July 28, 2019

2936 words 14 mins read

Paper Group ANR 197

Building a Semantic Role Labelling System for Vietnamese. Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data. Deep Graph Attention Model. Non-Euclidean Conditional Expectation and Filtering. Towards End-to-End Face Recognition through Alignment Learning. Towards Learned Clauses Database Red …

Building a Semantic Role Labelling System for Vietnamese


Title	Building a Semantic Role Labelling System for Vietnamese
Authors	Thai-Hoang Pham, Xuan-Khoai Pham, Phuong Le-Hong
Abstract	Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural language. There exists SRL systems for well-studied languages like English, Chinese or Japanese but there is not any such system for the Vietnamese language. In this paper, we present the first SRL system for Vietnamese with encouraging accuracy. We first demonstrate that a simple application of SRL techniques developed for English could not give a good accuracy for Vietnamese. We then introduce a new algorithm for extracting candidate syntactic constituents, which is much more accurate than the common node-mapping algorithm usually used in the identification step. Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL. Our SRL system achieves an $F_1$ score of 73.53% on the Vietnamese PropBank corpus. This system, including software and corpus, is available as an open source project and we believe that it is a good baseline for the development of future Vietnamese SRL systems.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04038v1
PDF	http://arxiv.org/pdf/1705.04038v1.pdf
PWC	https://paperswithcode.com/paper/building-a-semantic-role-labelling-system-for
Repo
Framework

Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data


Title	Bayesian Recurrent Neural Network Models for Forecasting and Quantifying Uncertainty in Spatial-Temporal Data
Authors	Patrick L. McDermott, Christopher K. Wikle
Abstract	Recurrent neural networks (RNNs) are nonlinear dynamical models commonly used in the machine learning and dynamical systems literature to represent complex dynamical or sequential relationships between variables. More recently, as deep learning models have become more common, RNNs have been used to forecast increasingly complicated systems. Dynamical spatio-temporal processes represent a class of complex systems that can potentially benefit from these types of models. Although the RNN literature is expansive and highly developed, uncertainty quantification is often ignored. Even when considered, the uncertainty is generally quantified without the use of a rigorous framework, such as a fully Bayesian setting. Here we attempt to quantify uncertainty in a more formal framework while maintaining the forecast accuracy that makes these models appealing, by presenting a Bayesian RNN model for nonlinear spatio-temporal forecasting. Additionally, we make simple modifications to the basic RNN to help accommodate the unique nature of nonlinear spatio-temporal data. The proposed model is applied to a Lorenz simulation and two real-world nonlinear spatio-temporal forecasting applications.
Tasks	Spatio-Temporal Forecasting
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00636v2
PDF	http://arxiv.org/pdf/1711.00636v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-recurrent-neural-network-models-for
Repo
Framework

Deep Graph Attention Model


Title	Deep Graph Attention Model
Authors	John Boaz Lee, Ryan Rossi, Xiangnan Kong
Abstract	Graph classification is a problem with practical applications in many different domains. Most of the existing methods take the entire graph into account when calculating graph features. In a graphlet-based approach, for instance, the entire graph is processed to get the total count of different graphlets or sub-graphs. In the real-world, however, graphs can be both large and noisy with discriminative patterns confined to certain regions in the graph only. In this work, we study the problem of attentional processing for graph classification. The use of attention allows us to focus on small but informative parts of the graph, avoiding noise in the rest of the graph. We present a novel RNN model, called the Graph Attention Model (GAM), that processes only a portion of the graph by adaptively selecting a sequence of “interesting” nodes. The model is equipped with an external memory component which allows it to integrate information gathered from different parts of the graph. We demonstrate the effectiveness of the model through various experiments.
Tasks	Graph Classification
Published	2017-09-15
URL	http://arxiv.org/abs/1709.06075v1
PDF	http://arxiv.org/pdf/1709.06075v1.pdf
PWC	https://paperswithcode.com/paper/deep-graph-attention-model
Repo
Framework

Non-Euclidean Conditional Expectation and Filtering


Title	Non-Euclidean Conditional Expectation and Filtering
Authors	Anastasis Kratsios, Cody B. Hyndman
Abstract	A non-Euclidean generalization of conditional expectation is introduced and characterized as the minimizer of expected intrinsic squared-distance from a manifold-valued target. The computational tractable formulation expresses the non-convex optimization problem as transformations of Euclidean conditional expectation. This gives computationally tractable filtering equations for the dynamics of the intrinsic conditional expectation of a manifold-valued signal and is used to obtain accurate numerical forecasts of efficient portfolios by incorporating their geometric structure into the estimates.
Tasks
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05829v3
PDF	http://arxiv.org/pdf/1710.05829v3.pdf
PWC	https://paperswithcode.com/paper/non-euclidean-conditional-expectation-and
Repo
Framework

