	The increased availability of the multi-view data (data on the same samples from multiple sources) has led to strong interest in models based on low-rank matrix factorizations. These models represent each data view via shared and individual components, and have been successfully applied for exploratory dimension reduction, association analysis between the views, and further learning tasks such as consensus clustering. Despite these advances, there remain significant challenges in modeling partially-shared components, and identifying the number of components of each type (shared/partially-shared/individual). In this work, we formulate a novel linked component model that directly incorporates partially-shared structures. We call this model SLIDE for Structural Learning and Integrative DEcomposition of multi-view data. We prove the existence of SLIDE decomposition and explicitly characterize the identifiability conditions. The proposed model fitting and selection techniques allow for joint identification of the number of components of each type, in contrast to existing sequential approaches. In our empirical studies, SLIDE demonstrates excellent performance in both signal estimation and component selection. We further illustrate the methodology on the breast cancer data from The Cancer Genome Atlas repository.
Tasks	Dimensionality Reduction
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06573v1
PDF	http://arxiv.org/pdf/1707.06573v1.pdf
PWC	https://paperswithcode.com/paper/structural-learning-and-integrative
Repo
Framework

Communication-efficient Algorithm for Distributed Sparse Learning via Two-way Truncation


Title	Communication-efficient Algorithm for Distributed Sparse Learning via Two-way Truncation
Authors	Jineng Ren, Jarvis Haupt
Abstract	We propose a communicationally and computationally efficient algorithm for high-dimensional distributed sparse learning. At each iteration, local machines compute the gradient on local data and the master machine solves one shifted $l_1$ regularized minimization problem. The communication cost is reduced from constant times of the dimension number for the state-of-the-art algorithm to constant times of the sparsity number via Two-way Truncation procedure. Theoretically, we prove that the estimation error of the proposed algorithm decreases exponentially and matches that of the centralized method under mild assumptions. Extensive experiments on both simulated data and real data verify that the proposed algorithm is efficient and has performance comparable with the centralized method on solving high-dimensional sparse learning problems.
Tasks	Sparse Learning
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00537v2
PDF	http://arxiv.org/pdf/1709.00537v2.pdf
PWC	https://paperswithcode.com/paper/communication-efficient-algorithm-for
Repo
Framework

Learning to Synthesize a 4D RGBD Light Field from a Single Image


Title	Learning to Synthesize a 4D RGBD Light Field from a Single Image
Authors	Pratul P. Srinivasan, Tongzhou Wang, Ashwin Sreelal, Ravi Ramamoorthi, Ren Ng
Abstract	We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction). For training, we introduce the largest public light field dataset, consisting of over 3300 plenoptic camera light fields of scenes containing flowers and plants. Our synthesis pipeline consists of a convolutional neural network (CNN) that estimates scene geometry, a stage that renders a Lambertian light field using that geometry, and a second CNN that predicts occluded rays and non-Lambertian effects. Our algorithm builds on recent view synthesis methods, but is unique in predicting RGBD for each light field ray and improving unsupervised single image depth estimation by enforcing consistency of ray depths that should intersect the same scene point. Please see our supplementary video at https://youtu.be/yLCvWoQLnms
Tasks	Depth Estimation
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03292v1
PDF	http://arxiv.org/pdf/1708.03292v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-synthesize-a-4d-rgbd-light-field
Repo
Framework

Multi-Resolution Dual-Tree Wavelet Scattering Network for Signal Classification


Title	Multi-Resolution Dual-Tree Wavelet Scattering Network for Signal Classification
Authors	Amarjot Singh, Nick Kingsbury
Abstract	This paper introduces a Deep Scattering network that utilizes Dual-Tree complex wavelets to extract translation invariant representations from an input signal. The computationally efficient Dual-Tree wavelets decompose the input signal into densely spaced representations over scales. Translation invariance is introduced in the representations by applying a non-linearity over a region followed by averaging. The discriminatory information in the densely spaced, locally smooth, signal representations aids the learning of the classifier. The proposed network is shown to outperform Mallat’s ScatterNet on four datasets with different modalities on classification accuracy.
Tasks
Published	2017-02-10
URL	http://arxiv.org/abs/1702.03345v1
PDF	http://arxiv.org/pdf/1702.03345v1.pdf
PWC	https://paperswithcode.com/paper/multi-resolution-dual-tree-wavelet-scattering
Repo
Framework

Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks


Title	Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks
Authors	Shuchang Zhou, Yuzhi Wang, He Wen, Qinyao He, Yuheng Zou
Abstract	Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and activations are uniformly quantized, such that the multiplications and additions can be accelerated by bitwise operations. However, distributions of parameters in Neural Networks are often imbalanced, such that the uniform quantization determined from extremal values may under utilize available bitwidth. In this paper, we propose a novel quantization method that can ensure the balance of distributions of quantized values. Our method first recursively partitions the parameters by percentiles into balanced bins, and then applies uniform quantization. We also introduce computationally cheaper approximations of percentiles to reduce the computation overhead introduced. Overall, our method improves the prediction accuracies of QNNs without introducing extra computation during inference, has negligible impact on training speed, and is applicable to both Convolutional Neural Networks and Recurrent Neural Networks. Experiments on standard datasets including ImageNet and Penn Treebank confirm the effectiveness of our method. On ImageNet, the top-5 error rate of our 4-bit quantized GoogLeNet model is 12.7%, which is superior to the state-of-the-arts of QNNs.
Tasks	Quantization
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07145v1
PDF	http://arxiv.org/pdf/1706.07145v1.pdf
PWC	https://paperswithcode.com/paper/balanced-quantization-an-effective-and
Repo
Framework

Sparse Phase Retrieval via Sparse PCA Despite Model Misspecification: A Simplified and Extended Analysis


Title	Sparse Phase Retrieval via Sparse PCA Despite Model Misspecification: A Simplified and Extended Analysis
Authors	Yan Shuo Tan
Abstract	We consider the problem of high-dimensional misspecified phase retrieval. This is where we have an $s$-sparse signal vector $\mathbf{x}$ in $\mathbb{R}^n$, which we wish to recover using sampling vectors $\textbf{a}_1,\ldots,\textbf{a}_m$, and measurements $y_1,\ldots,y_m$, which are related by the equation $f(\left<\textbf{a}i,\textbf{x}\right>) = y_i$. Here, $f$ is an unknown link function satisfying a positive correlation with the quadratic function. This problem was analyzed in a recent paper by Neykov, Wang and Liu, who provided recovery guarantees for a two-stage algorithm with sample complexity $m = O(s^2\log n)$. In this paper, we show that the first stage of their algorithm suffices for signal recovery with the same sample complexity, and extend the analysis to non-Gaussian measurements. Furthermore, we show how the algorithm can be generalized to recover a signal vector $\textbf{x}*$ efficiently given geometric prior information other than sparsity.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04106v2
PDF	http://arxiv.org/pdf/1712.04106v2.pdf
PWC	https://paperswithcode.com/paper/sparse-phase-retrieval-via-sparse-pca-despite
Repo
Framework

Subjectively Interesting Subgroup Discovery on Real-valued Targets


Title	Subjectively Interesting Subgroup Discovery on Real-valued Targets
Authors	Jefrey Lijffijt, Bo Kang, Wouter Duivesteijn, Kai Puolamäki, Emilia Oikarinen, Tijl De Bie
Abstract	Deriving insights from high-dimensional data is one of the core problems in data mining. The difficulty mainly stems from the fact that there are exponentially many variable combinations to potentially consider, and there are infinitely many if we consider weighted combinations, even for linear combinations. Hence, an obvious question is whether we can automate the search for interesting patterns and visualizations. In this paper, we consider the setting where a user wants to learn as efficiently as possible about real-valued attributes. For example, to understand the distribution of crime rates in different geographic areas in terms of other (numerical, ordinal and/or categorical) variables that describe the areas. We introduce a method to find subgroups in the data that are maximally informative (in the formal Information Theoretic sense) with respect to a single or set of real-valued target attributes. The subgroup descriptions are in terms of a succinct set of arbitrarily-typed other attributes. The approach is based on the Subjective Interestingness framework FORSIED to enable the use of prior knowledge when finding most informative non-redundant patterns, and hence the method also supports iterative data mining.
Tasks
Published	2017-10-12
URL	http://arxiv.org/abs/1710.04521v1
PDF	http://arxiv.org/pdf/1710.04521v1.pdf
PWC	https://paperswithcode.com/paper/subjectively-interesting-subgroup-discovery
Repo
Framework

