May 7, 2019

2775 words 14 mins read

Paper Group ANR 46

A New Spatio-Spectral Morphological Segmentation For Multi-Spectral Remote-Sensing Images. Conditional distribution variability measures for causality detection. Automatic Annotation of Structured Facts in Images. A Classification Leveraged Object Detector. Congruences and Concurrent Lines in Multi-View Geometry. Visualizing Linguistic Shift. Relat …

A New Spatio-Spectral Morphological Segmentation For Multi-Spectral Remote-Sensing Images


Title	A New Spatio-Spectral Morphological Segmentation For Multi-Spectral Remote-Sensing Images
Authors	Guillaume Noyel, Jesus Angulo, Dominique Jeulin
Abstract	A general framework of spatio-spectral segmentation for multi-spectral images is introduced in this paper. The method is based on classification-driven stochastic watershed (WS) by Monte Carlo simulations, and it gives more regular and reliable contours than standard WS. The present approach is decomposed into several sequential steps. First, a dimensionality-reduction stage is performed using the factor-correspondence analysis method. In this context, a new way to select the factor axes (eigenvectors) according to their spatial information is introduced. Then, a spectral classification produces a spectral pre-segmentation of the image. Subsequently, a probability density function (pdf) of contours containing spatial and spectral information is estimated by simulation using a stochastic WS approach driven by the spectral classification. The pdf of the contours is finally segmented by a WS controlled by markers from a regularization of the initial classification.
Tasks	Dimensionality Reduction
Published	2016-02-09
URL	http://arxiv.org/abs/1602.03145v1
PDF	http://arxiv.org/pdf/1602.03145v1.pdf
PWC	https://paperswithcode.com/paper/a-new-spatio-spectral-morphological
Repo
Framework

Conditional distribution variability measures for causality detection


Title	Conditional distribution variability measures for causality detection
Authors	José A. R. Fonollosa
Abstract	In this paper we derive variability measures for the conditional probability distributions of a pair of random variables, and we study its application in the inference of causal-effect relationships. We also study the combination of the proposed measures with standard statistical measures in the the framework of the ChaLearn cause-effect pair challenge. The developed model obtains an AUC score of 0.82 on the final test database and ranked second in the challenge.
Tasks
Published	2016-01-25
URL	http://arxiv.org/abs/1601.06680v1
PDF	http://arxiv.org/pdf/1601.06680v1.pdf
PWC	https://paperswithcode.com/paper/conditional-distribution-variability-measures
Repo
Framework

Automatic Annotation of Structured Facts in Images


Title	Automatic Annotation of Structured Facts in Images
Authors	Mohamed Elhoseiny, Scott Cohen, Walter Chang, Brian Price, Ahmed Elgammal
Abstract	Motivated by the application of fact-level image understanding, we present an automatic method for data collection of structured visual facts from images with captions. Example structured facts include attributed objects (e.g., <flower, red>), actions (e.g., <baby, smile>), interactions (e.g., <man, walking, dog>), and positional information (e.g., <vase, on, table>). The collected annotations are in the form of fact-image pairs (e.g.,<man, walking, dog> and an image region containing this fact). With a language approach, the proposed method is able to collect hundreds of thousands of visual fact annotations with accuracy of 83% according to human judgment. Our method automatically collected more than 380,000 visual fact annotations and more than 110,000 unique visual facts from images with captions and localized them in images in less than one day of processing time on standard CPU platforms.
Tasks
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00466v3
PDF	http://arxiv.org/pdf/1604.00466v3.pdf
PWC	https://paperswithcode.com/paper/automatic-annotation-of-structured-facts-in
Repo
Framework

A Classification Leveraged Object Detector


Title	A Classification Leveraged Object Detector
Authors	Miao Sun, Tony X. Han, Zhihai He
Abstract	Currently, the state-of-the-art image classification algorithms outperform the best available object detector by a big margin in terms of average precision. We, therefore, propose a simple yet principled approach that allows us to leverage object detection through image classification on supporting regions specified by a preliminary object detector. Using a simple bag-of- words model based image classification algorithm, we leveraged the performance of the deformable model objector from 35.9% to 39.5% in average precision over 20 categories on standard PASCAL VOC 2007 detection dataset.
Tasks	Image Classification, Object Detection
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01841v1
PDF	http://arxiv.org/pdf/1604.01841v1.pdf
PWC	https://paperswithcode.com/paper/a-classification-leveraged-object-detector
Repo
Framework

