Paper Group ANR 466
Segmentation of scanning electron microscopy images from natural rubber samples with gold nanoparticles using starlet wavelets. Predicting the Effectiveness of Self-Training: Application to Sentiment Classification. Multi-domain machine translation enhancements by parallel data extraction from comparable corpora. Multi-object Classification via Cro …
Segmentation of scanning electron microscopy images from natural rubber samples with gold nanoparticles using starlet wavelets
| Title | Segmentation of scanning electron microscopy images from natural rubber samples with gold nanoparticles using starlet wavelets |
| Authors | Alexandre Fioravante de Siqueira, Flávio Camargo Cabrera, Aylton Pagamisse, Aldo Eloizo Job |
| Abstract | Electronic microscopy has been used for morphology evaluation of different materials structures. However, microscopy results may be affected by several factors. Image processing methods can be used to correct and improve the quality of these results. In this paper we propose an algorithm based on starlets to perform the segmentation of scanning electron microscopy images. An application is presented in order to locate gold nanoparticles in natural rubber membranes. In this application, our method showed accuracy greater than 85% for all test images. Results given by this method will be used in future studies, to computationally estimate the density distribution of gold nanoparticles in natural rubber samples and to predict reduction kinetics of gold nanoparticles at different time periods. |
| Tasks | |
| Published | 2016-06-12 |
| URL | http://arxiv.org/abs/1606.03671v1 |
| http://arxiv.org/pdf/1606.03671v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-scanning-electron-microscopy |
| Repo | |
| Framework | |
Predicting the Effectiveness of Self-Training: Application to Sentiment Classification
| Title | Predicting the Effectiveness of Self-Training: Application to Sentiment Classification |
| Authors | Vincent Van Asch, Walter Daelemans |
| Abstract | The goal of this paper is to investigate the connection between the performance gain that can be obtained by selftraining and the similarity between the corpora used in this approach. Self-training is a semi-supervised technique designed to increase the performance of machine learning algorithms by automatically classifying instances of a task and adding these as additional training material to the same classifier. In the context of language processing tasks, this training material is mostly an (annotated) corpus. Unfortunately self-training does not always lead to a performance increase and whether it will is largely unpredictable. We show that the similarity between corpora can be used to identify those setups for which self-training can be beneficial. We consider this research as a step in the process of developing a classifier that is able to adapt itself to each new test corpus that it is presented with. |
| Tasks | Sentiment Analysis |
| Published | 2016-01-13 |
| URL | http://arxiv.org/abs/1601.03288v1 |
| http://arxiv.org/pdf/1601.03288v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-effectiveness-of-self-training |
| Repo | |
| Framework | |
Multi-domain machine translation enhancements by parallel data extraction from comparable corpora
| Title | Multi-domain machine translation enhancements by parallel data extraction from comparable corpora |
| Authors | Krzysztof Wołk, Emilia Rejmund, Krzysztof Marasek |
| Abstract | Parallel texts are a relatively rare language resource, however, they constitute a very useful research material with a wide range of applications. This study presents and analyses new methodologies we developed for obtaining such data from previously built comparable corpora. The methodologies are automatic and unsupervised which makes them good for large scale research. The task is highly practical as non-parallel multilingual data occur much more frequently than parallel corpora and accessing them is easy, although parallel sentences are a considerably more useful resource. In this study, we propose a method of automatic web crawling in order to build topic-aligned comparable corpora, e.g. based on the Wikipedia or Euronews.com. We also developed new methods of obtaining parallel sentences from comparable data and proposed methods of filtration of corpora capable of selecting inconsistent or only partially equivalent translations. Our methods are easily scalable to other languages. Evaluation of the quality of the created corpora was performed by analysing the impact of their use on statistical machine translation systems. Experiments were presented on the basis of the Polish-English language pair for texts from different domains, i.e. lectures, phrasebooks, film dialogues, European Parliament proceedings and texts contained medicines leaflets. We also tested a second method of creating parallel corpora based on data from comparable corpora which allows for automatically expanding the existing corpus of sentences about a given domain on the basis of analogies found between them. It does not require, therefore, having past parallel resources in order to train a classifier. |
| Tasks | Machine Translation |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1603.06785v1 |
| http://arxiv.org/pdf/1603.06785v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-domain-machine-translation-enhancements |
| Repo | |
| Framework | |
Multi-object Classification via Crowdsourcing with a Reject Option
| Title | Multi-object Classification via Crowdsourcing with a Reject Option |
