July 27, 2019

3151 words 15 mins read

Paper Group ANR 677

Developpement de Methodes Automatiques pour la Reutilisation des Composants Logiciels. From Depth Data to Head Pose Estimation: a Siamese approach. High Five: Improving Gesture Recognition by Embracing Uncertainty. Distributed Bayesian Matrix Factorization with Limited Communication. Using Deep Convolutional Networks for Gesture Recognition in Amer …

Developpement de Methodes Automatiques pour la Reutilisation des Composants Logiciels


Title	Developpement de Methodes Automatiques pour la Reutilisation des Composants Logiciels
Authors	Kouakou Ive Arsene Koffi, Konan Marcellin Brou, Souleymane Oumtanaga
Abstract	The large amount of information and the increasing complexity of applications constrain developers to have stand-alone and reusable components from libraries and component markets.Our approach consists in developing methods to evaluate the quality of the software component of these libraries, on the one hand and moreover to optimize the financial cost and the adaptation’s time of these selected components. Our objective function defines a metric that maximizes the value of the software component quality by minimizing the financial cost and maintenance time. This model should make it possible to classify the components and order them in order to choose the most optimized. MOTS-CLES : d{'e}veloppement de m{'e}thode, r{'e}utilisation, composants logiciels, qualit{'e} de composant KEYWORDS:method development, reuse, software components, component quality .
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.09749v1
PDF	http://arxiv.org/pdf/1703.09749v1.pdf
PWC	https://paperswithcode.com/paper/developpement-de-methodes-automatiques-pour
Repo
Framework

From Depth Data to Head Pose Estimation: a Siamese approach


Title	From Depth Data to Head Pose Estimation: a Siamese approach
Authors	Marco Venturelli, Guido Borghi, Roberto Vezzani, Rita Cucchiara
Abstract	The correct estimation of the head pose is a problem of the great importance for many applications. For instance, it is an enabling technology in automotive for driver attention monitoring. In this paper, we tackle the pose estimation problem through a deep learning network working in regression manner. Traditional methods usually rely on visual facial features, such as facial landmarks or nose tip position. In contrast, we exploit a Convolutional Neural Network (CNN) to perform head pose estimation directly from depth data. We exploit a Siamese architecture and we propose a novel loss function to improve the learning of the regression network layer. The system has been tested on two public datasets, Biwi Kinect Head Pose and ICT-3DHP database. The reported results demonstrate the improvement in accuracy with respect to current state-of-the-art approaches and the real time capabilities of the overall framework.
Tasks	Driver Attention Monitoring, Head Pose Estimation, Pose Estimation
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03624v1
PDF	http://arxiv.org/pdf/1703.03624v1.pdf
PWC	https://paperswithcode.com/paper/from-depth-data-to-head-pose-estimation-a
Repo
Framework

High Five: Improving Gesture Recognition by Embracing Uncertainty


Title	High Five: Improving Gesture Recognition by Embracing Uncertainty
Authors	Diman Zad Tootaghaj, Adrian Sampson, Todd Mytkowicz, Kathryn S McKinley
Abstract	Sensors on mobile devices—accelerometers, gyroscopes, pressure meters, and GPS—invite new applications in gesture recognition, gaming, and fitness tracking. However, programming them remains challenging because human gestures captured by sensors are noisy. This paper illustrates that noisy gestures degrade training and classification accuracy for gesture recognition in state-of-the-art deterministic Hidden Markov Models (HMM). We introduce a new statistical quantization approach that mitigates these problems by (1) during training, producing gesture-specific codebooks, HMMs, and error models for gesture sequences; and (2) during classification, exploiting the error model to explore multiple feasible HMM state sequences. We implement classification in Uncertain, a probabilistic programming system that encapsulates HMMs and error models and then automates sampling and inference in the runtime. Uncertain developers directly express a choice of application-specific trade-off between recall and precision at gesture recognition time, rather than at training time. We demonstrate benefits in configurability, precision, recall, and recognition on two data sets with 25 gestures from 28 people and 4200 total gestures. Incorporating gesture error more accurately in modeling improves the average recognition rate of 20 gestures from 34% in prior work to 62%. Incorporating the error model during classification further improves the average gesture recognition rate to 71%. As far as we are aware, no prior work shows how to generate an HMM error model during training and use it to improve classification rates.
Tasks	Gesture Recognition, Probabilistic Programming, Quantization
Published	2017-10-25
URL	http://arxiv.org/abs/1710.09441v1
PDF	http://arxiv.org/pdf/1710.09441v1.pdf
PWC	https://paperswithcode.com/paper/high-five-improving-gesture-recognition-by
Repo
Framework