Congruences and Concurrent Lines in Multi-View Geometry


Title	Congruences and Concurrent Lines in Multi-View Geometry
Authors	Jean Ponce, Bernd Sturmfels, Matthew Trager
Abstract	We present a new framework for multi-view geometry in computer vision. A camera is a mapping between $\mathbb{P}^3$ and a line congruence. This model, which ignores image planes and measurements, is a natural abstraction of traditional pinhole cameras. It includes two-slit cameras, pushbroom cameras, catadioptric cameras, and many more. We study the concurrent lines variety, which consists of $n$-tuples of lines in $\mathbb{P}^3$ that intersect at a point. Combining its equations with those of various congruences, we derive constraints for corresponding images in multiple views. We also study photographic cameras which use image measurements and are modeled as rational maps from $\mathbb{P}^3$ to $\mathbb{P}^2$ or $\mathbb{P}^1\times \mathbb{P}^1$.
Tasks
Published	2016-08-21
URL	http://arxiv.org/abs/1608.05924v2
PDF	http://arxiv.org/pdf/1608.05924v2.pdf
PWC	https://paperswithcode.com/paper/congruences-and-concurrent-lines-in-multi
Repo
Framework

Visualizing Linguistic Shift


Title	Visualizing Linguistic Shift
Authors	Salman Mahmood, Rami Al-Rfou, Klaus Mueller
Abstract	Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together. These embeddings have been used as features to improve results in various applications such as document classification, named entity recognition, etc. Neural language models are able to learn word representations which have been used to capture semantic shifts across time and geography. The objective of this paper is to first identify and then visualize how words change meaning in different text corpus. We will train a neural language model on texts from a diverse set of disciplines philosophy, religion, fiction etc. Each text will alter the embeddings of the words to represent the meaning of the word inside that text. We will present a computational technique to detect words that exhibit significant linguistic shift in meaning and usage. We then use enhanced scatterplots and storyline visualization to visualize the linguistic shift.
Tasks	Document Classification, Language Modelling, Named Entity Recognition, Word Embeddings
Published	2016-11-20
URL	http://arxiv.org/abs/1611.06478v1
PDF	http://arxiv.org/pdf/1611.06478v1.pdf
PWC	https://paperswithcode.com/paper/visualizing-linguistic-shift
Repo
Framework

Relationship between Variants of One-Class Nearest Neighbours and Creating their Accurate Ensembles


Title	Relationship between Variants of One-Class Nearest Neighbours and Creating their Accurate Ensembles
Authors	Shehroz S. Khan, Amir Ahmad
Abstract	In one-class classification problems, only the data for the target class is available, whereas the data for the non-target class may be completely absent. In this paper, we study one-class nearest neighbour (OCNN) classifiers and their different variants. We present a theoretical analysis to show the relationships among different variants of OCNN that may use different neighbours or thresholds to identify unseen examples of the non-target class. We also present a method based on inter-quartile range for optimising parameters used in OCNN in the absence of non-target data during training. Then, we propose two ensemble approaches based on random subspace and random projection methods to create accurate OCNN ensembles. We tested the proposed methods on 15 benchmark and real world domain-specific datasets and show that random-projection ensembles of OCNN perform best.
Tasks
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01686v5
PDF	http://arxiv.org/pdf/1604.01686v5.pdf
PWC	https://paperswithcode.com/paper/relationship-between-variants-of-one-class
Repo
Framework

Neural Headline Generation with Sentence-wise Optimization


Title	Neural Headline Generation with Sentence-wise Optimization
Authors	Ayana, Shiqi Shen, Yu Zhao, Zhiyuan Liu, Maosong Sun
Abstract	Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural networks. Nevertheless, as traditional neural network utilizes maximum likelihood estimation for parameter optimization, it essentially constrains the expected training objective within word level rather than sentence level. Moreover, the performance of model prediction significantly relies on training data distribution. To overcome these drawbacks, we employ minimum risk training strategy in this paper, which directly optimizes model parameters in sentence level with respect to evaluation metrics and leads to significant improvements for headline generation. Experiment results show that our models outperforms state-of-the-art systems on both English and Chinese headline generation tasks.
Tasks
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01904v2
PDF	http://arxiv.org/pdf/1604.01904v2.pdf
PWC	https://paperswithcode.com/paper/neural-headline-generation-with-sentence-wise
Repo
Framework

Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation


Title	Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation
Authors	Himabindu Lakkaraju, Cynthia Rudin
Abstract	Decision makers, such as doctors and judges, make crucial decisions such as recommending treatments to patients, and granting bails to defendants on a daily basis. Such decisions typically involve weighting the potential benefits of taking an action against the costs involved. In this work, we aim to automate this task of learning {cost-effective, interpretable and actionable treatment regimes. We formulate this as a problem of learning a decision list – a sequence of if-then-else rules – which maps characteristics of subjects (eg., diagnostic test results of patients) to treatments. We propose a novel objective to construct a decision list which maximizes outcomes for the population, and minimizes overall costs. We model the problem of learning such a list as a Markov Decision Process (MDP) and employ a variant of the Upper Confidence Bound for Trees (UCT) strategy which leverages customized checks for pruning the search space effectively. Experimental results on real world observational data capturing treatment recommendations for asthma patients demonstrate the effectiveness of our approach.
Tasks
Published	2016-11-23
URL	http://arxiv.org/abs/1611.07663v1
PDF	http://arxiv.org/pdf/1611.07663v1.pdf
PWC	https://paperswithcode.com/paper/learning-cost-effective-and-interpretable
Repo
Framework

A Tucker decomposition process for probabilistic modeling of diffusion magnetic resonance imaging


Title	A Tucker decomposition process for probabilistic modeling of diffusion magnetic resonance imaging
Authors	Hernan Dario Vargas Cardona, Mauricio A. Alvarez, Alvaro A. Orozco
Abstract	Diffusion magnetic resonance imaging (dMRI) is an emerging medical technique used for describing water diffusion in an organic tissue. Typically, rank-2 tensors quantify this diffusion. From this quantification, it is possible to calculate relevant scalar measures (i.e. fractional anisotropy and mean diffusivity) employed in clinical diagnosis of neurological diseases. Nonetheless, 2nd-order tensors fail to represent complex tissue structures like crossing fibers. To overcome this limitation, several researchers proposed a diffusion representation with higher order tensors (HOT), specifically 4th and 6th orders. However, the current acquisition protocols of dMRI data allow images with a spatial resolution between 1 $mm^3$ and 2 $mm^3$. This voxel size is much smaller than tissue structures. Therefore, several clinical procedures derived from dMRI may be inaccurate. Interpolation has been used to enhance resolution of dMRI in a tensorial space. Most interpolation methods are valid only for rank-2 tensors and a generalization for HOT data is missing. In this work, we propose a novel stochastic process called Tucker decomposition process (TDP) for performing HOT data interpolation. Our model is based on the Tucker decomposition and Gaussian processes as parameters of the TDP. We test the TDP in 2nd, 4th and 6th rank HOT fields. For rank-2 tensors, we compare against direct interpolation, log-Euclidean approach and Generalized Wishart processes. For rank-4 and rank-6 tensors we compare against direct interpolation. Results obtained show that TDP interpolates accurately the HOT fields and generalizes to any rank.
Tasks	Gaussian Processes
Published	2016-06-25
URL	http://arxiv.org/abs/1606.07970v1
PDF	http://arxiv.org/pdf/1606.07970v1.pdf
PWC	https://paperswithcode.com/paper/a-tucker-decomposition-process-for
Repo
Framework

Robust mixture of experts modeling using the skew $t$ distribution


Title	Robust mixture of experts modeling using the skew $t$ distribution
Authors	Faicel Chamroukhi
Abstract	Mixture of Experts (MoE) is a popular framework in the fields of statistics and machine learning for modeling heterogeneity in data for regression, classification and clustering. MoE for continuous data are usually based on the normal distribution. However, it is known that for data with asymmetric behavior, heavy tails and atypical observations, the use of the normal distribution is unsuitable. We introduce a new robust non-normal mixture of experts modeling using the skew $t$ distribution. The proposed skew $t$ mixture of experts, named STMoE, handles these issues of the normal mixtures experts regarding possibly skewed, heavy-tailed and noisy data. We develop a dedicated expectation conditional maximization (ECM) algorithm to estimate the model parameters by monotonically maximizing the observed data log-likelihood. We describe how the presented model can be used in prediction and in model-based clustering of regression data. Numerical experiments carried out on simulated data show the effectiveness and the robustness of the proposed model in fitting non-linear regression functions as well as in model-based clustering. Then, the proposed model is applied to the real-world data of tone perception for musical data analysis, and the one of temperature anomalies for the analysis of climate change data. The obtained results confirm the usefulness of the model for practical data analysis applications.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1612.06879v1
PDF	http://arxiv.org/pdf/1612.06879v1.pdf
PWC	https://paperswithcode.com/paper/robust-mixture-of-experts-modeling-using-the
Repo
Framework

