Paper Group ANR 33
Stochastic Frank-Wolfe Methods for Nonconvex Optimization. Improving Weakly-Supervised Object Localization By Micro-Annotation. Using Natural Language Processing to Screen Patients with Active Heart Failure: An Exploration for Hospital-wide Surveillance. Machine Learning Techniques for Stackelberg Security Games: a Survey. Sub-pixel accuracy edge f …
Stochastic Frank-Wolfe Methods for Nonconvex Optimization
| Title | Stochastic Frank-Wolfe Methods for Nonconvex Optimization |
| Authors | Sashank J. Reddi, Suvrit Sra, Barnabas Poczos, Alex Smola |
| Abstract | We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems. Frank-Wolfe methods (in the convex case) have gained tremendous recent interest in machine learning and optimization communities due to their projection-free property and their ability to exploit structured constraints. However, our understanding of these algorithms in the nonconvex setting is fairly limited. In this paper, we propose nonconvex stochastic Frank-Wolfe methods and analyze their convergence properties. For objective functions that decompose into a finite-sum, we leverage ideas from variance reduction techniques for convex optimization to obtain new variance reduced nonconvex Frank-Wolfe methods that have provably faster convergence than the classical Frank-Wolfe method. Finally, we show that the faster convergence rates of our variance reduced methods also translate into improved convergence rates for the stochastic setting. |
| Tasks | |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08254v2 |
| http://arxiv.org/pdf/1607.08254v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-frank-wolfe-methods-for-nonconvex |
| Repo | |
| Framework | |
Improving Weakly-Supervised Object Localization By Micro-Annotation
| Title | Improving Weakly-Supervised Object Localization By Micro-Annotation |
| Authors | Alexander Kolesnikov, Christoph H. Lampert |
| Abstract | Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network’s mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation. |
| Tasks | Object Localization, Semantic Segmentation, Weakly-Supervised Object Localization |
| Published | 2016-05-18 |
| URL | http://arxiv.org/abs/1605.05538v1 |
| http://arxiv.org/pdf/1605.05538v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-weakly-supervised-object |
| Repo | |
| Framework | |
Using Natural Language Processing to Screen Patients with Active Heart Failure: An Exploration for Hospital-wide Surveillance
| Title | Using Natural Language Processing to Screen Patients with Active Heart Failure: An Exploration for Hospital-wide Surveillance |
| Authors | Shu Dong, R Kannan Mutharasan, Siddhartha Jonnalagadda |
| Abstract | In this paper, we proposed two different approaches, a rule-based approach and a machine-learning based approach, to identify active heart failure cases automatically by analyzing electronic health records (EHR). For the rule-based approach, we extracted cardiovascular data elements from clinical notes and matched patients to different colors according their heart failure condition by using rules provided by experts in heart failure. It achieved 69.4% accuracy and 0.729 F1-Score. For the machine learning approach, with bigram of clinical notes as features, we tried four different models while SVM with linear kernel achieved the best performance with 87.5% accuracy and 0.86 F1-Score. Also, from the classification comparison between the four different models, we believe that linear models fit better for this problem. Once we combine the machine-learning and rule-based algorithms, we will enable hospital-wide surveillance of active heart failure through increased accuracy and interpretability of the outputs. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01580v1 |
| http://arxiv.org/pdf/1609.01580v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-natural-language-processing-to-screen |
| Repo | |
| Framework | |
Machine Learning Techniques for Stackelberg Security Games: a Survey
| Title | Machine Learning Techniques for Stackelberg Security Games: a Survey |
| Authors | Giuseppe De Nittis, Francesco Trovò |
| Abstract | The present survey aims at presenting the current machine learning techniques employed in security games domains. Specifically, we focused on papers and works developed by the Teamcore of University of Southern California, which deepened different directions in this field. After a brief introduction on Stackelberg Security Games (SSGs) and the poaching setting, the rest of the work presents how to model a boundedly rational attacker taking into account her human behavior, then describes how to face the problem of having attacker’s payoffs not defined and how to estimate them and, finally, presents how online learning techniques have been exploited to learn a model of the attacker. |
| Tasks | |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09341v1 |
| http://arxiv.org/pdf/1609.09341v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-techniques-for-stackelberg |
| Repo | |
| Framework | |
Sub-pixel accuracy edge fitting by means of B-spline
| Title | Sub-pixel accuracy edge fitting by means of B-spline |
| Authors | R. L. B. Breder, Vania V. Estrela, J. T. de Assis |
