July 27, 2019

2872 words 14 mins read

Paper Group ANR 749

A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese. Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition. A Semantic QA-Based Approach for Text Summarization Evaluation. Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning …

A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese


Title	A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese
Authors	Leandro B. dos Santos, Magali S. Duran, Nathan S. Hartmann, Arnaldo Candido Jr., Gustavo H. Paetzold, Sandra M. Aluisio
Abstract	Psycholinguistic properties of words have been used in various approaches to Natural Language Processing tasks, such as text simplification and readability assessment. Most of these properties are subjective, involving costly and time-consuming surveys to be gathered. Recent approaches use the limited datasets of psycholinguistic properties to extend them automatically to large lexicons. However, some of the resources used by such approaches are not available to most languages. This study presents a method to infer psycholinguistic properties for Brazilian Portuguese (BP) using regressors built with a light set of features usually available for less resourced languages: word length, frequency lists, lexical databases composed of school dictionaries and word embedding models. The correlations between the properties inferred are close to those obtained by related works. The resulting resource contains 26,874 words in BP annotated with concreteness, age of acquisition, imageability and subjective frequency.
Tasks	Text Simplification
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07008v1
PDF	http://arxiv.org/pdf/1705.07008v1.pdf
PWC	https://paperswithcode.com/paper/a-lightweight-regression-method-to-infer
Repo
Framework

Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition


Title	Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition
Authors	Matias Valdenegro-Toro
Abstract	Convolutional Neural Networks (CNN) have revolutionized perception for color images, and their application to sonar images has also obtained good results. But in general CNNs are difficult to train without a large dataset, need manual tuning of a considerable number of hyperparameters, and require many careful decisions by a designer. In this work, we evaluate three common decisions that need to be made by a CNN designer, namely the performance of transfer learning, the effect of object/image size and the relation between training set size. We evaluate three CNN models, namely one based on LeNet, and two based on the Fire module from SqueezeNet. Our findings are: Transfer learning with an SVM works very well, even when the train and transfer sets have no classes in common, and high classification performance can be obtained even when the target dataset is small. The ADAM optimizer combined with Batch Normalization can make a high accuracy CNN classifier, even with small image sizes (16 pixels). At least 50 samples per class are required to obtain $90%$ test accuracy, and using Dropout with a small dataset helps improve performance, but Batch Normalization is better when a large dataset is available.
Tasks	Transfer Learning
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02601v1
PDF	http://arxiv.org/pdf/1709.02601v1.pdf
PWC	https://paperswithcode.com/paper/best-practices-in-convolutional-networks-for
Repo
Framework

A Semantic QA-Based Approach for Text Summarization Evaluation


Title	A Semantic QA-Based Approach for Text Summarization Evaluation
Authors	Ping Chen, Fei Wu, Tong Wang, Wei Ding
Abstract	Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.
Tasks	Machine Translation, Text Simplification, Text Summarization
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06259v2
PDF	http://arxiv.org/pdf/1704.06259v2.pdf
PWC	https://paperswithcode.com/paper/a-semantic-qa-based-approach-for-text
Repo
Framework

Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning


Title	Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
Authors	Dingwen Zhang, Deyu Meng, Long Zhao, Junwei Han
Abstract	Weakly-supervised object detection (WOD) is a challenging problems in computer vision. The key problem is to simultaneously infer the exact object locations in the training images and train the object detectors, given only the training images with weak image-level labels. Intuitively, by simulating the selective attention mechanism of human visual system, saliency detection technique can select attractive objects in scenes and thus is a potential way to provide useful priors for WOD. However, the way to adopt saliency detection in WOD is not trivial since the detected saliency region might be possibly highly ambiguous in complex cases. To this end, this paper first comprehensively analyzes the challenges in applying saliency detection to WOD. Then, we make one of the earliest efforts to bridge saliency detection to WOD via the self-paced curriculum learning, which can guide the learning procedure to gradually achieve faithful knowledge of multi-class objects from easy to hard. The experimental results demonstrate that the proposed approach can successfully bridge saliency detection and WOD tasks and achieve the state-of-the-art object detection results under the weak supervision.
Tasks	Object Detection, Saliency Detection, Weakly Supervised Object Detection
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01290v1
PDF	http://arxiv.org/pdf/1703.01290v1.pdf
PWC	https://paperswithcode.com/paper/bridging-saliency-detection-to-weakly
Repo
Framework