Guaranteed Outlier Removal for Point Cloud Registration with Correspondences


Title	Guaranteed Outlier Removal for Point Cloud Registration with Correspondences
Authors	Álvaro Parra Bustos, Tat-Jun Chin
Abstract	An established approach for 3D point cloud registration is to estimate the registration function from 3D keypoint correspondences. Typically, a robust technique is required to conduct the estimation, since there are false correspondences or outliers. Current 3D keypoint techniques are much less accurate than their 2D counterparts, thus they tend to produce extremely high outlier rates. A large number of putative correspondences must thus be extracted to ensure that sufficient good correspondences are available. Both factors (high outlier rates, large data sizes) however cause existing robust techniques to require very high computational cost. In this paper, we present a novel preprocessing method called \emph{guaranteed outlier removal} for point cloud registration. Our method reduces the input to a smaller set, in a way that any rejected correspondence is guaranteed to not exist in the globally optimal solution. The reduction is performed using purely geometric operations which are deterministic and fast. Our method significantly reduces the population of outliers, such that further optimization can be performed quickly. Further, since only true outliers are removed, the globally optimal solution is preserved. On various synthetic and real data experiments, we demonstrate the effectiveness of our preprocessing method. Demo code is available as supplementary material.
Tasks	Point Cloud Registration
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10209v1
PDF	http://arxiv.org/pdf/1711.10209v1.pdf
PWC	https://paperswithcode.com/paper/guaranteed-outlier-removal-for-point-cloud
Repo
Framework

SPARK: Static Program Analysis Reasoning and Retrieving Knowledge


Title	SPARK: Static Program Analysis Reasoning and Retrieving Knowledge
Authors	Wasuwee Sodsong, Bernhard Scholz, Sanjay Chawla
Abstract	Program analysis is a technique to reason about programs without executing them, and it has various applications in compilers, integrated development environments, and security. In this work, we present a machine learning pipeline that induces a security analyzer for programs by example. The security analyzer determines whether a program is either secure or insecure based on symbolic rules that were deduced by our machine learning pipeline. The machine pipeline is two-staged consisting of a Recurrent Neural Networks (RNN) and an Extractor that converts an RNN to symbolic rules. To evaluate the quality of the learned symbolic rules, we propose a sampling-based similarity measurement between two infinite regular languages. We conduct a case study using real-world data. In this work, we discuss the limitations of existing techniques and possible improvements in the future. The results show that with sufficient training data and a fair distribution of program paths it is feasible to deducing symbolic security rules for the OpenJDK library with millions lines of code.
Tasks
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01024v1
PDF	http://arxiv.org/pdf/1711.01024v1.pdf
PWC	https://paperswithcode.com/paper/spark-static-program-analysis-reasoning-and
Repo
Framework

A new take on measuring relative nutritional density: The feasibility of using a deep neural network to assess commercially-prepared pureed food concentrations


Title	A new take on measuring relative nutritional density: The feasibility of using a deep neural network to assess commercially-prepared pureed food concentrations
Authors	Kaylen J. Pfisterer, Robert Amelard, Audrey G. Chung, Alexander Wong
Abstract	Dysphagia affects 590 million people worldwide and increases risk for malnutrition. Pureed food may reduce choking, however preparation differences impact nutrient density making quality assurance necessary. This paper is the first study to investigate the feasibility of computational pureed food nutritional density analysis using an imaging system. Motivated by a theoretical optical dilution model, a novel deep neural network (DNN) was evaluated using 390 samples from thirteen types of commercially prepared purees at five dilutions. The DNN predicted relative concentration of the puree sample (20%, 40%, 60%, 80%, 100% initial concentration). Data were captured using same-side reflectance of multispectral imaging data at different polarizations at three exposures. Experimental results yielded an average top-1 prediction accuracy of 92.2+/-0.41% with sensitivity and specificity of 83.0+/-15.0% and 95.0+/-4.8%, respectively. This DNN imaging system for nutrient density analysis of pureed food shows promise as a novel tool for nutrient quality assurance.
Tasks
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07312v2
PDF	http://arxiv.org/pdf/1707.07312v2.pdf
PWC	https://paperswithcode.com/paper/a-new-take-on-measuring-relative-nutritional
Repo
Framework

Micro-Expression Spotting: A Benchmark


Title	Micro-Expression Spotting: A Benchmark
Authors	Xiaopeng Hong, Thuong-Khanh Tran, Guoying Zhao
Abstract	Micro-expressions are rapid and involuntary facial expressions, which indicate the suppressed or concealed emotions. Recently, the research on automatic micro-expression (ME) spotting obtains increasing attention. ME spotting is a crucial step prior to further ME analysis tasks. The spotting results can be used as important cues to assist many other human-oriented tasks and thus have many potential applications. In this paper, by investigating existing ME spotting methods, we recognize the immediacy of standardizing the performance evaluation of micro-expression spotting methods. To this end, we construct a micro-expression spotting benchmark (MESB). Firstly, we set up a sliding window based multi-scale evaluation framework. Secondly, we introduce a series of protocols. Thirdly, we also provide baseline results of popular methods. The MESB facilitates the research on ME spotting with fairer and more comprehensive evaluation and also enables to leverage the cutting-edge machine learning tools widely.
Tasks
Published	2017-10-08
URL	http://arxiv.org/abs/1710.02820v1
PDF	http://arxiv.org/pdf/1710.02820v1.pdf
PWC	https://paperswithcode.com/paper/micro-expression-spotting-a-benchmark
Repo
Framework