Towards End-to-End Face Recognition through Alignment Learning


Title	Towards End-to-End Face Recognition through Alignment Learning
Authors	Yuanyi Zhong, Jiansheng Chen, Bo Huang
Abstract	Plenty of effective methods have been proposed for face recognition during the past decade. Although these methods differ essentially in many aspects, a common practice of them is to specifically align the facial area based on the prior knowledge of human face structure before feature extraction. In most systems, the face alignment module is implemented independently. This has actually caused difficulties in the designing and training of end-to-end face recognition models. In this paper we study the possibility of alignment learning in end-to-end face recognition, in which neither prior knowledge on facial landmarks nor artificially defined geometric transformations are required. Specifically, spatial transformer layers are inserted in front of the feature extraction layers in a Convolutional Neural Network (CNN) for face recognition. Only human identity clues are used for driving the neural network to automatically learn the most suitable geometric transformation and the most appropriate facial area for the recognition task. To ensure reproducibility, our model is trained purely on the publicly available CASIA-WebFace dataset, and is tested on the Labeled Face in the Wild (LFW) dataset. We have achieved a verification accuracy of 99.08% which is comparable to state-of-the-art single model based methods.
Tasks	Face Alignment, Face Recognition
Published	2017-01-25
URL	http://arxiv.org/abs/1701.07174v1
PDF	http://arxiv.org/pdf/1701.07174v1.pdf
PWC	https://paperswithcode.com/paper/towards-end-to-end-face-recognition-through
Repo
Framework

Towards Learned Clauses Database Reduction Strategies Based on Dominance Relationship


Title	Towards Learned Clauses Database Reduction Strategies Based on Dominance Relationship
Authors	Jerry Lonlac, Engelbert Mephu Nguifo
Abstract	Clause Learning is one of the most important components of a conflict driven clause learning (CDCL) SAT solver that is effective on industrial instances. Since the number of learned clauses is proved to be exponential in the worse case, it is necessary to identify the most relevant clauses to maintain and delete the irrelevant ones. As reported in the literature, several learned clauses deletion strategies have been proposed. However the diversity in both the number of clauses to be removed at each step of reduction and the results obtained with each strategy creates confusion to determine which criterion is better. Thus, the problem to select which learned clauses are to be removed during the search step remains very challenging. In this paper, we propose a novel approach to identify the most relevant learned clauses without favoring or excluding any of the proposed measures, but by adopting the notion of dominance relationship among those measures. Our approach bypasses the problem of the diversity of results and reaches a compromise between the assessments of these measures. Furthermore, the proposed approach also avoids another non-trivial problem which is the amount of clauses to be deleted at each reduction of the learned clause database.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1705.10898v1
PDF	http://arxiv.org/pdf/1705.10898v1.pdf
PWC	https://paperswithcode.com/paper/towards-learned-clauses-database-reduction
Repo
Framework

Robustly Learning a Gaussian: Getting Optimal Error, Efficiently


Title	Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
Authors	Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart
Abstract	We study the fundamental problem of learning the parameters of a high-dimensional Gaussian in the presence of noise – where an $\varepsilon$-fraction of our samples were chosen by an adversary. We give robust estimators that achieve estimation error $O(\varepsilon)$ in the total variation distance, which is optimal up to a universal constant that is independent of the dimension. In the case where just the mean is unknown, our robustness guarantee is optimal up to a factor of $\sqrt{2}$ and the running time is polynomial in $d$ and $1/\epsilon$. When both the mean and covariance are unknown, the running time is polynomial in $d$ and quasipolynomial in $1/\varepsilon$. Moreover all of our algorithms require only a polynomial number of samples. Our work shows that the same sorts of error guarantees that were established over fifty years ago in the one-dimensional setting can also be achieved by efficient algorithms in high-dimensional settings.
Tasks
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03866v2
PDF	http://arxiv.org/pdf/1704.03866v2.pdf
PWC	https://paperswithcode.com/paper/robustly-learning-a-gaussian-getting-optimal
Repo
Framework

