Paper Group ANR 16
![Paper Group ANR 16](/2017/images/pwc/paper-arxiv_hu144ec288a26b3e360d673e256787de3e_28623_900x500_fit_q75_box.jpg)
Multiple Instance Hybrid Estimator for Learning Target Signatures. Neural Expectation Maximization. Expert Opinion Extraction from a Biomedical Database. Robust Stochastic Configuration Networks with Kernel Density Estimation. CASICT Tibetan Word Segmentation System for MLWS2017. Identifying the Mislabeled Training Samples of ECG Signals using Mach …
Multiple Instance Hybrid Estimator for Learning Target Signatures
Title | Multiple Instance Hybrid Estimator for Learning Target Signatures |
Authors | Changzhe Jiao, Alina Zare |
Abstract | Signature-based detectors for hyperspectral target detection rely on knowing the specific target signature in advance. However, target signature are often difficult or impossible to obtain. Furthermore, common methods for obtaining target signatures, such as from laboratory measurements or manual selection from an image scene, usually do not capture the discriminative features of target class. In this paper, an approach for estimating a discriminative target signature from imprecise labels is presented. The proposed approach maximizes the response of the hybrid sub-pixel detector within a multiple instance learning framework and estimates a set of discriminative target signatures. After learning target signatures, any signature based detector can then be applied on test data. Both simulated and real hyperspectral target detection experiments are shown to illustrate the effectiveness of the method. |
Tasks | Multiple Instance Learning |
Published | 2017-01-09 |
URL | http://arxiv.org/abs/1701.02258v1 |
http://arxiv.org/pdf/1701.02258v1.pdf | |
PWC | https://paperswithcode.com/paper/multiple-instance-hybrid-estimator-for |
Repo | |
Framework | |
Neural Expectation Maximization
Title | Neural Expectation Maximization |
Authors | Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber |
Abstract | Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (sequential) perceptual grouping task and find that it is able to accurately recover the constituent objects. We demonstrate that the learned representations are useful for next-step prediction. |
Tasks | |
Published | 2017-08-11 |
URL | http://arxiv.org/abs/1708.03498v2 |
http://arxiv.org/pdf/1708.03498v2.pdf | |
PWC | https://paperswithcode.com/paper/neural-expectation-maximization |
Repo | |
Framework | |
Expert Opinion Extraction from a Biomedical Database
Title | Expert Opinion Extraction from a Biomedical Database |
Authors | Ahmed Samet, Thomas Guyet, Benjamin Negrevergne, Tien-Tuan Dao, Tuan Nha Hoang, Marie-Christine Ho Ba Tho |
Abstract | In this paper, we tackle the problem of extracting frequent opinions from uncertain databases. We introduce the foundation of an opinion mining approach with the definition of pattern and support measure. The support measure is derived from the commitment definition. A new algorithm called OpMiner that extracts the set of frequent opinions modelled as a mass functions is detailed. Finally, we apply our approach on a real-world biomedical database that stores opinions of experts to evaluate the reliability level of biomedical data. Performance analysis showed a better quality patterns for our proposed model in comparison with literature-based methods. |
Tasks | Opinion Mining |
Published | 2017-09-11 |
URL | http://arxiv.org/abs/1709.03270v1 |
http://arxiv.org/pdf/1709.03270v1.pdf | |
PWC | https://paperswithcode.com/paper/expert-opinion-extraction-from-a-biomedical |
Repo | |
Framework | |
Robust Stochastic Configuration Networks with Kernel Density Estimation
Title | Robust Stochastic Configuration Networks with Kernel Density Estimation |
Authors | Dianhui Wang, Ming Li |