Teaching Compositionality to CNNs


Title	Teaching Compositionality to CNNs
Authors	Austin Stone, Huayan Wang, Michael Stark, Yi Liu, D. Scott Phoenix, Dileep George
Abstract	Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting and training CNNs so that their learned features are compositional. It encourages networks to form representations that disentangle objects from their surroundings and from each other, thereby promoting better generalization. Our method is agnostic to the specific details of the underlying CNN to which it is applied and can in principle be used with any CNN. As we show in our experiments, the learned representations lead to feature activations that are more localized and improve performance over non-compositional baselines in object recognition tasks.
Tasks	Object Recognition
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04313v1
PDF	http://arxiv.org/pdf/1706.04313v1.pdf
PWC	https://paperswithcode.com/paper/teaching-compositionality-to-cnns
Repo
Framework

Deformable Deep Convolutional Generative Adversarial Network in Microwave Based Hand Gesture Recognition System


Title	Deformable Deep Convolutional Generative Adversarial Network in Microwave Based Hand Gesture Recognition System
Authors	Jiajun Zhang, Zhiguo Shi
Abstract	Traditional vision-based hand gesture recognition systems is limited under dark circumstances. In this paper, we build a hand gesture recognition system based on microwave transceiver and deep learning algorithm. A Doppler radar sensor with dual receiving channels at 5.8GHz is used to acquire a big database of hand gestures signals. The received hand gesture signals are then processed with time-frequency analysis. Based on these big databases of hand gesture, we propose a new machine learning architecture called deformable deep convolutional generative adversarial network. Experimental results show the new architecture can upgrade the recognition rate by 10% and the deformable kernel can reduce the testing time cost by 30%.
Tasks	Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01968v2
PDF	http://arxiv.org/pdf/1711.01968v2.pdf
PWC	https://paperswithcode.com/paper/deformable-deep-convolutional-generative
Repo
Framework

Image Projective Invariants


Title	Image Projective Invariants
Authors	Erbo Li, Hanlin Mo, Dong Xu, Hua Li
Abstract	In this paper, we propose relative projective differential invariants (RPDIs) which are invariant to general projective transformations. By using RPDIs and the structural frame of integral invariant, projective weighted moment invariants (PIs) can be constructed very easily. It is first proved that a kind of projective invariants exists in terms of weighted integration of images, with relative differential invariants as the weight functions. Then, some simple instances of PIs are given. In order to ensure the stability and discriminability of PIs, we discuss how to calculate partial derivatives of discrete images more accurately. Since the number of pixels in discrete images before and after the geometric transformation may be different, we design the method to normalize the number of pixels. These ways enhance the performance of PIs. Finally, we carry out some experiments based on synthetic and real image datasets. We choose commonly used moment invariants for comparison. The results indicate that PIs have better performance than other moment invariants in image retrieval and classification. With PIs, one can compare the similarity between images under the projective transformation without knowing the parameters of the transformation, which provides a good tool to shape analysis in image processing, computer vision and pattern recognition.
Tasks	Image Retrieval
Published	2017-07-19
URL	http://arxiv.org/abs/1707.05950v1
PDF	http://arxiv.org/pdf/1707.05950v1.pdf
PWC	https://paperswithcode.com/paper/image-projective-invariants
Repo
Framework

Hierarchical Multinomial-Dirichlet model for the estimation of conditional probability tables


Title	Hierarchical Multinomial-Dirichlet model for the estimation of conditional probability tables
Authors	L. Azzimonti, G. Corani, M. Zaffalon
Abstract	We present a novel approach for estimating conditional probability tables, based on a joint, rather than independent, estimate of the conditional distributions belonging to the same table. We derive exact analytical expressions for the estimators and we analyse their properties both analytically and via simulation. We then apply this method to the estimation of parameters in a Bayesian network. Given the structure of the network, the proposed approach better estimates the joint distribution and significantly improves the classification performance with respect to traditional approaches.
Tasks
Published	2017-08-23
URL	http://arxiv.org/abs/1708.06935v1
PDF	http://arxiv.org/pdf/1708.06935v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-multinomial-dirichlet-model-for
Repo
Framework