A hybrid supervised/unsupervised machine learning approach to solar flare prediction


Title	A hybrid supervised/unsupervised machine learning approach to solar flare prediction
Authors	Federico Benvenuto, Michele Piana, Cristina Campi, Anna Maria Massone
Abstract	We introduce a hybrid approach to solar flare prediction, whereby a supervised regularization method is used to realize feature importance and an unsupervised clustering method is used to realize the binary flare/no-flare decision. The approach is validated against NOAA SWPC data.
Tasks	Feature Importance
Published	2017-06-21
URL	http://arxiv.org/abs/1706.07103v1
PDF	http://arxiv.org/pdf/1706.07103v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-supervisedunsupervised-machine
Repo
Framework

A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis


Title	A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
Authors	Tor Lattimore
Abstract	Existing strategies for finite-armed stochastic bandits mostly depend on a parameter of scale that must be known in advance. Sometimes this is in the form of a bound on the payoffs, or the knowledge of a variance or subgaussian parameter. The notable exceptions are the analysis of Gaussian bandits with unknown mean and variance by Cowan and Katehakis [2015] and of uniform distributions with unknown support [Cowan and Katehakis, 2015]. The results derived in these specialised cases are generalised here to the non-parametric setup, where the learner knows only a bound on the kurtosis of the noise, which is a scale free measure of the extremity of outliers.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08937v1
PDF	http://arxiv.org/pdf/1703.08937v1.pdf
PWC	https://paperswithcode.com/paper/a-scale-free-algorithm-for-stochastic-bandits
Repo
Framework

Integral Equations and Machine Learning


Title	Integral Equations and Machine Learning
Authors	Alexander Keller, Ken Dahm
Abstract	As both light transport simulation and reinforcement learning are ruled by the same Fredholm integral equation of the second kind, reinforcement learning techniques may be used for photorealistic image synthesis: Efficiency may be dramatically improved by guiding light transport paths by an approximate solution of the integral equation that is learned during rendering. In the light of the recent advances in reinforcement learning for playing games, we investigate the representation of an approximate solution of an integral equation by artificial neural networks and derive a loss function for that purpose. The resulting Monte Carlo and quasi-Monte Carlo methods train neural networks with standard information instead of linear information and naturally are able to generate an arbitrary number of training samples. The methods are demonstrated for applications in light transport simulation.
Tasks	Image Generation
Published	2017-12-17
URL	http://arxiv.org/abs/1712.06115v3
PDF	http://arxiv.org/pdf/1712.06115v3.pdf
PWC	https://paperswithcode.com/paper/integral-equations-and-machine-learning
Repo
Framework

An optimized shape descriptor based on structural properties of networks


Title	An optimized shape descriptor based on structural properties of networks
Authors	Gisele H. B. Miranda, Jeaneth Machicao, Odemir M. Bruno
Abstract	The structural analysis of shape boundaries leads to the characterization of objects as well as to the understanding of shape properties. The literature on graphs and networks have contributed to the structural characterization of shapes with different theoretical approaches. We performed a study on the relationship between the shape architecture and the network topology constructed over the shape boundary. For that, we used a method for network modeling proposed in 2009. Firstly, together with curvature analysis, we evaluated the proposed approach for regular polygons. This way, it was possible to investigate how the network measurements vary according to some specific shape properties. Secondly, we evaluated the performance of the proposed shape descriptor in classification tasks for three datasets, accounting for both real-world and synthetic shapes. We demonstrated that not only degree related measurements are capable of distinguishing classes of objects. Yet, when using measurements that account for distinct properties of the network structure, the construction of the shape descriptor becomes more computationally efficient. Given the fact the network is dynamically constructed, the number of iterations can be reduced. The proposed approach accounts for a more robust set of structural measurements, that improved the discriminant power of the shape descriptors.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.05104v1
PDF	http://arxiv.org/pdf/1711.05104v1.pdf
PWC	https://paperswithcode.com/paper/an-optimized-shape-descriptor-based-on
Repo
Framework

