May 6, 2019

2855 words 14 mins read

Paper Group ANR 424

Multi-stage Object Detection with Group Recursive Learning. Multi-Information Source Optimization. A Critical Examination of RESCAL for Completion of Knowledge Bases with Transitive Relations. A Bayesian approach to type-specific conic fitting. Context and Interference Effects in the Combinations of Natural Concepts. 1.5 billion words Arabic Corpus …

Multi-stage Object Detection with Group Recursive Learning


Title	Multi-stage Object Detection with Group Recursive Learning
Authors	Jianan Li, Xiaodan Liang, Jianshu Li, Tingfa Xu, Jiashi Feng, Shuicheng Yan
Abstract	Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are often ignored, which are actually useful for more accurate object detection. In this work, we propose a new EM-like group recursive learning approach to iteratively refine object proposals by incorporating such context of surrounding proposals and provide an optimal spatial configuration of object detections. In addition, we propose to incorporate the weakly-supervised object segmentation cues and region-based object detection into a multi-stage architecture in order to fully exploit the learned segmentation features for better object detection in an end-to-end way. The proposed architecture consists of three cascaded networks which respectively learn to perform weakly-supervised object segmentation, object proposal generation and recursive detection refinement. Combining the group recursive learning and the multi-stage architecture provides competitive mAPs of 78.6% and 74.9% on the PASCAL VOC2007 and VOC2012 datasets respectively, which outperforms many well-established baselines [10] [20] significantly.
Tasks	Object Detection, Object Proposal Generation, Semantic Segmentation
Published	2016-08-18
URL	http://arxiv.org/abs/1608.05159v1
PDF	http://arxiv.org/pdf/1608.05159v1.pdf
PWC	https://paperswithcode.com/paper/multi-stage-object-detection-with-group
Repo
Framework

Multi-Information Source Optimization


Title	Multi-Information Source Optimization
Authors	Matthias Poloczek, Jialei Wang, Peter I. Frazier
Abstract	We consider Bayesian optimization of an expensive-to-evaluate black-box objective function, where we also have access to cheaper approximations of the objective. In general, such approximations arise in applications such as reinforcement learning, engineering, and the natural sciences, and are subject to an inherent, unknown bias. This model discrepancy is caused by an inadequate internal model that deviates from reality and can vary over the domain, making the utilization of these approximations a non-trivial task. We present a novel algorithm that provides a rigorous mathematical treatment of the uncertainties arising from model discrepancies and noisy observations. Its optimization decisions rely on a value of information analysis that extends the Knowledge Gradient factor to the setting of multiple information sources that vary in cost: each sampling decision maximizes the predicted benefit per unit cost. We conduct an experimental evaluation that demonstrates that the method consistently outperforms other state-of-the-art techniques: it finds designs of considerably higher objective value and additionally inflicts less cost in the exploration process.
Tasks
Published	2016-03-01
URL	http://arxiv.org/abs/1603.00389v2
PDF	http://arxiv.org/pdf/1603.00389v2.pdf
PWC	https://paperswithcode.com/paper/multi-information-source-optimization
Repo
Framework

A Critical Examination of RESCAL for Completion of Knowledge Bases with Transitive Relations


Title	A Critical Examination of RESCAL for Completion of Knowledge Bases with Transitive Relations
Authors	Pushpendre Rastogi, Benjamin Van Durme
Abstract	Link prediction in large knowledge graphs has received a lot of attention recently because of its importance for inferring missing relations and for completing and improving noisily extracted knowledge graphs. Over the years a number of machine learning researchers have presented various models for predicting the presence of missing relations in a knowledge base. Although all the previous methods are presented with empirical results that show high performance on select datasets, there is almost no previous work on understanding the connection between properties of a knowledge base and the performance of a model. In this paper we analyze the RESCAL method and prove that it can not encode asymmetric transitive relations in knowledge bases.
Tasks	Knowledge Graphs, Link Prediction
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04672v1
PDF	http://arxiv.org/pdf/1605.04672v1.pdf
PWC	https://paperswithcode.com/paper/a-critical-examination-of-rescal-for
Repo
Framework

A Bayesian approach to type-specific conic fitting


Title	A Bayesian approach to type-specific conic fitting
Authors	Matthew Collett
Abstract	A perturbative approach is used to quantify the effect of noise in data points on fitted parameters in a general homogeneous linear model, and the results applied to the case of conic sections. There is an optimal choice of normalisation that minimises bias, and iteration with the correct reweighting significantly improves statistical reliability. By conditioning on an appropriate prior, an unbiased type-specific fit can be obtained. Error estimates for the conic coefficients may also be used to obtain both bias corrections and confidence intervals for other curve parameters.
Tasks
Published	2016-11-19
URL	http://arxiv.org/abs/1611.06296v1
PDF	http://arxiv.org/pdf/1611.06296v1.pdf
PWC	https://paperswithcode.com/paper/a-bayesian-approach-to-type-specific-conic
Repo
Framework