| Abstract | Local perturbations around contours strongly disturb the final result of computer vision tasks. It is common to introduce a priori information in the estimation process. Improvement can be achieved via a deformable model such as the snake model. In recent works, the deformable contour is modeled by means of B-spline snakes which allows local control, concise representation, and the use of fewer parameters. The estimation of the sub-pixel edges using a global B-spline model relies on the contour global determination according to a maximum likelihood framework and using the observed data likelihood. This procedure guarantees that the noisiest data will be filtered out. The data likelihood is computed as a consequence of the observation model which includes both orientation and position information. Comparative experiments of this algorithm and the classical spline interpolation have shown that the proposed algorithm outperforms the classical approach for Gaussian and Salt & Pepper noise. |
| Tasks | |
| Published | 2016-03-31 |
| URL | http://arxiv.org/abs/1603.09558v1 |
| http://arxiv.org/pdf/1603.09558v1.pdf | |
| PWC | https://paperswithcode.com/paper/sub-pixel-accuracy-edge-fitting-by-means-of-b |
| Repo | |
| Framework | |
FEAST: An Automated Feature Selection Framework for Compilation Tasks
| Title | FEAST: An Automated Feature Selection Framework for Compilation Tasks |
| Authors | Pai-Shun Ting, Chun-Chen Tu, Pin-Yu Chen, Ya-Yun Lo, Shin-Ming Cheng |
| Abstract | The success of the application of machine-learning techniques to compilation tasks can be largely attributed to the recent development and advancement of program characterization, a process that numerically or structurally quantifies a target program. While great achievements have been made in identifying key features to characterize programs, choosing a correct set of features for a specific compiler task remains an ad hoc procedure. In order to guarantee a comprehensive coverage of features, compiler engineers usually need to select excessive number of features. This, unfortunately, would potentially lead to a selection of multiple similar features, which in turn could create a new problem of bias that emphasizes certain aspects of a program’s characteristics, hence reducing the accuracy and performance of the target compiler task. In this paper, we propose FEAture Selection for compilation Tasks (FEAST), an efficient and automated framework for determining the most relevant and representative features from a feature pool. Specifically, FEAST utilizes widely used statistics and machine-learning tools, including LASSO, sequential forward and backward selection, for automatic feature selection, and can in general be applied to any numerical feature set. This paper further proposes an automated approach to compiler parameter assignment for assessing the performance of FEAST. Intensive experimental results demonstrate that, under the compiler parameter assignment task, FEAST can achieve comparable results with about 18% of features that are automatically selected from the entire feature pool. We also inspect these selected features and discuss their roles in program execution. |
| Tasks | Feature Selection |
| Published | 2016-10-29 |
| URL | http://arxiv.org/abs/1610.09543v1 |
| http://arxiv.org/pdf/1610.09543v1.pdf | |
| PWC | https://paperswithcode.com/paper/feast-an-automated-feature-selection |
| Repo | |
| Framework | |
Multi-instance Dynamic Ordinal Random Fields for Weakly-Supervised Pain Intensity Estimation
| Title | Multi-instance Dynamic Ordinal Random Fields for Weakly-Supervised Pain Intensity Estimation |
| Authors | Adria Ruiz, Ognjen Rudovic, Xavier Binefa, Maja Pantic |
| Abstract | In this paper, we address the Multi-Instance-Learning (MIL) problem when bag labels are naturally represented as ordinal variables (Multi–Instance–Ordinal Regression). Moreover, we consider the case where bags are temporal sequences of ordinal instances. To model this, we propose the novel Multi-Instance Dynamic Ordinal Random Fields (MI-DORF). In this model, we treat instance-labels inside the bag as latent ordinal states. The MIL assumption is modelled by incorporating a high-order cardinality potential relating bag and instance-labels,into the energy function. We show the benefits of the proposed approach on the task of weakly-supervised pain intensity estimation from the UNBC Shoulder-Pain Database. In our experiments, the proposed approach significantly outperforms alternative non-ordinal methods that either ignore the MIL assumption, or do not model dynamic information in target data. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01465v1 |
| http://arxiv.org/pdf/1609.01465v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-instance-dynamic-ordinal-random-fields |
| Repo | |
| Framework | |
Spatial Context based Angular Information Preserving Projection for Hyperspectral Image Classification
| Title | Spatial Context based Angular Information Preserving Projection for Hyperspectral Image Classification |
| Authors | Minshan Cui, Saurabh Prasad |