Abstract | Neural networks have been widely used as predictive models to fit data distribution, and they could be implemented through learning a collection of samples. In many applications, however, the given dataset may contain noisy samples or outliers which may result in a poor learner model in terms of generalization. This paper contributes to a development of robust stochastic configuration networks (RSCNs) for resolving uncertain data regression problems. RSCNs are built on original stochastic configuration networks with weighted least squares method for evaluating the output weights, and the input weights and biases are incrementally and randomly generated by satisfying with a set of inequality constrains. The kernel density estimation (KDE) method is employed to set the penalty weights for each training samples, so that some negative impacts, caused by noisy data or outliers, on the resulting learner model can be reduced. The alternating optimization technique is applied for updating a RSCN model with improved penalty weights computed from the kernel density estimation function. Performance evaluation is carried out by a function approximation, four benchmark datasets and a case study on engineering application. Comparisons to other robust randomised neural modelling techniques, including the probabilistic robust learning algorithm for neural networks with random weights and improved RVFL networks, indicate that the proposed RSCNs with KDE perform favourably and demonstrate good potential for real-world applications. |
Tasks | Density Estimation |
Published | 2017-02-15 |
URL | http://arxiv.org/abs/1702.04459v2 |
http://arxiv.org/pdf/1702.04459v2.pdf | |
PWC | https://paperswithcode.com/paper/robust-stochastic-configuration-networks-with |
Repo | |
Framework | |
CASICT Tibetan Word Segmentation System for MLWS2017
Title | CASICT Tibetan Word Segmentation System for MLWS2017 |
Authors | Jiawei Hu, Qun Liu |
Abstract | We participated in the MLWS 2017 on Tibetan word segmentation task, our system is trained in a unrestricted way, by introducing a baseline system and 76w tibetan segmented sentences of ours. In the system character sequence is processed by the baseline system into word sequence, then a subword unit (BPE algorithm) split rare words into subwords with its corresponding features, after that a neural network classifier is adopted to token each subword into “B,M,E,S” label, in decoding step a simple rule is used to recover a final word sequence. The candidate system for submition is selected by evaluating the F-score in dev set pre-extracted from the 76w sentences. Experiment shows that this method can fix segmentation errors of baseline system and result in a significant performance gain. |
Tasks | |
Published | 2017-10-17 |
URL | http://arxiv.org/abs/1710.06112v1 |
http://arxiv.org/pdf/1710.06112v1.pdf | |
PWC | https://paperswithcode.com/paper/casict-tibetan-word-segmentation-system-for |
Repo | |
Framework | |
Identifying the Mislabeled Training Samples of ECG Signals using Machine Learning
Title | Identifying the Mislabeled Training Samples of ECG Signals using Machine Learning |
Authors | Yaoguang Li, Wei Cui, Cong Wang |
Abstract | The classification accuracy of electrocardiogram signal is often affected by diverse factors in which mislabeled training samples issue is one of the most influential problems. In order to mitigate this negative effect, the method of cross validation is introduced to identify the mislabeled samples. The method utilizes the cooperative advantages of different classifiers to act as a filter for the training samples. The filter removes the mislabeled training samples and retains the correctly labeled ones with the help of 10-fold cross validation. Consequently, a new training set is provided to the final classifiers to acquire higher classification accuracies. Finally, we numerically show the effectiveness of the proposed method with the MIT-BIH arrhythmia database. |
Tasks | |
Published | 2017-12-11 |
URL | http://arxiv.org/abs/1712.03792v1 |
http://arxiv.org/pdf/1712.03792v1.pdf | |
PWC | https://paperswithcode.com/paper/identifying-the-mislabeled-training-samples |
Repo | |
Framework | |
An unsupervised long short-term memory neural network for event detection in cell videos
Title | An unsupervised long short-term memory neural network for event detection in cell videos |
Authors | Ha Tran Hong Phan, Ashnil Kumar, David Feng, Michael Fulham, Jinman Kim |
