July 27, 2019

3025 words 15 mins read

Paper Group ANR 493

Adaptive Sampling Strategies for Stochastic Optimization. An Annotated Corpus of Relational Strategies in Customer Service. Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach. Artifact reduction for separable non-local means. Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery. D …

Adaptive Sampling Strategies for Stochastic Optimization


Title	Adaptive Sampling Strategies for Stochastic Optimization
Authors	Raghu Bollapragada, Richard Byrd, Jorge Nocedal
Abstract	In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the regular computation of full gradients, the proposed method reduces variance by increasing the sample size as needed. The decision to increase the sample size is governed by an inner product test that ensures that search directions are descent directions with high probability. We show that the inner product test improves upon the well known norm test, and can be used as a basis for an algorithm that is globally convergent on nonconvex functions and enjoys a global linear rate of convergence on strongly convex functions. Numerical experiments on logistic regression problems illustrate the performance of the algorithm.
Tasks	Stochastic Optimization
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11258v1
PDF	http://arxiv.org/pdf/1710.11258v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-sampling-strategies-for-stochastic
Repo
Framework

An Annotated Corpus of Relational Strategies in Customer Service


Title	An Annotated Corpus of Relational Strategies in Customer Service
Authors	Ian Beaver, Cynthia Freeman, Abdullah Mueen
Abstract	We create and release the first publicly available commercial customer service corpus with annotated relational segments. Human-computer data from three live customer service Intelligent Virtual Agents (IVAs) in the domains of travel and telecommunications were collected, and reviewers marked all text that was deemed unnecessary to the determination of user intention. After merging the selections of multiple reviewers to create highlighted texts, a second round of annotation was done to determine the classes of language present in the highlighted sections such as the presence of Greetings, Backstory, Justification, Gratitude, Rants, or Emotions. This resulting corpus is a valuable resource for improving the quality and relational abilities of IVAs. As well as discussing the corpus itself, we compare the usage of such language in human-human interactions on TripAdvisor forums. We show that removal of this language from task-based inputs has a positive effect on IVA understanding by both an increase in confidence and improvement in responses, demonstrating the need for automated methods of its discovery.
Tasks
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05449v1
PDF	http://arxiv.org/pdf/1708.05449v1.pdf
PWC	https://paperswithcode.com/paper/an-annotated-corpus-of-relational-strategies
Repo
Framework

Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach


Title	Applying High-Resolution Visible Imagery to Satellite Melt Pond Fraction Retrieval: A Neural Network Approach
Authors	Qi Liu, Yawen Zhang, Qin Lv, Li Shang
Abstract	During summer, melt ponds have a significant influence on Arctic sea-ice albedo. The melt pond fraction (MPF) also has the ability to forecast the Arctic sea-ice in a certain period. It is important to retrieve accurate melt pond fraction (MPF) from satellite data for Arctic research. This paper proposes a satellite MPF retrieval model based on the multi-layer neural network, named MPF-NN. Our model uses multi-spectral satellite data as model input and MPF information from multi-site and multi-period visible imagery as prior knowledge for modeling. It can effectively model melt ponds evolution of different regions and periods over the Arctic. Evaluation results show that the MPF retrieved from MODIS data using the proposed model has an RMSE of 3.91% and a correlation coefficient of 0.73. The seasonal distribution of MPF is also consistent with previous results.
Tasks
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04281v1
PDF	http://arxiv.org/pdf/1704.04281v1.pdf
PWC	https://paperswithcode.com/paper/applying-high-resolution-visible-imagery-to
Repo
Framework