Distributed Bayesian Matrix Factorization with Limited Communication


Title	Distributed Bayesian Matrix Factorization with Limited Communication
Authors	Xiangju Qin, Paul Blomstedt, Eemeli Leppäaho, Pekka Parviainen, Samuel Kaski
Abstract	Bayesian matrix factorization (BMF) is a powerful tool for producing low-rank representations of matrices and for predicting missing values and providing confidence intervals. Scaling up the posterior inference for massive-scale matrices is challenging and requires distributing both data and computation over many workers, making communication the main computational bottleneck. Embarrassingly parallel inference would remove the communication needed, by using completely independent computations on different data subsets, but it suffers from the inherent unidentifiability of BMF solutions. We introduce a hierarchical decomposition of the joint posterior distribution, which couples the subset inferences, allowing for embarrassingly parallel computations in a sequence of at most three stages. Using an efficient approximate implementation, we show improvements empirically on both real and simulated data. Our distributed approach is able to achieve a speed-up of almost an order of magnitude over the full posterior, with a negligible effect on predictive accuracy. Our method outperforms state-of-the-art embarrassingly parallel MCMC methods in accuracy, and achieves results competitive to other available distributed and parallel implementations of BMF.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00734v4
PDF	http://arxiv.org/pdf/1703.00734v4.pdf
PWC	https://paperswithcode.com/paper/distributed-bayesian-matrix-factorization
Repo
Framework

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language


Title	Using Deep Convolutional Networks for Gesture Recognition in American Sign Language
Authors	Vivek Bheda, Dianna Radpour
Abstract	In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied areas. In line with recent advances in the field of deep learning, there are far reaching implications and applications that neural networks can have for sign language interpretation. In this paper, we present a method for using deep convolutional networks to classify images of both the the letters and digits in American Sign Language.
Tasks	Gesture Recognition
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06836v3
PDF	http://arxiv.org/pdf/1710.06836v3.pdf
PWC	https://paperswithcode.com/paper/using-deep-convolutional-networks-for-gesture
Repo
Framework

A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts


Title	A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
Authors	Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal
Abstract	Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks(GANs) to generate images, we instead leverage GANs to imagine unseen categories from text descriptions and hence recognize novel classes with no examples being seen. Specifically, we propose a simple yet effective generative model that takes as input noisy text descriptions about an unseen class (e.g.Wikipedia articles) and generates synthesized visual features for this class. With added pseudo data, zero-shot learning is naturally converted to a traditional classification problem. Additionally, to preserve the inter-class discrimination of the generated features, a visual pivot regularization is proposed as an explicit supervision. Unlike previous methods using complex engineered regularizers, our approach can suppress the noise well without additional regularization. Empirically, we show that our method consistently outperforms the state of the art on the largest available benchmarks on Text-based Zero-shot Learning.
Tasks	Zero-Shot Learning
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01381v3
PDF	http://arxiv.org/pdf/1712.01381v3.pdf
PWC	https://paperswithcode.com/paper/a-generative-adversarial-approach-for-zero
Repo
Framework

Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis


Title	Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis
Authors	Pengyuan Lyu, Xiang Bai, Cong Yao, Zhen Zhu, Tengteng Huang, Wenyu Liu
Abstract	In this paper, we investigate the Chinese calligraphy synthesis problem: synthesizing Chinese calligraphy images with specified style from standard font(eg. Hei font) images (Fig. 1(a)). Recent works mostly follow the stroke extraction and assemble pipeline which is complex in the process and limited by the effect of stroke extraction. We treat the calligraphy synthesis problem as an image-to-image translation problem and propose a deep neural network based model which can generate calligraphy images from standard font images directly. Besides, we also construct a large scale benchmark that contains various styles for Chinese calligraphy synthesis. We evaluate our method as well as some baseline methods on the proposed dataset, and the experimental results demonstrate the effectiveness of our proposed model.
Tasks	Image-to-Image Translation
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08789v1
PDF	http://arxiv.org/pdf/1706.08789v1.pdf
PWC	https://paperswithcode.com/paper/auto-encoder-guided-gan-for-chinese
Repo
Framework

Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation


Title	Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
Authors	Ngan Le, Kha Gia Quach, Khoa Luu, Marios Savvides, Chenchen Zhu
Abstract	Variational Level Set (LS) has been a widely used method in medical segmentation. However, it is limited when dealing with multi-instance objects in the real world. In addition, its segmentation results are quite sensitive to initial settings and highly depend on the number of iterations. To address these issues and boost the classic variational LS methods to a new level of the learnable deep learning approaches, we propose a novel definition of contour evolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under the energy minimization of a variational LS functional. The curve deformation process in RLS is formed as a hidden state evolution procedure and updated by minimizing an energy functional composed of fitting forces and contour length. By sharing the convolutional features in a fully end-to-end trainable framework, we extend RLS to Contextual RLS (CRLS) to address semantic segmentation in the wild. The experimental results have shown that our proposed RLS improves both computational time and segmentation accuracy against the classic variations LS-based method, whereas the fully end-to-end system CRLS achieves competitive performance compared to the state-of-the-art semantic segmentation approaches.
Tasks	Semantic Segmentation
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03593v1
PDF	http://arxiv.org/pdf/1704.03593v1.pdf
PWC	https://paperswithcode.com/paper/reformulating-level-sets-as-deep-recurrent
Repo
Framework

Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network


Title	Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network
Authors	Loic Bontemps, Van Loi Cao, James McDermott, Nhien-An Le-Khac
Abstract	Intrusion detection for computer network systems becomes one of the most critical tasks for network administrators today. It has an important role for organizations, governments and our society due to its valuable resources on computer networks. Traditional misuse detection strategies are unable to detect new and unknown intrusion. Besides, anomaly detection in network security is aim to distinguish between illegal or malicious events and normal behavior of network systems. Anomaly detection can be considered as a classification problem where it builds models of normal network behavior, which it uses to detect new patterns that significantly deviate from the model. Most of the cur- rent research on anomaly detection is based on the learning of normally and anomaly behaviors. They do not take into account the previous, re- cent events to detect the new incoming one. In this paper, we propose a real time collective anomaly detection model based on neural network learning and feature operating. Normally a Long Short Term Memory Recurrent Neural Network (LSTM RNN) is trained only on normal data and it is capable of predicting several time steps ahead of an input. In our approach, a LSTM RNN is trained with normal time series data before performing a live prediction for each time step. Instead of considering each time step separately, the observation of prediction errors from a certain number of time steps is now proposed as a new idea for detecting collective anomalies. The prediction errors from a number of the latest time steps above a threshold will indicate a collective anomaly. The model is built on a time series version of the KDD 1999 dataset. The experiments demonstrate that it is possible to offer reliable and efficient for collective anomaly detection.
Tasks	Anomaly Detection, Intrusion Detection, Time Series
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09752v1
PDF	http://arxiv.org/pdf/1703.09752v1.pdf
PWC	https://paperswithcode.com/paper/collective-anomaly-detection-based-on-long
Repo
Framework

Nudged elastic band calculations accelerated with Gaussian process regression


Title	Nudged elastic band calculations accelerated with Gaussian process regression
Authors	Olli-Pekka Koistinen, Freyja B. Dagbjartsdóttir, Vilhjálmur Ásgeirsson, Aki Vehtari, Hannes Jónsson
Abstract	Minimum energy paths for transitions such as atomic and/or spin rearrangements in thermalized systems are the transition paths of largest statistical weight. Such paths are frequently calculated using the nudged elastic band method, where an initial path is iteratively shifted to the nearest minimum energy path. The computational effort can be large, especially when ab initio or electron density functional calculations are used to evaluate the energy and atomic forces. Here, we show how the number of such evaluations can be reduced by an order of magnitude using a Gaussian process regression approach where an approximate energy surface is generated and refined in each iteration. When the goal is to evaluate the transition rate within harmonic transition state theory, the evaluation of the Hessian matrix at the initial and final state minima can be carried out beforehand and used as input in the minimum energy path calculation, thereby improving stability and reducing the number of iterations needed for convergence. A Gaussian process model also provides an uncertainty estimate for the approximate energy surface, and this can be used to focus the calculations on the lesser-known part of the path, thereby reducing the number of needed energy and force evaluations to a half in the present calculations. The methodology is illustrated using the two-dimensional M"uller-Brown potential surface and performance assessed on an established benchmark involving 13 rearrangement transitions of a heptamer island on a solid surface.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04606v2
PDF	http://arxiv.org/pdf/1706.04606v2.pdf
PWC	https://paperswithcode.com/paper/nudged-elastic-band-calculations-accelerated
Repo
Framework

Using Echo State Networks for Cryptography


Title	Using Echo State Networks for Cryptography
Authors	Rajkumar Ramamurthy, Christian Bauckhage, Krisztian Buza, Stefan Wrobel
Abstract	Echo state networks are simple recurrent neural networks that are easy to implement and train. Despite their simplicity, they show a form of memory and can predict or regenerate sequences of data. We make use of this property to realize a novel neural cryptography scheme. The key idea is to assume that Alice and Bob share a copy of an echo state network. If Alice trains her copy to memorize a message, she can communicate the trained part of the network to Bob who plugs it into his copy to regenerate the message. Considering a byte-level representation of in- and output, the technique applies to arbitrary types of data (texts, images, audio files, etc.) and practical experiments reveal it to satisfy the fundamental cryptographic properties of diffusion and confusion.
Tasks
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01046v1
PDF	http://arxiv.org/pdf/1704.01046v1.pdf
PWC	https://paperswithcode.com/paper/using-echo-state-networks-for-cryptography
Repo
Framework