Phase transitions in Restricted Boltzmann Machines with generic priors


Title	Phase transitions in Restricted Boltzmann Machines with generic priors
Authors	Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
Abstract	We study Generalised Restricted Boltzmann Machines with generic priors for units and weights, interpolating between Boolean and Gaussian variables. We present a complete analysis of the replica symmetric phase diagram of these systems, which can be regarded as Generalised Hopfield models. We underline the role of the retrieval phase for both inference and learning processes and we show that retrieval is robust for a large class of weight and unit priors, beyond the standard Hopfield scenario. Furthermore we show how the paramagnetic phase boundary is directly related to the optimal size of the training set necessary for good generalisation in a teacher-student scenario of unsupervised learning.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03132v2
PDF	http://arxiv.org/pdf/1612.03132v2.pdf
PWC	https://paperswithcode.com/paper/phase-transitions-in-restricted-boltzmann
Repo
Framework

Unsupervised Learning for Lexicon-Based Classification


Title	Unsupervised Learning for Lexicon-Based Classification
Authors	Jacob Eisenstein
Abstract	In lexicon-based classification, documents are assigned labels by comparing the number of words that appear from two opposed lexicons, such as positive and negative sentiment. Creating such words lists is often easier than labeling instances, and they can be debugged by non-experts if classification performance is unsatisfactory. However, there is little analysis or justification of this classification heuristic. This paper describes a set of assumptions that can be used to derive a probabilistic justification for lexicon-based classification, as well as an analysis of its expected accuracy. One key assumption behind lexicon-based classification is that all words in each lexicon are equally predictive. This is rarely true in practice, which is why lexicon-based approaches are usually outperformed by supervised classifiers that learn distinct weights on each word from labeled instances. This paper shows that it is possible to learn such weights without labeled data, by leveraging co-occurrence statistics across the lexicons. This offers the best of both worlds: light supervision in the form of lexicons, and data-driven classification with higher accuracy than traditional word-counting heuristics.
Tasks
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06933v1
PDF	http://arxiv.org/pdf/1611.06933v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-for-lexicon-based
Repo
Framework

Machine Learning and Cloud Computing: Survey of Distributed and SaaS Solutions


Title	Machine Learning and Cloud Computing: Survey of Distributed and SaaS Solutions
Authors	Daniel Pop
Abstract	Applying popular machine learning algorithms to large amounts of data raised new challenges for the ML practitioners. Traditional ML libraries does not support well processing of huge datasets, so that new approaches were needed. Parallelization using modern parallel computing frameworks, such as MapReduce, CUDA, or Dryad gained in popularity and acceptance, resulting in new ML libraries developed on top of these frameworks. We will briefly introduce the most prominent industrial and academic outcomes, such as Apache Mahout, GraphLab or Jubatus. We will investigate how cloud computing paradigm impacted the field of ML. First direction is of popular statistics tools and libraries (R system, Python) deployed in the cloud. A second line of products is augmenting existing tools with plugins that allow users to create a Hadoop cluster in the cloud and run jobs on it. Next on the list are libraries of distributed implementations for ML algorithms, and on-premise deployments of complex systems for data analytics and data mining. Last approach on the radar of this survey is ML as Software-as-a-Service, several BigData start-ups (and large companies as well) already opening their solutions to the market.
Tasks
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08767v1
PDF	http://arxiv.org/pdf/1603.08767v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-and-cloud-computing-survey
Repo
Framework

Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models


Title	Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models
Authors	Viktoriya Krakovna, Finale Doshi-Velez
Abstract	As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks, state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining a long short-term memory (LSTM) model with a hidden Markov model (HMM), a simpler and more transparent model. We add the HMM state probabilities to the output layer of the LSTM, and then train the HMM and LSTM either sequentially or jointly. The LSTM can make use of the information from the HMM, and fill in the gaps when the HMM is not performing well. A small hybrid model usually performs better than a standalone LSTM of the same size, especially on smaller data sets. We test the algorithms on text data and medical time series data, and find that the LSTM and HMM learn complementary information about the features in the text.
Tasks	Speech Recognition, Time Series
Published	2016-11-18
URL	http://arxiv.org/abs/1611.05934v1
PDF	http://arxiv.org/pdf/1611.05934v1.pdf
PWC	https://paperswithcode.com/paper/increasing-the-interpretability-of-recurrent-1
Repo
Framework