| Authors | Qunwei Li, Aditya Vempaty, Lav R. Varshney, Pramod K. Varshney |
| Abstract | Consider designing an effective crowdsourcing system for an $M$-ary classification task. Crowd workers complete simple binary microtasks whose results are aggregated to give the final result. We consider the novel scenario where workers have a reject option so they may skip microtasks when they are unable or choose not to respond. For example, in mismatched speech transcription, workers who do not know the language may not be able to respond to microtasks focused on phonological dimensions outside their categorical perception. We present an aggregation approach using a weighted majority voting rule, where each worker’s response is assigned an optimized weight to maximize the crowd’s classification performance. We evaluate system performance in both exact and asymptotic forms. Further, we consider the setting where there may be a set of greedy workers that complete microtasks even when they are unable to perform it reliably. We consider an oblivious and an expurgation strategy to deal with greedy workers, developing an algorithm to adaptively switch between the two based on the estimated fraction of greedy workers in the anonymous crowd. Simulation results show improved performance compared with conventional majority voting. |
| Tasks | Object Classification |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00575v2 |
| http://arxiv.org/pdf/1602.00575v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-object-classification-via-crowdsourcing |
| Repo | |
| Framework | |
A Distributed Deep Representation Learning Model for Big Image Data Classification
| Title | A Distributed Deep Representation Learning Model for Big Image Data Classification |
| Authors | Le Dong, Na Lv, Qianni Zhang, Shanshan Xie, Ling He, Mengdie Mao |
| Abstract | This paper describes an effective and efficient image classification framework nominated distributed deep representation learning model (DDRL). The aim is to strike the balance between the computational intensive deep learning approaches (tuned parameters) which are intended for distributed computing, and the approaches that focused on the designed parameters but often limited by sequential computing and cannot scale up. In the evaluation of our approach, it is shown that DDRL is able to achieve state-of-art classification accuracy efficiently on both medium and large datasets. The result implies that our approach is more efficient than the conventional deep learning approaches, and can be applied to big data that is too complex for parameter designing focused approaches. More specifically, DDRL contains two main components, i.e., feature extraction and selection. A hierarchical distributed deep representation learning algorithm is designed to extract image statistics and a nonlinear mapping algorithm is used to map the inherent statistics into abstract features. Both algorithms are carefully designed to avoid millions of parameters tuning. This leads to a more compact solution for image classification of big data. We note that the proposed approach is designed to be friendly with parallel computing. It is generic and easy to be deployed to different distributed computing resources. In the experiments, the largescale image datasets are classified with a DDRM implementation on Hadoop MapReduce, which shows high scalability and resilience. |
| Tasks | Image Classification, Representation Learning |
| Published | 2016-07-02 |
| URL | http://arxiv.org/abs/1607.00501v1 |
| http://arxiv.org/pdf/1607.00501v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributed-deep-representation-learning |
| Repo | |
| Framework | |
Social planning for social HRI
| Title | Social planning for social HRI |
| Authors | Liz Sonenberg, Tim Miller, Adrian Pearce, Paolo Felli, Christian Muise, Frank Dignum |
| Abstract | Making a computational agent ‘social’ has implications for how it perceives itself and the environment in which it is situated, including the ability to recognise the behaviours of others. We point to recent work on social planning, i.e. planning in settings where the social context is relevant in the assessment of the beliefs and capabilities of others, and in making appropriate choices of what to do next. |
| Tasks | |
| Published | 2016-02-21 |
| URL | http://arxiv.org/abs/1602.06483v1 |
| http://arxiv.org/pdf/1602.06483v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-planning-for-social-hri |
| Repo | |
| Framework | |
Essence’ Description
| Title | Essence’ Description |
| Authors | Peter Nightingale, Andrea Rendl |
| Abstract | A description of the Essence’ language as used by the tool Savile Row. |
| Tasks | |
| Published | 2016-01-12 |
| URL | http://arxiv.org/abs/1601.02865v1 |
| http://arxiv.org/pdf/1601.02865v1.pdf | |
| PWC | https://paperswithcode.com/paper/essence-description |
| Repo | |
| Framework | |
Statistical power and prediction accuracy in multisite resting-state fMRI connectivity
| Title | Statistical power and prediction accuracy in multisite resting-state fMRI connectivity |
| Authors | Christian Dansereau, Yassine Benhajali, Celine Risterucci, Emilio Merlo Pich, Pierre Orban, Douglas Arnold, Pierre Bellec |