Abstract | We propose an automatic unsupervised cell event detection and classification method, which expands convolutional Long Short-Term Memory (LSTM) neural networks, for cellular events in cell video sequences. Cells in images that are captured from various biomedical applications usually have different shapes and motility, which pose difficulties for the automated event detection in cell videos. Current methods to detect cellular events are based on supervised machine learning and rely on tedious manual annotation from investigators with specific expertise. So that our LSTM network could be trained in an unsupervised manner, we designed it with a branched structure where one branch learns the frequent, regular appearance and movements of objects and the second learns the stochastic events, which occur rarely and without warning in a cell video sequence. We tested our network on a publicly available dataset of densely packed stem cell phase-contrast microscopy images undergoing cell division. This dataset is considered to be more challenging that a dataset with sparse cells. We compared our method to several published supervised methods evaluated on the same dataset and to a supervised LSTM method with a similar design and configuration to our unsupervised method. We used an F1-score, which is a balanced measure for both precision and recall. Our results show that our unsupervised method has a higher or similar F1-score when compared to two fully supervised methods that are based on Hidden Conditional Random Fields (HCRF), and has comparable accuracy with the current best supervised HCRF-based method. Our method was generalizable as after being trained on one video it could be applied to videos where the cells were in different conditions. The accuracy of our unsupervised method approached that of its supervised counterpart. |
Tasks | |
Published | 2017-09-07 |
URL | http://arxiv.org/abs/1709.02081v1 |
http://arxiv.org/pdf/1709.02081v1.pdf | |
PWC | https://paperswithcode.com/paper/an-unsupervised-long-short-term-memory-neural |
Repo | |
Framework | |
Cellular Automaton Based Simulation of Large Pedestrian Facilities - A Case Study on the Staten Island Ferry Terminals
Title | Cellular Automaton Based Simulation of Large Pedestrian Facilities - A Case Study on the Staten Island Ferry Terminals |
Authors | Luca Crociani, Gregor Lämmel, H. Joon Park, Giuseppe Vizzari |
Abstract | Current metropolises largely depend on a functioning transport infrastructure and the increasing demand can only be satisfied by a well organized mass transit. One example for a crucial mass transit system is New York City’s Staten Island Ferry, connecting the two boroughs of Staten Island and Manhattan with a regular passenger service. Today’s demand already exceeds 2500 passengers for a single cycle during peek hours, and future projections suggest that it will further increase. One way to appraise how the system will cope with future demand is by simulation. This contribution proposes an integrated simulation approach to evaluate the system performance with respect to future demand. The simulation relies on a multiscale modeling approach where the terminal buildings are simulated by a microscopic and quantitatively valid cellular automata (CA) and the journeys of the ferries themselves are modeled by a mesoscopic queue simulation approach. Based on the simulation results recommendations with respect to the future demand are given. |
Tasks | |
Published | 2017-09-11 |
URL | http://arxiv.org/abs/1709.03297v1 |
http://arxiv.org/pdf/1709.03297v1.pdf | |
PWC | https://paperswithcode.com/paper/cellular-automaton-based-simulation-of-large |
Repo | |
Framework | |
Online Clustering of Contextual Cascading Bandits
Title | Online Clustering of Contextual Cascading Bandits |
Authors | Shuai Li |
Abstract | We consider a new setting of online clustering of contextual cascading bandits, an online learning problem where the underlying cluster structure over users is unknown and needs to be learned from a random prefix feedback. More precisely, a learning agent recommends an ordered list of items to a user, who checks the list and stops at the first satisfactory item, if any. We propose an algorithm of CLUB-cascade for this setting and prove a $T$-step regret bound of order $\tilde{O}(\sqrt{T})$. Previous work corresponds to the degenerate case of only one cluster, and our general regret bound in this special case also significantly improves theirs. We conduct experiments on both synthetic and real data, and demonstrate the effectiveness of our algorithm and the advantage of incorporating online clustering method. |