Kullback-Leibler Principal Component for Tensors is not NP-hard


Title	Kullback-Leibler Principal Component for Tensors is not NP-hard
Authors	Kejun Huang, Nicholas D. Sidiropoulos
Abstract	We study the problem of nonnegative rank-one approximation of a nonnegative tensor, and show that the globally optimal solution that minimizes the generalized Kullback-Leibler divergence can be efficiently obtained, i.e., it is not NP-hard. This result works for arbitrary nonnegative tensors with an arbitrary number of modes (including two, i.e., matrices). We derive a closed-form expression for the KL principal component, which is easy to compute and has an intuitive probabilistic interpretation. For generalized KL approximation with higher ranks, the problem is for the first time shown to be equivalent to multinomial latent variable modeling, and an iterative algorithm is derived that resembles the expectation-maximization algorithm. On the Iris dataset, we showcase how the derived results help us learn the model in an \emph{unsupervised} manner, and obtain strikingly close performance to that from supervised methods.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07925v1
PDF	http://arxiv.org/pdf/1711.07925v1.pdf
PWC	https://paperswithcode.com/paper/kullback-leibler-principal-component-for
Repo
Framework

GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures


Title	GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures
Authors	Gaëtan Hadjeres, Frank Nielsen, François Pachet
Abstract	VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-VAE, a Geodesic Latent Space Regularization for the Variational AutoEncoder architecture and its generalizations which allows a fine control on the embedding of the data into the latent space. When augmenting the VAE loss with this regularization, changes in the learned latent space reflects changes of the attributes of the data. This deeper understanding of the VAE latent space structure offers the possibility to modulate the attributes of the generated data in a continuous way. We demonstrate its efficiency on a monophonic music generation task where we manage to generate variations of discrete sequences in an intended and playful way.
Tasks	Music Generation
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04588v1
PDF	http://arxiv.org/pdf/1707.04588v1.pdf
PWC	https://paperswithcode.com/paper/glsr-vae-geodesic-latent-space-regularization
Repo
Framework

Recommender Systems with Random Walks: A Survey


Title	Recommender Systems with Random Walks: A Survey
Authors	Laknath Semage
Abstract	Recommender engines have become an integral component in today’s e-commerce systems. From recommending books in Amazon to finding friends in social networks such as Facebook, they have become omnipresent. Generally, recommender systems can be classified into two main categories: content based and collaborative filtering based models. Both these models build relationships between users and items to provide recommendations. Content based systems achieve this task by utilizing features extracted from the context available, whereas collaborative systems use shared interests between user-item subsets. There is another relatively unexplored approach for providing recommendations that utilizes a stochastic process named random walks. This study is a survey exploring use cases of random walks in recommender systems and an attempt at classifying them.
Tasks	Recommendation Systems
Published	2017-11-11
URL	http://arxiv.org/abs/1711.04101v1
PDF	http://arxiv.org/pdf/1711.04101v1.pdf
PWC	https://paperswithcode.com/paper/recommender-systems-with-random-walks-a
Repo
Framework