Artifact reduction for separable non-local means


Title	Artifact reduction for separable non-local means
Authors	Sanjay Ghosh, Kunal N. Chaudhury
Abstract	It was recently demonstrated [J. Electron. Imaging, 25(2), 2016] that one can perform fast non-local means (NLM) denoising of one-dimensional signals using a method called lifting. The cost of lifting is independent of the patch length, which dramatically reduces the run-time for large patches. Unfortunately, it is difficult to directly extend lifting for non-local means denoising of images. To bypass this, the authors proposed a separable approximation in which the image rows and columns are filtered using lifting. The overall algorithm is significantly faster than NLM, and the results are comparable in terms of PSNR. However, the separable processing often produces vertical and horizontal stripes in the image. This problem was previously addressed by using a bilateral filter-based post-smoothing, which was effective in removing some of the stripes. In this letter, we demonstrate that stripes can be mitigated in the first place simply by involving the neighboring rows (or columns) in the filtering. In other words, we use a two-dimensional search (similar to NLM), while still using one-dimensional patches (as in the previous proposal). The novelty is in the observation that one can use lifting for performing two-dimensional searches. The proposed approach produces artifact-free images, whose quality and PSNR are comparable to NLM, while being significantly faster.
Tasks	Denoising
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09552v1
PDF	http://arxiv.org/pdf/1710.09552v1.pdf
PWC	https://paperswithcode.com/paper/artifact-reduction-for-separable-non-local
Repo
Framework

Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery


Title	Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery
Authors	Mohammad Golbabaee, Zhouye Chen, Yves Wiaux, Mike E. Davies
Abstract	We adopt data structure in the form of cover trees and iteratively apply approximate nearest neighbour (ANN) searches for fast compressed sensing reconstruction of signals living on discrete smooth manifolds. Levering on the recent stability results for the inexact Iterative Projected Gradient (IPG) algorithm and by using the cover tree’s ANN searches, we decrease the projection cost of the IPG algorithm to be logarithmically growing with data population for low dimensional smooth manifolds. We apply our results to quantitative MRI compressed sensing and in particular within the Magnetic Resonance Fingerprinting (MRF) framework. For a similar (or sometimes better) reconstruction accuracy, we report 2-3 orders of magnitude reduction in computations compared to the standard iterative method which uses brute-force searches.
Tasks	Magnetic Resonance Fingerprinting
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07834v2
PDF	http://arxiv.org/pdf/1706.07834v2.pdf
PWC	https://paperswithcode.com/paper/cover-tree-compressed-sensing-for-fast-mr
Repo
Framework

Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges


Title	Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges
Authors	Mennatullah Siam, Sara Elkerdawy, Martin Jagersand, Senthil Yogamani
Abstract	Semantic segmentation was seen as a challenging computer vision problem few years ago. Due to recent advancements in deep learning, relatively accurate solutions are now possible for its use in automated driving. In this paper, the semantic segmentation problem is explored from the perspective of automated driving. Most of the current semantic segmentation algorithms are designed for generic images and do not incorporate prior structure and end goal for automated driving. First, the paper begins with a generic taxonomic survey of semantic segmentation algorithms and then discusses how it fits in the context of automated driving. Second, the particular challenges of deploying it into a safety system which needs high level of accuracy and robustness are listed. Third, different alternatives instead of using an independent semantic segmentation module are explored. Finally, an empirical evaluation of various semantic segmentation architectures was performed on CamVid dataset in terms of accuracy and speed. This paper is a preliminary shorter version of a more detailed survey which is work in progress.
Tasks	Semantic Segmentation
Published	2017-07-08
URL	http://arxiv.org/abs/1707.02432v2
PDF	http://arxiv.org/pdf/1707.02432v2.pdf
PWC	https://paperswithcode.com/paper/deep-semantic-segmentation-for-automated
Repo
Framework

Theoretical and Practical Advances on Smoothing for Extensive-Form Games


Title	Theoretical and Practical Advances on Smoothing for Extensive-Form Games
Authors	Christian Kroer, Kevin Waugh, Fatma Kilinc-Karzan, Tuomas Sandholm
Abstract	Sparse iterative methods, in particular first-order methods, are known to be among the most effective in solving large-scale two-player zero-sum extensive-form games. The convergence rates of these methods depend heavily on the properties of the distance-generating function that they are based on. We investigate the acceleration of first-order methods for solving extensive-form games through better design of the dilated entropy function—a class of distance-generating functions related to the domains associated with the extensive-form games. By introducing a new weighting scheme for the dilated entropy function, we develop the first distance-generating function for the strategy spaces of sequential games that has no dependence on the branching factor of the player. This result improves the convergence rate of several first-order methods by a factor of $\Omega(b^dd)$, where $b$ is the branching factor of the player, and $d$ is the depth of the game tree. Thus far, counterfactual regret minimization methods have been faster in practice, and more popular, than first-order methods despite their theoretically inferior convergence rates. Using our new weighting scheme and practical tuning we show that, for the first time, the excessive gap technique can be made faster than the fastest counterfactual regret minimization algorithm, CFR+, in practice.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.04849v2
PDF	http://arxiv.org/pdf/1702.04849v2.pdf
PWC	https://paperswithcode.com/paper/theoretical-and-practical-advances-on
Repo
Framework