Tasks | |
Published | 2017-11-23 |
URL | http://arxiv.org/abs/1711.08594v2 |
http://arxiv.org/pdf/1711.08594v2.pdf | |
PWC | https://paperswithcode.com/paper/online-clustering-of-contextual-cascading |
Repo | |
Framework | |
Nonlinear Spectral Image Fusion
Title | Nonlinear Spectral Image Fusion |
Authors | Martin Benning, Michael Möller, Raz Z. Nossek, Martin Burger, Daniel Cremers, Guy Gilboa, Carola-Bibiane Schönlieb |
Abstract | In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks. The well-localized and edge-preserving spectral TV decomposition allows to select frequencies of a certain image to transfer particular features, such as wrinkles in a face, from one image to another. We illustrate the effectiveness of the proposed approach in several numerical experiments, including a comparison to the competing techniques of Poisson image editing, linear osmosis, wavelet fusion and Laplacian pyramid fusion. We conclude that the proposed spectral TV image decomposition framework is a valuable tool for semi- and fully-automatic image editing and fusion. |
Tasks | |
Published | 2017-03-23 |
URL | http://arxiv.org/abs/1703.08001v1 |
http://arxiv.org/pdf/1703.08001v1.pdf | |
PWC | https://paperswithcode.com/paper/nonlinear-spectral-image-fusion |
Repo | |
Framework | |
Graphical Nonconvex Optimization for Optimal Estimation in Gaussian Graphical Models
Title | Graphical Nonconvex Optimization for Optimal Estimation in Gaussian Graphical Models |
Authors | Qiang Sun, Kean Ming Tan, Han Liu, Tong Zhang |
Abstract | We consider the problem of learning high-dimensional Gaussian graphical models. The graphical lasso is one of the most popular methods for estimating Gaussian graphical models. However, it does not achieve the oracle rate of convergence. In this paper, we propose the graphical nonconvex optimization for optimal estimation in Gaussian graphical models, which is then approximated by a sequence of convex programs. Our proposal is computationally tractable and produces an estimator that achieves the oracle rate of convergence. The statistical error introduced by the sequential approximation using the convex programs are clearly demonstrated via a contraction property. The rate of convergence can be further improved using the notion of sparsity pattern. The proposed methodology is then extended to semiparametric graphical models. We show through numerical studies that the proposed estimator outperforms other popular methods for estimating Gaussian graphical models. |
Tasks | |
Published | 2017-06-04 |
URL | http://arxiv.org/abs/1706.01158v1 |
http://arxiv.org/pdf/1706.01158v1.pdf | |
PWC | https://paperswithcode.com/paper/graphical-nonconvex-optimization-for-optimal |
Repo | |
Framework | |
Attribute-Guided Face Generation Using Conditional CycleGAN
Title | Attribute-Guided Face Generation Using Conditional CycleGAN |
Authors | Yongyi Lu, Yu-Wing Tai, Chi-Keung Tang |
Abstract | We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the CycleGAN and propose conditional CycleGAN, which is designed to 1) handle unpaired training data because the training low/high-res and high-res attribute images may not necessarily align with each other, and to 2) allow easy control of the appearance of the generated face via the input attributes. We demonstrate impressive results on the attribute-guided conditional CycleGAN, which can synthesize realistic face images with appearance easily controlled by user-supplied attributes (e.g., gender, makeup, hair color, eyeglasses). Using the attribute image as identity to produce the corresponding conditional vector and by incorporating a face verification network, the attribute-guided network becomes the identity-guided conditional CycleGAN which produces impressive and interesting results on identity transfer. We demonstrate three applications on identity-guided conditional CycleGAN: identity-preserving face superresolution, face swapping, and frontal face generation, which consistently show the advantage of our new method. |
Tasks | Face Generation, Face Swapping, Face Verification |
Published | 2017-05-28 |
URL | http://arxiv.org/abs/1705.09966v2 |