| Abstract | Dimensionality reduction is a crucial preprocessing for hyperspectral data analysis - finding an appropriate subspace is often required for subsequent image classification. In recent work, we proposed supervised angular information based dimensionality reduction methods to find effective subspaces. Since unlabeled data are often more readily available compared to labeled data, we propose an unsupervised projection that finds a lower dimensional subspace where local angular information is preserved. To exploit spatial information from the hyperspectral images, we further extend our unsupervised projection to incorporate spatial contextual information around each pixel in the image. Additionally, we also propose a sparse representation based classifier which is optimized to exploit spatial information during classification - we hence assert that our proposed projection is particularly suitable for classifiers where local similarity and spatial context are both important. Experimental results with two real-world hyperspectral datasets demonstrate that our proposed methods provide a robust classification performance. |
| Tasks | Dimensionality Reduction, Hyperspectral Image Classification, Image Classification |
| Published | 2016-07-15 |
| URL | http://arxiv.org/abs/1607.04593v1 |
| http://arxiv.org/pdf/1607.04593v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-context-based-angular-information |
| Repo | |
| Framework | |
Learning Stylometric Representations for Authorship Analysis
| Title | Learning Stylometric Representations for Authorship Analysis |
| Authors | Steven H. H. Ding, Benjamin C. M. Fung, Farkhund Iqbal, William K. Cheung |
| Abstract | Authorship analysis (AA) is the study of unveiling the hidden properties of authors from a body of exponentially exploding textual data. It extracts an author’s identity and sociolinguistic characteristics based on the reflected writing styles in the text. It is an essential process for various areas, such as cybercrime investigation, psycholinguistics, political socialization, etc. However, most of the previous techniques critically depend on the manual feature engineering process. Consequently, the choice of feature set has been shown to be scenario- or dataset-dependent. In this paper, to mimic the human sentence composition process using a neural network approach, we propose to incorporate different categories of linguistic features into distributed representation of words in order to learn simultaneously the writing style representations based on unlabeled texts for authorship analysis. In particular, the proposed models allow topical, lexical, syntactical, and character-level feature vectors of each document to be extracted as stylometrics. We evaluate the performance of our approach on the problems of authorship characterization and authorship verification with the Twitter, novel, and essay datasets. The experiments suggest that our proposed text representation outperforms the bag-of-lexical-n-grams, Latent Dirichlet Allocation, Latent Semantic Analysis, PVDM, PVDBOW, and word2vec representations. |
| Tasks | Feature Engineering |
| Published | 2016-06-03 |
| URL | http://arxiv.org/abs/1606.01219v1 |
| http://arxiv.org/pdf/1606.01219v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-stylometric-representations-for |
| Repo | |
| Framework | |
Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
| Title | Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions |
| Authors | Devis Tuia, Rémi Flamary, Nicolas Courty |
| Abstract | In this paper, we tackle the question of discovering an effective set of spatial filters to solve hyperspectral classification problems. Instead of fixing a priori the filters and their parameters using expert knowledge, we let the model find them within random draws in the (possibly infinite) space of possible filters. We define an active set feature learner that includes in the model only features that improve the classifier. To this end, we consider a fast and linear classifier, multiclass logistic classification, and show that with a good representation (the filters discovered), such a simple classifier can reach at least state of the art performances. We apply the proposed active set learner in four hyperspectral image classification problems, including agricultural and urban classification at different resolutions, as well as multimodal data. We also propose a hierarchical setting, which allows to generate more complex banks of features that can better describe the nonlinearities present in the data. |
| Tasks | Hyperspectral Image Classification, Image Classification |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07279v1 |
| http://arxiv.org/pdf/1606.07279v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiclass-feature-learning-for-hyperspectral |
| Repo | |
| Framework | |
The word entropy of natural languages
| Title | The word entropy of natural languages |
| Authors | Christian Bentz, Dimitrios Alikaniotis |
| Abstract | The average uncertainty associated with words is an information-theoretic concept at the heart of quantitative and computational linguistics. The entropy has been established as a measure of this average uncertainty - also called average information content. We here use parallel texts of 21 languages to establish the number of tokens at which word entropies converge to stable values. These convergence points are then used to select texts from a massively parallel corpus, and to estimate word entropies across more than 1000 languages. Our results help to establish quantitative language comparisons, to understand the performance of multilingual translation systems, and to normalize semantic similarity measures. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.06996v1 |