| Abstract | Connectivity studies using resting-state functional magnetic resonance imaging are increasingly pooling data acquired at multiple sites. While this may allow investigators to speed up recruitment or increase sample size, multisite studies also potentially introduce systematic biases in connectivity measures across sites. In this work, we measure the inter-site effect in connectivity and its impact on our ability to detect individual and group differences. Our study was based on real, as opposed to simulated, multisite fMRI datasets collected in N=345 young, healthy subjects across 8 scanning sites with 3T scanners and heterogeneous scanning protocols, drawn from the 1000 functional connectome project. We first empirically show that typical functional networks were reliably found at the group level in all sites, and that the amplitude of the inter-site effects was small to moderate, with a Cohen’s effect size below 0.5 on average across brain connections. We then implemented a series of Monte-Carlo simulations, based on real data, to evaluate the impact of the multisite effects on detection power in statistical tests comparing two groups (with and without the effect) using a general linear model, as well as on the prediction of group labels with a support-vector machine. As a reference, we also implemented the same simulations with fMRI data collected at a single site using an identical sample size. Simulations revealed that using data from heterogeneous sites only slightly decreased our ability to detect changes compared to a monosite study with the GLM, and had a greater impact on prediction accuracy. Taken together, our results support the feasibility of multisite studies in rs-fMRI provided the sample size is large enough. |
| Tasks | |
| Published | 2016-07-12 |
| URL | http://arxiv.org/abs/1607.03392v3 |
| http://arxiv.org/pdf/1607.03392v3.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-power-and-prediction-accuracy-in |
| Repo | |
| Framework | |
Simultaneous Inpainting and Denoising by Directional Global Three-part Decomposition: Connecting Variational and Fourier Domain Based Image Processing
| Title | Simultaneous Inpainting and Denoising by Directional Global Three-part Decomposition: Connecting Variational and Fourier Domain Based Image Processing |
| Authors | Duy Hoang Thai, Carsten Gottschlich |
| Abstract | We consider the very challenging task of restoring images (i) which have a large number of missing pixels, (ii) whose existing pixels are corrupted by noise and (iii) the ideal image to be restored contains both cartoon and texture elements. The combination of these three properties makes this inverse problem a very difficult one. The solution proposed in this manuscript is based on directional global three-part decomposition (DG3PD) [ThaiGottschlich2016] with directional total variation norm, directional G-norm and $\ell_\infty$-norm in curvelet domain as key ingredients of the model. Image decomposition by DG3PD enables a decoupled inpainting and denoising of the cartoon and texture components. A comparison to existing approaches for inpainting and denoising shows the advantages of the proposed method. Moreover, we regard the image restoration problem from the viewpoint of a Bayesian framework and we discuss the connections between the proposed solution by function space and related image representation by harmonic analysis and pyramid decomposition. |
| Tasks | Denoising, Image Restoration |
| Published | 2016-06-09 |
| URL | http://arxiv.org/abs/1606.02861v1 |
| http://arxiv.org/pdf/1606.02861v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-inpainting-and-denoising-by |
| Repo | |
| Framework | |
Diagnostic Prediction Using Discomfort Drawings
| Title | Diagnostic Prediction Using Discomfort Drawings |
| Authors | Cheng Zhang, Hedvig Kjellstrom, Bo C. Bertilson |
| Abstract | In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. A discomfort drawing is an intuitive way for patients to express discomfort and pain related symptoms. These drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from real-world patient cases is collected for which medical experts provide diagnostic labels. Next, we extend a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel. |
| Tasks | |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01356v1 |
| http://arxiv.org/pdf/1612.01356v1.pdf | |
| PWC | https://paperswithcode.com/paper/diagnostic-prediction-using-discomfort |
| Repo | |
| Framework | |
DeepMovie: Using Optical Flow and Deep Neural Networks to Stylize Movies
| Title | DeepMovie: Using Optical Flow and Deep Neural Networks to Stylize Movies |
| Authors | Alexander G. Anderson, Cory P. Berg, Daniel P. Mossing, Bruno A. Olshausen |
| Abstract | A recent paper by Gatys et al. describes a method for rendering an image in the style of another image. First, they use convolutional neural network features to build a statistical model for the style of an image. Then they create a new image with the content of one image but the style statistics of another image. Here, we extend this method to render a movie in a given artistic style. The naive solution that independently renders each frame produces poor results because the features of the style move substantially from one frame to the next. The other naive method that initializes the optimization for the next frame using the rendered version of the previous frame also produces poor results because the features of the texture stay fixed relative to the frame of the movie instead of moving with objects in the scene. The main contribution of this paper is to use optical flow to initialize the style transfer optimization so that the texture features move with the objects in the video. Finally, we suggest a method to incorporate optical flow explicitly into the cost function. |
| Tasks | Optical Flow Estimation, Style Transfer |
| Published | 2016-05-26 |
| URL | http://arxiv.org/abs/1605.08153v1 |