Context and Interference Effects in the Combinations of Natural Concepts


Title	Context and Interference Effects in the Combinations of Natural Concepts
Authors	Diederik Aerts, Jonito Aerts Arguëlles, Lester Beltran, Lyneth Beltran, Massimiliano Sassoli de Bianchi, Sandro Sozzo, Tomas Veloz
Abstract	The mathematical formalism of quantum theory exhibits significant effectiveness when applied to cognitive phenomena that have resisted traditional (set theoretical) modeling. Relying on a decade of research on the operational foundations of micro-physical and conceptual entities, we present a theoretical framework for the representation of concepts and their conjunctions and disjunctions that uses the quantum formalism. This framework provides a unified solution to the ‘conceptual combinations problem’ of cognitive psychology, explaining the observed deviations from classical (Boolean, fuzzy set and Kolmogorovian) structures in terms of genuine quantum effects. In particular, natural concepts ‘interfere’ when they combine to form more complex conceptual entities, and they also exhibit a ‘quantum-type context-dependence’, which are responsible of the ‘over- and under-extension’ that are systematically observed in experiments on membership judgments.
Tasks
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06038v1
PDF	http://arxiv.org/pdf/1612.06038v1.pdf
PWC	https://paperswithcode.com/paper/context-and-interference-effects-in-the
Repo
Framework

1.5 billion words Arabic Corpus


Title	1.5 billion words Arabic Corpus
Authors	Ibrahim Abu El-khair
Abstract	This study is an attempt to build a contemporary linguistic corpus for Arabic language. The corpus produced, is a text corpus includes more than five million newspaper articles. It contains over a billion and a half words in total, out of which, there is about three million unique words. The data were collected from newspaper articles in ten major news sources from eight Arabic countries, over a period of fourteen years. The corpus was encoded with two types of encoding, namely: UTF-8, and Windows CP-1256. Also it was marked with two mark-up languages, namely: SGML, and XML.
Tasks
Published	2016-11-12
URL	http://arxiv.org/abs/1611.04033v1
PDF	http://arxiv.org/pdf/1611.04033v1.pdf
PWC	https://paperswithcode.com/paper/15-billion-words-arabic-corpus
Repo
Framework

Iterative Learning of Answer Set Programs from Context Dependent Examples


Title	Iterative Learning of Answer Set Programs from Context Dependent Examples
Authors	Mark Law, Alessandra Russo, Krysia Broda
Abstract	In recent years, several frameworks and systems have been proposed that extend Inductive Logic Programming (ILP) to the Answer Set Programming (ASP) paradigm. In ILP, examples must all be explained by a hypothesis together with a given background knowledge. In existing systems, the background knowledge is the same for all examples; however, examples may be context-dependent. This means that some examples should be explained in the context of some information, whereas others should be explained in different contexts. In this paper, we capture this notion and present a context-dependent extension of the Learning from Ordered Answer Sets framework. In this extension, contexts can be used to further structure the background knowledge. We then propose a new iterative algorithm, ILASP2i, which exploits this feature to scale up the existing ILASP2 system to learning tasks with large numbers of examples. We demonstrate the gain in scalability by applying both algorithms to various learning tasks. Our results show that, compared to ILASP2, the newly proposed ILASP2i system can be two orders of magnitude faster and use two orders of magnitude less memory, whilst preserving the same average accuracy. This paper is under consideration for acceptance in TPLP.
Tasks
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01946v1
PDF	http://arxiv.org/pdf/1608.01946v1.pdf
PWC	https://paperswithcode.com/paper/iterative-learning-of-answer-set-programs
Repo
Framework

Embedded Line Scan Image Sensors: The Low Cost Alternative for High Speed Imaging


Title	Embedded Line Scan Image Sensors: The Low Cost Alternative for High Speed Imaging
Authors	Stef Van Wolputte, Wim Abbeloos, Stijn Helsen, Abdellatif Bey-Temsamani, Toon Goedemé
Abstract	In this paper we propose a low-cost high-speed imaging line scan system. We replace an expensive industrial line scan camera and illumination with a custom-built set-up of cheap off-the-shelf components, yielding a measurement system with comparative quality while costing about 20 times less. We use a low-cost linear (1D) image sensor, cheap optics including a LED-based or LASER-based lighting and an embedded platform to process the images. A step-by-step method to design such a custom high speed imaging system and select proper components is proposed. Simulations allowing to predict the final image quality to be obtained by the set-up has been developed. Finally, we applied our method in a lab, closely representing the real-life cases. Our results shows that our simulations are very accurate and that our low-cost line scan set-up acquired image quality compared to the high-end commercial vision system, for a fraction of the price.
Tasks
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02218v1
PDF	http://arxiv.org/pdf/1612.02218v1.pdf
PWC	https://paperswithcode.com/paper/embedded-line-scan-image-sensors-the-low-cost
Repo
Framework