http://arxiv.org/pdf/1705.09966v2.pdf | |
PWC | https://paperswithcode.com/paper/attribute-guided-face-generation-using |
Repo | |
Framework | |
Generative Adversarial Positive-Unlabelled Learning
Title | Generative Adversarial Positive-Unlabelled Learning |
Authors | Ming Hou, Brahim Chaib-draa, Chao Li, Qibin Zhao |
Abstract | In this work, we consider the task of classifying binary positive-unlabeled (PU) data. The existing discriminative learning based PU models attempt to seek an optimal reweighting strategy for U data, so that a decent decision boundary can be found. However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks. In contrast, we are the first to innovate a totally new paradigm to attack the binary PU task, from perspective of generative learning by leveraging the powerful generative adversarial networks (GAN). Our generative positive-unlabeled (GenPU) framework incorporates an array of discriminators and generators that are endowed with different roles in simultaneously producing positive and negative realistic samples. We provide theoretical analysis to justify that, at equilibrium, GenPU is capable of recovering both positive and negative data distributions. Moreover, we show GenPU is generalizable and closely related to the semi-supervised classification. Given rather limited P data, experiments on both synthetic and real-world dataset demonstrate the effectiveness of our proposed framework. With infinite realistic and diverse sample streams generated from GenPU, a very flexible classifier can then be trained using deep neural networks. |
Tasks | |
Published | 2017-11-21 |
URL | http://arxiv.org/abs/1711.08054v2 |
http://arxiv.org/pdf/1711.08054v2.pdf | |
PWC | https://paperswithcode.com/paper/generative-adversarial-positive-unlabelled |
Repo | |
Framework | |
A Visual Web Tool to Perform What-If Analysis of Optimization Approaches
Title | A Visual Web Tool to Perform What-If Analysis of Optimization Approaches |
Authors | Sascha Van Cauwelaert, Michele Lombardi, Pierre Schaus |
Abstract | In Operation Research, practical evaluation is essential to validate the efficacy of optimization approaches. This paper promotes the usage of performance profiles as a standard practice to visualize and analyze experimental results. It introduces a Web tool to construct and export performance profiles as SVG or HTML files. In addition, the application relies on a methodology to estimate the benefit of hypothetical solver improvements. Therefore, the tool allows one to employ what-if analysis to screen possible research directions, and identify those having the best potential. The approach is showcased on two Operation Research technologies: Constraint Programming and Mixed Integer Linear Programming. |
Tasks | |
Published | 2017-03-16 |
URL | http://arxiv.org/abs/1703.06042v1 |
http://arxiv.org/pdf/1703.06042v1.pdf | |
PWC | https://paperswithcode.com/paper/a-visual-web-tool-to-perform-what-if-analysis |
Repo | |
Framework | |
Fuzzy Model Tree For Early Effort Estimation
Title | Fuzzy Model Tree For Early Effort Estimation |
Authors | Mohammad Azzeh, Ali Bou Nassif |
Abstract | Use Case Points (UCP) is a well-known method to estimate the project size, based on Use Case diagram, at early phases of software development. Although the Use Case diagram is widely accepted as a de-facto model for analyzing object oriented software requirements over the world, UCP method did not take sufficient amount of attention because, as yet, there is no consensus on how to produce software effort from UCP. This paper aims to study the potential of using Fuzzy Model Tree to derive effort estimates based on UCP size measure using a dataset collected for that purpose. The proposed approach has been validated against Treeboost model, Multiple Linear Regression and classical effort estimation based on the UCP model. The obtained results are promising and show better performance than those obtained by classical UCP, Multiple Linear Regression and slightly better than those obtained by Tree boost model. |
Tasks | |
Published | 2017-03-11 |
URL | http://arxiv.org/abs/1703.04565v1 |
http://arxiv.org/pdf/1703.04565v1.pdf | |
PWC | https://paperswithcode.com/paper/fuzzy-model-tree-for-early-effort-estimation |
Repo | |
Framework | |