| http://arxiv.org/pdf/1605.08153v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepmovie-using-optical-flow-and-deep-neural |
| Repo | |
| Framework | |
Pose for Action - Action for Pose
| Title | Pose for Action - Action for Pose |
| Authors | Umar Iqbal, Martin Garbade, Juergen Gall |
| Abstract | In this work we propose to utilize information about human actions to improve pose estimation in monocular videos. To this end, we present a pictorial structure model that exploits high-level information about activities to incorporate higher-order part dependencies by modeling action specific appearance models and pose priors. However, instead of using an additional expensive action recognition framework, the action priors are efficiently estimated by our pose estimation framework. This is achieved by starting with a uniform action prior and updating the action prior during pose estimation. We also show that learning the right amount of appearance sharing among action classes improves the pose estimation. We demonstrate the effectiveness of the proposed method on two challenging datasets for pose estimation and action recognition with over 80,000 test images. |
| Tasks | Pose Estimation, Temporal Action Localization |
| Published | 2016-03-13 |
| URL | http://arxiv.org/abs/1603.04037v2 |
| http://arxiv.org/pdf/1603.04037v2.pdf | |
| PWC | https://paperswithcode.com/paper/pose-for-action-action-for-pose |
| Repo | |
| Framework | |
Controlling Explanatory Heatmap Resolution and Semantics via Decomposition Depth
| Title | Controlling Explanatory Heatmap Resolution and Semantics via Decomposition Depth |
| Authors | Sebastian Bach, Alexander Binder, Klaus-Robert Müller, Wojciech Samek |
| Abstract | We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps. Layer-wise Relevance Propagation (LRP) is a method to compute scores for individual components of an input image, denoting their contribution to the prediction of the classifier for one particular test point. We demonstrate the impact of different choices of decomposition cut-off points during the LRP-process, controlling the resolution and semantics of the heatmap on test images from the PASCAL VOC 2007 test data set. |
| Tasks | |
| Published | 2016-03-21 |
| URL | http://arxiv.org/abs/1603.06463v3 |
| http://arxiv.org/pdf/1603.06463v3.pdf | |
| PWC | https://paperswithcode.com/paper/controlling-explanatory-heatmap-resolution |
| Repo | |
| Framework | |
Modeling self-organization of vocabularies under phonological similarity effects
| Title | Modeling self-organization of vocabularies under phonological similarity effects |
| Authors | Javier Vera |
| Abstract | This work develops a computational model (by Automata Networks) of phonological similarity effects involved in the formation of word-meaning associations on artificial populations of speakers. Classical studies show that in recalling experiments memory performance was impaired for phonologically similar words versus dissimilar ones. Here, the individuals confound phonologically similar words according to a predefined parameter. The main hypothesis is that there is a critical range of the parameter, and with this, of working-memory mechanisms, which implies drastic changes in the final consensus of the entire population. Theoretical results present proofs of convergence for a particular case of the model within a worst-case complexity framework. Computer simulations describe the evolution of an energy function that measures the amount of local agreement between individuals. The main finding is the appearance of sudden changes in the energy function at critical parameters. |
| Tasks | |
| Published | 2016-03-17 |
| URL | http://arxiv.org/abs/1603.05354v2 |
| http://arxiv.org/pdf/1603.05354v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-self-organization-of-vocabularies |
| Repo | |
| Framework | |
Distributed Low Rank Approximation of Implicit Functions of a Matrix
| Title | Distributed Low Rank Approximation of Implicit Functions of a Matrix |
| Authors | David P. Woodruff, Peilin Zhong |
| Abstract | We study distributed low rank approximation in which the matrix to be approximated is only implicitly represented across the different servers. For example, each of $s$ servers may have an $n \times d$ matrix $A^t$, and we may be interested in computing a low rank approximation to $A = f(\sum_{t=1}^s A^t)$, where $f$ is a function which is applied entrywise to the matrix $\sum_{t=1}^s A^t$. We show for a wide class of functions $f$ it is possible to efficiently compute a $d \times d$ rank-$k$ projection matrix $P$ for which $\A - AP_F^2 \leq \A - [A]_k_F^2 + \varepsilon \A_F^2$, where $AP$ denotes the projection of $A$ onto the row span of $P$, and $[A]_k$ denotes the best rank-$k$ approximation to $A$ given by the singular value decomposition. The communication cost of our protocols is $d \cdot (sk/\varepsilon)^{O(1)}$, and they succeed with high probability. Our framework allows us to efficiently compute a low rank approximation to an entry-wise softmax, to a Gaussian kernel expansion, and to $M$-Estimators applied entrywise (i.e., forms of robust low rank approximation). We also show that our additive error approximation is best possible, in the sense that any protocol achieving relative error for these problems requires significantly more communication. Finally, we experimentally validate our algorithms on real datasets. |
| Tasks | |
| Published | 2016-01-28 |
| URL | http://arxiv.org/abs/1601.07721v1 |
| http://arxiv.org/pdf/1601.07721v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-low-rank-approximation-of |
| Repo | |
| Framework | |