Theoretical limitations of Encoder-Decoder GAN architectures


Title	Theoretical limitations of Encoder-Decoder GAN architectures
Authors	Sanjeev Arora, Andrej Risteski, Yi Zhang
Abstract	Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings. The intuition is that being forced to train an encoder alongside the usual generator forces the system to learn meaningful mappings from the code to the data-point and vice-versa, which should improve the learning of the target distribution and ameliorate mode-collapse. It should also yield meaningful codes that are useful as features for downstream tasks. The current paper shows rigorously that even on real-life distributions of images, the encode-decoder GAN training objectives (a) cannot prevent mode collapse; i.e. the objective can be near-optimal even when the generated distribution has low and finite support (b) cannot prevent learning meaningless codes for data – essentially white noise. Thus if encoder-decoder GANs do indeed work then it must be due to reasons as yet not understood, since the training objective can be low even for meaningless solutions.
Tasks
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02651v1
PDF	http://arxiv.org/pdf/1711.02651v1.pdf
PWC	https://paperswithcode.com/paper/theoretical-limitations-of-encoder-decoder
Repo
Framework

Automatic Real-time Background Cut for Portrait Videos


Title	Automatic Real-time Background Cut for Portrait Videos
Authors	Xiaoyong Shen, Ruixing Wang, Hengshuang Zhao, Jiaya Jia
Abstract	We in this paper solve the problem of high-quality automatic real-time background cut for 720p portrait videos. We first handle the background ambiguity issue in semantic segmentation by proposing a global background attenuation model. A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map. We form an end-to-end network for training and testing. Each module is designed considering efficiency and accuracy. We build a portrait dataset, which includes 8,000 images with high-quality labeled map for training and testing. To further improve the performance, we build a portrait video dataset with 50 sequences to fine-tune video segmentation. Our framework benefits many video processing applications.
Tasks	Semantic Segmentation, Video Semantic Segmentation
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08812v1
PDF	http://arxiv.org/pdf/1704.08812v1.pdf
PWC	https://paperswithcode.com/paper/automatic-real-time-background-cut-for
Repo
Framework

Class-specific Poisson denoising by patch-based importance sampling


Title	Class-specific Poisson denoising by patch-based importance sampling
Authors	Milad Niknejad, Jose M. Bioucas-Dias, Mario A. T. Figueiredo
Abstract	In this paper, we address the problem of recovering images degraded by Poisson noise, where the image is known to belong to a specific class. In the proposed method, a dataset of clean patches from images of the class of interest is clustered using multivariate Gaussian distributions. In order to recover the noisy image, each noisy patch is assigned to one of these distributions, and the corresponding minimum mean squared error (MMSE) estimate is obtained. We propose to use a self-normalized importance sampling approach, which is a method of the Monte-Carlo family, for the both determining the most likely distribution and approximating the MMSE estimate of the clean patch. Experimental results shows that our proposed method outperforms other methods for Poisson denoising at a low SNR regime.
Tasks	Denoising
Published	2017-06-09
URL	http://arxiv.org/abs/1706.02867v1
PDF	http://arxiv.org/pdf/1706.02867v1.pdf
PWC	https://paperswithcode.com/paper/class-specific-poisson-denoising-by-patch
Repo
Framework

Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR Data


Title	Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR Data
Authors	Dimitrios Marmanis, Wei Yao, Fathalrahman Adam, Mihai Datcu, Peter Reinartz, Konrad Schindler, Jan Dirk Wegner, Uwe Stilla
Abstract	Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field. In this work, we propose such a dataset and use it to explore patch-based classification in urban and periurban areas, considering 7 distinct semantic classes. In this context, we investigate the accuracy of large CNN classification models and pre-trained networks for SAR imaging systems. Furthermore, we propose a Generative Adversarial Network (GAN) for SAR image generation and test, whether the synthetic data can actually improve classification accuracy.
Tasks	Image Classification, Image Generation
Published	2017-11-06
URL	http://arxiv.org/abs/1711.02010v1
PDF	http://arxiv.org/pdf/1711.02010v1.pdf
PWC	https://paperswithcode.com/paper/artificial-generation-of-big-data-for
Repo
Framework