Statistical and Computational Guarantees of Lloyd’s Algorithm and its Variants


Title	Statistical and Computational Guarantees of Lloyd’s Algorithm and its Variants
Authors	Yu Lu, Harrison H. Zhou
Abstract	Clustering is a fundamental problem in statistics and machine learning. Lloyd’s algorithm, proposed in 1957, is still possibly the most widely used clustering algorithm in practice due to its simplicity and empirical performance. However, there has been little theoretical investigation on the statistical and computational guarantees of Lloyd’s algorithm. This paper is an attempt to bridge this gap between practice and theory. We investigate the performance of Lloyd’s algorithm on clustering sub-Gaussian mixtures. Under an appropriate initialization for labels or centers, we show that Lloyd’s algorithm converges to an exponentially small clustering error after an order of $\log n$ iterations, where $n$ is the sample size. The error rate is shown to be minimax optimal. For the two-mixture case, we only require the initializer to be slightly better than random guess. In addition, we extend the Lloyd’s algorithm and its analysis to community detection and crowdsourcing, two problems that have received a lot of attention recently in statistics and machine learning. Two variants of Lloyd’s algorithm are proposed respectively for community detection and crowdsourcing. On the theoretical side, we provide statistical and computational guarantees of the two algorithms, and the results improve upon some previous signal-to-noise ratio conditions in literature for both problems. Experimental results on simulated and real data sets demonstrate competitive performance of our algorithms to the state-of-the-art methods.
Tasks	Community Detection
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02099v1
PDF	http://arxiv.org/pdf/1612.02099v1.pdf
PWC	https://paperswithcode.com/paper/statistical-and-computational-guarantees-of
Repo
Framework

An Empirical Study of ADMM for Nonconvex Problems


Title	An Empirical Study of ADMM for Nonconvex Problems
Authors	Zheng Xu, Soham De, Mario Figueiredo, Christoph Studer, Tom Goldstein
Abstract	The alternating direction method of multipliers (ADMM) is a common optimization tool for solving constrained and non-differentiable problems. We provide an empirical study of the practical performance of ADMM on several nonconvex applications, including l0 regularized linear regression, l0 regularized image denoising, phase retrieval, and eigenvector computation. Our experiments suggest that ADMM performs well on a broad class of non-convex problems. Moreover, recently proposed adaptive ADMM methods, which automatically tune penalty parameters as the method runs, can improve algorithm efficiency and solution quality compared to ADMM with a non-tuned penalty.
Tasks	Denoising, Image Denoising
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03349v1
PDF	http://arxiv.org/pdf/1612.03349v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-study-of-admm-for-nonconvex
Repo
Framework

Creating Simplified 3D Models with High Quality Textures


Title	Creating Simplified 3D Models with High Quality Textures
Authors	Song Liu, Wanqing Li, Philip Ogunbona, Yang-Wai Chow
Abstract	This paper presents an extension to the KinectFusion algorithm which allows creating simplified 3D models with high quality RGB textures. This is achieved through (i) creating model textures using images from an HD RGB camera that is calibrated with Kinect depth camera, (ii) using a modified scheme to update model textures in an asymmetrical colour volume that contains a higher number of voxels than that of the geometry volume, (iii) simplifying dense polygon mesh model using quadric-based mesh decimation algorithm, and (iv) creating and mapping 2D textures to every polygon in the output 3D model. The proposed method is implemented in real-time by means of GPU parallel processing. Visualization via ray casting of both geometry and colour volumes provides users with a real-time feedback of the currently scanned 3D model. Experimental results show that the proposed method is capable of keeping the model texture quality even for a heavily decimated model and that, when reconstructing small objects, photorealistic RGB textures can still be reconstructed.
Tasks
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06645v1
PDF	http://arxiv.org/pdf/1602.06645v1.pdf
PWC	https://paperswithcode.com/paper/creating-simplified-3d-models-with-high
Repo
Framework

Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health


Title	Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health
Authors	Tim Althoff, Kevin Clark, Jure Leskovec
Abstract	Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack of large-scale data with labeled outcomes of the conversations. In this paper, we present a large-scale, quantitative study on the discourse of text-message-based counseling conversations. We develop a set of novel computational discourse analysis methods to measure how various linguistic aspects of conversations are correlated with conversation outcomes. Applying techniques such as sequence-based conversation models, language model comparisons, message clustering, and psycholinguistics-inspired word frequency analyses, we discover actionable conversation strategies that are associated with better conversation outcomes.
Tasks	Language Modelling
Published	2016-05-14
URL	http://arxiv.org/abs/1605.04462v3
PDF	http://arxiv.org/pdf/1605.04462v3.pdf
PWC	https://paperswithcode.com/paper/large-scale-analysis-of-counseling
Repo
Framework

Hyperspectral Image Classification with Support Vector Machines on Kernel Distribution Embeddings


Title	Hyperspectral Image Classification with Support Vector Machines on Kernel Distribution Embeddings
Authors	Gianni Franchi, Jesus Angulo, Dino Sejdinovic
Abstract	We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data. The introduced method relies on a recently proposed framework for learning on distributions – by representing them with mean elements in reproducing kernel Hilbert spaces (RKHS) and formulating a classification algorithm therein. In particular, we associate each pixel to an empirical distribution of its neighbouring pixels, a judicious representation of which in an RKHS, in conjunction with the spectral information contained in the pixel itself, give a new explicit set of features that can be fed into a suite of standard classification techniques – we opt for a well-established framework of support vector machines (SVM). Furthermore, the computational complexity is reduced via random Fourier features formalism. We study the consistency and the convergence rates of the proposed method and the experiments demonstrate strong performance on hyperspectral data with gains in comparison to the state-of-the-art results.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2016-05-30
URL	http://arxiv.org/abs/1605.09136v1
PDF	http://arxiv.org/pdf/1605.09136v1.pdf
PWC	https://paperswithcode.com/paper/hyperspectral-image-classification-with
Repo
Framework

A Bootstrap Machine Learning Approach to Identify Rare Disease Patients from Electronic Health Records


Title	A Bootstrap Machine Learning Approach to Identify Rare Disease Patients from Electronic Health Records
Authors	Ravi Garg, Shu Dong, Sanjiv Shah, Siddhartha R Jonnalagadda
Abstract	Rare diseases are very difficult to identify among large number of other possible diagnoses. Better availability of patient data and improvement in machine learning algorithms empower us to tackle this problem computationally. In this paper, we target one such rare disease - cardiac amyloidosis. We aim to automate the process of identifying potential cardiac amyloidosis patients with the help of machine learning algorithms and also learn most predictive factors. With the help of experienced cardiologists, we prepared a gold standard with 73 positive (cardiac amyloidosis) and 197 negative instances. We achieved high average cross-validation F1 score of 0.98 using an ensemble machine learning classifier. Some of the predictive variables were: Age and Diagnosis of cardiac arrest, chest pain, congestive heart failure, hypertension, prim open angle glaucoma, and shoulder arthritis. Further studies are needed to validate the accuracy of the system across an entire health system and its generalizability for other diseases.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01586v1
PDF	http://arxiv.org/pdf/1609.01586v1.pdf
PWC	https://paperswithcode.com/paper/a-bootstrap-machine-learning-approach-to
Repo
Framework

Convolution by Evolution: Differentiable Pattern Producing Networks


Title	Convolution by Evolution: Differentiable Pattern Producing Networks
Authors	Chrisantha Fernando, Dylan Banarse, Malcolm Reynolds, Frederic Besse, David Pfau, Max Jaderberg, Marc Lanctot, Daan Wierstra
Abstract	In this work we introduce a differentiable version of the Compositional Pattern Producing Network, called the DPPN. Unlike a standard CPPN, the topology of a DPPN is evolved but the weights are learned. A Lamarckian algorithm, that combines evolution and learning, produces DPPNs to reconstruct an image. Our main result is that DPPNs can be evolved/trained to compress the weights of a denoising autoencoder from 157684 to roughly 200 parameters, while achieving a reconstruction accuracy comparable to a fully connected network with more than two orders of magnitude more parameters. The regularization ability of the DPPN allows it to rediscover (approximate) convolutional network architectures embedded within a fully connected architecture. Such convolutional architectures are the current state of the art for many computer vision applications, so it is satisfying that DPPNs are capable of discovering this structure rather than having to build it in by design. DPPNs exhibit better generalization when tested on the Omniglot dataset after being trained on MNIST, than directly encoded fully connected autoencoders. DPPNs are therefore a new framework for integrating learning and evolution.
Tasks	Denoising, Omniglot
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02580v1
PDF	http://arxiv.org/pdf/1606.02580v1.pdf
PWC	https://paperswithcode.com/paper/convolution-by-evolution-differentiable
Repo
Framework