Multi-Robot Transfer Learning: A Dynamical System Perspective


Title	Multi-Robot Transfer Learning: A Dynamical System Perspective
Authors	Mohamed K. Helwa, Angela P. Schoellig
Abstract	Multi-robot transfer learning allows a robot to use data generated by a second, similar robot to improve its own behavior. The potential advantages are reducing the time of training and the unavoidable risks that exist during the training phase. Transfer learning algorithms aim to find an optimal transfer map between different robots. In this paper, we investigate, through a theoretical study of single-input single-output (SISO) systems, the properties of such optimal transfer maps. We first show that the optimal transfer learning map is, in general, a dynamic system. The main contribution of the paper is to provide an algorithm for determining the properties of this optimal dynamic map including its order and regressors (i.e., the variables it depends on). The proposed algorithm does not require detailed knowledge of the robots’ dynamics, but relies on basic system properties easily obtainable through simple experimental tests. We validate the proposed algorithm experimentally through an example of transfer learning between two different quadrotor platforms. Experimental results show that an optimal dynamic map, with correct properties obtained from our proposed algorithm, achieves 60-70% reduction of transfer learning error compared to the cases when the data is directly transferred or transferred using an optimal static map.
Tasks	Transfer Learning
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08689v1
PDF	http://arxiv.org/pdf/1707.08689v1.pdf
PWC	https://paperswithcode.com/paper/multi-robot-transfer-learning-a-dynamical
Repo
Framework

Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation with LIGO Data


Title	Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation with LIGO Data
Authors	Daniel George, E. A. Huerta
Abstract	The recent Nobel-prize-winning detections of gravitational waves from merging black holes and the subsequent detection of the collision of two neutron stars in coincidence with electromagnetic observations have inaugurated a new era of multimessenger astrophysics. To enhance the scope of this emergent science, we proposed the use of deep convolutional neural networks for the detection and characterization of gravitational wave signals in real-time. This method, Deep Filtering, was initially demonstrated using simulated LIGO noise. In this article, we present the extension of Deep Filtering using real data from the first observing run of LIGO, for both detection and parameter estimation of gravitational waves from binary black hole mergers with continuous data streams from multiple LIGO detectors. We show for the first time that machine learning can detect and estimate the true parameters of a real GW event observed by LIGO. Our comparisons show that Deep Filtering is far more computationally efficient than matched-filtering, while retaining similar sensitivity and lower errors, allowing real-time processing of weak time-series signals in non-stationary non-Gaussian noise, with minimal resources, and also enables the detection of new classes of gravitational wave sources that may go unnoticed with existing detection algorithms. This approach is uniquely suited to enable coincident detection campaigns of gravitational waves and their multimessenger counterparts in real-time.
Tasks	Gravitational Wave Detection, Time Series
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07966v2
PDF	http://arxiv.org/pdf/1711.07966v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-real-time-gravitational
Repo
Framework

Ensemble Sampling


Title	Ensemble Sampling
Authors	Xiuyuan Lu, Benjamin Van Roy
Abstract	Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a posterior distribution over models, which is tractable only for simple special cases. This paper develops ensemble sampling, which aims to approximate Thompson sampling while maintaining tractability even in the face of complex models such as neural networks. Ensemble sampling dramatically expands on the range of applications for which Thompson sampling is viable. We establish a theoretical basis that supports the approach and present computational results that offer further insight.
Tasks
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07347v3
PDF	http://arxiv.org/pdf/1705.07347v3.pdf
PWC	https://paperswithcode.com/paper/ensemble-sampling
Repo
Framework

Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds


Title	Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds
Authors	Mahdyar Ravanbakhsh, Enver Sangineto, Moin Nabi, Nicu Sebe
Abstract	Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios. However, the ambiguity and the lack of sufficient abnormal ground truth data makes end-to-end training of large deep networks hard in this domain. In this paper we propose to use Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data. During the adversarial GAN training, a discriminator (D) is used as a supervisor for the generator network (G) and vice versa. At testing time we use D to solve our discriminative task (abnormality detection), where D has been trained without the need of manually-annotated abnormal data. Moreover, in order to prevent G learn a trivial identity function, we use a cross-channel approach, forcing G to transform raw-pixel data in motion information and vice versa. The quantitative results on standard benchmarks show that our method outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.
Tasks	Anomaly Detection
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07680v2
PDF	http://arxiv.org/pdf/1706.07680v2.pdf
PWC	https://paperswithcode.com/paper/training-adversarial-discriminators-for-cross
Repo
Framework