Linear Regression with Sparsely Permuted Data


Title	Linear Regression with Sparsely Permuted Data
Authors	Martin Slawski, Emanuel Ben-David
Abstract	In regression analysis of multivariate data, it is tacitly assumed that response and predictor variables in each observed response-predictor pair correspond to the same entity or unit. In this paper, we consider the situation of “permuted data” in which this basic correspondence has been lost. Several recent papers have considered this situation without further assumptions on the underlying permutation. In applications, the latter is often to known to have additional structure that can be leveraged. Specifically, we herein consider the common scenario of “sparsely permuted data” in which only a small fraction of the data is affected by a mismatch between response and predictors. However, an adverse effect already observed for sparsely permuted data is that the least squares estimator as well as other estimators not accounting for such partial mismatch are inconsistent. One approach studied in detail herein is to treat permuted data as outliers which motivates the use of robust regression formulations to estimate the regression parameter. The resulting estimate can subsequently be used to recover the permutation. A notable benefit of the proposed approach is its computational simplicity given the general lack of procedures for the above problem that are both statistically sound and computationally appealing.
Tasks
Published	2017-10-16
URL	http://arxiv.org/abs/1710.06030v2
PDF	http://arxiv.org/pdf/1710.06030v2.pdf
PWC	https://paperswithcode.com/paper/linear-regression-with-sparsely-permuted-data
Repo
Framework

Road Friction Estimation for Connected Vehicles using Supervised Machine Learning


Title	Road Friction Estimation for Connected Vehicles using Supervised Machine Learning
Authors	Ghazaleh Panahandeh, Erik Ek, Nasser Mohammadiha
Abstract	In this paper, the problem of road friction prediction from a fleet of connected vehicles is investigated. A framework is proposed to predict the road friction level using both historical friction data from the connected cars and data from weather stations, and comparative results from different methods are presented. The problem is formulated as a classification task where the available data is used to train three machine learning models including logistic regression, support vector machine, and neural networks to predict the friction class (slippery or non-slippery) in the future for specific road segments. In addition to the friction values, which are measured by moving vehicles, additional parameters such as humidity, temperature, and rainfall are used to obtain a set of descriptive feature vectors as input to the classification methods. The proposed prediction models are evaluated for different prediction horizons (0 to 120 minutes in the future) where the evaluation shows that the neural networks method leads to more stable results in different conditions.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05379v1
PDF	http://arxiv.org/pdf/1709.05379v1.pdf
PWC	https://paperswithcode.com/paper/road-friction-estimation-for-connected
Repo
Framework

Deep Neural Networks for Czech Multi-label Document Classification


Title	Deep Neural Networks for Czech Multi-label Document Classification
Authors	Ladislav Lenc, Pavel Král
Abstract	This paper is focused on automatic multi-label document classification of Czech text documents. The current approaches usually use some pre-processing which can have negative impact (loss of information, additional implementation work, etc). Therefore, we would like to omit it and use deep neural networks that learn from simple features. This choice was motivated by their successful usage in many other machine learning fields. Two different networks are compared: the first one is a standard multi-layer perceptron, while the second one is a popular convolutional network. The experiments on a Czech newspaper corpus show that both networks significantly outperform baseline method which uses a rich set of features with maximum entropy classifier. We have also shown that convolutional network gives the best results.
Tasks	Document Classification
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03849v2
PDF	http://arxiv.org/pdf/1701.03849v2.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-for-czech-multi-label
Repo
Framework

A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe


Title	A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe
Authors	Volodymyr Turchenko, Eric Chalmers, Artur Luczak
Abstract	This paper presents the development of several models of a deep convolutional auto-encoder in the Caffe deep learning framework and their experimental evaluation on the example of MNIST dataset. We have created five models of a convolutional auto-encoder which differ architecturally by the presence or absence of pooling and unpooling layers in the auto-encoder’s encoder and decoder parts. Our results show that the developed models provide very good results in dimensionality reduction and unsupervised clustering tasks, and small classification errors when we used the learned internal code as an input of a supervised linear classifier and multi-layer perceptron. The best results were provided by a model where the encoder part contains convolutional and pooling layers, followed by an analogous decoder part with deconvolution and unpooling layers without the use of switch variables in the decoder part. The paper also discusses practical details of the creation of a deep convolutional auto-encoder in the very popular Caffe deep learning framework. We believe that our approach and results presented in this paper could help other researchers to build efficient deep neural network architectures in the future.
Tasks	Dimensionality Reduction
Published	2017-01-18
URL	http://arxiv.org/abs/1701.04949v1
PDF	http://arxiv.org/pdf/1701.04949v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-convolutional-auto-encoder-with
Repo
Framework