| http://arxiv.org/pdf/1606.06996v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-word-entropy-of-natural-languages |
| Repo | |
| Framework | |
Prediction performance after learning in Gaussian process regression
| Title | Prediction performance after learning in Gaussian process regression |
| Authors | Johan Wågberg, Dave Zachariah, Thomas B. Schön, Petre Stoica |
| Abstract | This paper considers the quantification of the prediction performance in Gaussian process regression. The standard approach is to base the prediction error bars on the theoretical predictive variance, which is a lower bound on the mean square-error (MSE). This approach, however, does not take into account that the statistical model is learned from the data. We show that this omission leads to a systematic underestimation of the prediction errors. Starting from a generalization of the Cram'er-Rao bound, we derive a more accurate MSE bound which provides a measure of uncertainty for prediction of Gaussian processes. The improved bound is easily computed and we illustrate it using synthetic and real data examples. of uncertainty for prediction of Gaussian processes and illustrate it using synthetic and real data examples. |
| Tasks | Gaussian Processes |
| Published | 2016-06-13 |
| URL | http://arxiv.org/abs/1606.03865v3 |
| http://arxiv.org/pdf/1606.03865v3.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-performance-after-learning-in |
| Repo | |
| Framework | |
OntoCat: Automatically categorizing knowledge in API Documentation
| Title | OntoCat: Automatically categorizing knowledge in API Documentation |
| Authors | Niraj Kumar, Premkumar Devanbu |
| Abstract | Most application development happens in the context of complex APIs; reference documentation for APIs has grown tremendously in variety, complexity, and volume, and can be difficult to navigate. There is a growing need to develop well-organized ways to access the knowledge latent in the documentation; several research efforts deal with the organization (ontology) of API-related knowledge. Extensive knowledge-engineering work, supported by a rigorous qualitative analysis, by Maalej & Robillard [3] has identified a useful taxonomy of API knowledge. Based on this taxonomy, we introduce a domain independent technique to extract the knowledge types from the given API reference documentation. Our system, OntoCat, introduces total nine different features and their semantic and statistical combinations to classify the different knowledge types. We tested OntoCat on python API reference documentation. Our experimental results show the effectiveness of the system and opens the scope of probably related research areas (i.e., user behavior, documentation quality, etc.). |
| Tasks | |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07602v1 |
| http://arxiv.org/pdf/1607.07602v1.pdf | |
| PWC | https://paperswithcode.com/paper/ontocat-automatically-categorizing-knowledge |
| Repo | |
| Framework | |
Movie Description
| Title | Movie Description |
| Authors | Anna Rohrbach, Atousa Torabi, Marcus Rohrbach, Niket Tandon, Christopher Pal, Hugo Larochelle, Aaron Courville, Bernt Schiele |
| Abstract | Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. In total the Large Scale Movie Description Challenge (LSMDC) contains a parallel corpus of 118,114 sentences and video clips from 202 movies. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are indeed more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in a challenge organized in the context of the workshop “Describing and Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at ICCV 2015. |
| Tasks | |
| Published | 2016-05-12 |
| URL | http://arxiv.org/abs/1605.03705v1 |
| http://arxiv.org/pdf/1605.03705v1.pdf | |
| PWC | https://paperswithcode.com/paper/movie-description |
| Repo | |
| Framework | |
A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems
| Title | A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems |
| Authors | Subarna Tripathi, Brian Guenter |
| Abstract | We present a novel, automatic eye gaze tracking scheme inspired by smooth pursuit eye motion while playing mobile games or watching virtual reality contents. Our algorithm continuously calibrates an eye tracking system for a head mounted display. This eliminates the need for an explicit calibration step and automatically compensates for small movements of the headset with respect to the head. The algorithm finds correspondences between corneal motion and screen space motion, and uses these to generate Gaussian Process Regression models. A combination of those models provides a continuous mapping from corneal position to screen space position. Accuracy is nearly as good as achieved with an explicit calibration step. |
| Tasks | Calibration, Eye Tracking |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06919v1 |
| http://arxiv.org/pdf/1612.06919v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-statistical-approach-to-continuous-self |
| Repo | |
| Framework | |