Fractal dimension analysis for automatic morphological galaxy classification


Title	Fractal dimension analysis for automatic morphological galaxy classification
Authors	Jorge de la Calleja, Elsa M. de la Calleja, Hugo Jair Escalante
Abstract	In this report we present experimental results using \emph{Haussdorf-Besicovich} fractal dimension for performing morphological galaxy classification. The fractal dimension is a topological, structural and spatial property that give us information about the space were an object lives. We have calculated the fractal dimension value of the main types of galaxies: ellipticals, spirals and irregulars; and we use it as a feature for classifying them. Also, we have performed an image analysis process in order to standardize the galaxy images, and we have used principal component analysis to obtain the main attributes in the images. Galaxy classification was performed using machine learning algorithms: C4.5, k-nearest neighbors, random forest and support vector machines. Preliminary experimental results using 10-fold cross-validation show that fractal dimension helps to improve classification, with over 88 per cent accuracy for elliptical galaxies, 100 per cent accuracy for spiral galaxies and over 40 per cent for irregular galaxies.
Tasks
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07507v1
PDF	http://arxiv.org/pdf/1706.07507v1.pdf
PWC	https://paperswithcode.com/paper/fractal-dimension-analysis-for-automatic
Repo
Framework

Adaptive Smoothing in fMRI Data Processing Neural Networks


Title	Adaptive Smoothing in fMRI Data Processing Neural Networks
Authors	Albert Vilamala, Kristoffer Hougaard Madsen, Lars Kai Hansen
Abstract	Functional Magnetic Resonance Imaging (fMRI) relies on multi-step data processing pipelines to accurately determine brain activity; among them, the crucial step of spatial smoothing. These pipelines are commonly suboptimal, given the local optimisation strategy they use, treating each step in isolation. With the advent of new tools for deep learning, recent work has proposed to turn these pipelines into end-to-end learning networks. This change of paradigm offers new avenues to improvement as it allows for a global optimisation. The current work aims at benefitting from this paradigm shift by defining a smoothing step as a layer in these networks able to adaptively modulate the degree of smoothing required by each brain volume to better accomplish a given data analysis task. The viability is evaluated on real fMRI data where subjects did alternate between left and right finger tapping tasks.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00629v1
PDF	http://arxiv.org/pdf/1710.00629v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-smoothing-in-fmri-data-processing
Repo
Framework

PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples


Title	PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Authors	Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman
Abstract	Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show empirically that adversarial examples mainly lie in the low probability regions of the training distribution, regardless of attack types and targeted models. Using statistical hypothesis testing, we find that modern neural density models are surprisingly good at detecting imperceptible image perturbations. Based on this discovery, we devised PixelDefend, a new approach that purifies a maliciously perturbed image by moving it back towards the distribution seen in the training data. The purified image is then run through an unmodified classifier, making our method agnostic to both the classifier and the attacking method. As a result, PixelDefend can be used to protect already deployed models and be combined with other model-specific defenses. Experiments show that our method greatly improves resilience across a wide variety of state-of-the-art attacking methods, increasing accuracy on the strongest attack from 63% to 84% for Fashion MNIST and from 32% to 70% for CIFAR-10.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10766v3
PDF	http://arxiv.org/pdf/1710.10766v3.pdf
PWC	https://paperswithcode.com/paper/pixeldefend-leveraging-generative-models-to
Repo
Framework

Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation


Title	Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
Authors	Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine
Abstract	Manipulation of deformable objects, such as ropes and cloth, is an important but challenging problem in robotics. We present a learning-based system where a robot takes as input a sequence of images of a human manipulating a rope from an initial to goal configuration, and outputs a sequence of actions that can reproduce the human demonstration, using only monocular images as input. To perform this task, the robot learns a pixel-level inverse dynamics model of rope manipulation directly from images in a self-supervised manner, using about 60K interactions with the rope collected autonomously by the robot. The human demonstration provides a high-level plan of what to do and the low-level inverse model is used to execute the plan. We show that by combining the high and low-level plans, the robot can successfully manipulate a rope into a variety of target shapes using only a sequence of human-provided images for direction.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.02018v1
PDF	http://arxiv.org/pdf/1703.02018v1.pdf
PWC	https://paperswithcode.com/paper/combining-self-supervised-learning-and
Repo
Framework