Robust mixture modelling using sub-Gaussian stable distribution


Title	Robust mixture modelling using sub-Gaussian stable distribution
Authors	Mahdi Teimouri, Saeid Rezakhah, Adel Mohammdpour
Abstract	Heavy-tailed distributions are widely used in robust mixture modelling due to possessing thick tails. As a computationally tractable subclass of the stable distributions, sub-Gaussian $\alpha$-stable distribution received much interest in the literature. Here, we introduce a type of expectation maximization algorithm that estimates parameters of a mixture of sub-Gaussian stable distributions. A comparative study, in the presence of some well-known mixture models, is performed to show the robustness and performance of the mixture of sub-Gaussian $\alpha$-stable distributions for modelling, simulated, synthetic, and real data.
Tasks
Published	2017-01-24
URL	http://arxiv.org/abs/1701.06749v1
PDF	http://arxiv.org/pdf/1701.06749v1.pdf
PWC	https://paperswithcode.com/paper/robust-mixture-modelling-using-sub-gaussian
Repo
Framework

NODDI-SH: a computational efficient NODDI extension for fODF estimation in diffusion MRI


Title	NODDI-SH: a computational efficient NODDI extension for fODF estimation in diffusion MRI
Authors	Mauro Zucchelli, Maxime Descoteaux, Gloria Menegaz
Abstract	Diffusion Magnetic Resonance Imaging (DMRI) is the only non-invasive imaging technique which is able to detect the principal directions of water diffusion as well as neurites density in the human brain. Exploiting the ability of Spherical Harmonics (SH) to model spherical functions, we propose a new reconstruction model for DMRI data which is able to estimate both the fiber Orientation Distribution Function (fODF) and the relative volume fractions of the neurites in each voxel, which is robust to multiple fiber crossings. We consider a Neurite Orientation Dispersion and Density Imaging (NODDI) inspired single fiber diffusion signal to be derived from three compartments: intracellular, extracellular, and cerebrospinal fluid. The model, called NODDI-SH, is derived by convolving the single fiber response with the fODF in each voxel. NODDI-SH embeds the calculation of the fODF and the neurite density in a unified mathematical model providing efficient, robust and accurate results. Results were validated on simulated data and tested on \textit{in-vivo} data of human brain, and compared to and Constrained Spherical Deconvolution (CSD) for benchmarking. Results revealed competitive performance in all respects and inherent adaptivity to local microstructure, while sensibly reducing the computational cost. We also investigated NODDI-SH performance when only a limited number of samples are available for the fitting, demonstrating that 60 samples are enough to obtain reliable results. The fast computational time and the low number of signal samples required, make NODDI-SH feasible for clinical application.
Tasks
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08999v2
PDF	http://arxiv.org/pdf/1708.08999v2.pdf
PWC	https://paperswithcode.com/paper/noddi-sh-a-computational-efficient-noddi
Repo
Framework

Modified Frank-Wolfe Algorithm for Enhanced Sparsity in Support Vector Machine Classifiers


Title	Modified Frank-Wolfe Algorithm for Enhanced Sparsity in Support Vector Machine Classifiers
Authors	Carlos M. Alaíz, Johan A. K. Suykens
Abstract	This work proposes a new algorithm for training a re-weighted L2 Support Vector Machine (SVM), inspired on the re-weighted Lasso algorithm of Cand`es et al. and on the equivalence between Lasso and SVM shown recently by Jaggi. In particular, the margin required for each training vector is set independently, defining a new weighted SVM model. These weights are selected to be binary, and they are automatically adapted during the training of the model, resulting in a variation of the Frank-Wolfe optimization algorithm with essentially the same computational complexity as the original algorithm. As shown experimentally, this algorithm is computationally cheaper to apply since it requires less iterations to converge, and it produces models with a sparser representation in terms of support vectors and which are more stable with respect to the selection of the regularization hyper-parameter.
Tasks
Published	2017-06-19
URL	http://arxiv.org/abs/1706.05928v2
PDF	http://arxiv.org/pdf/1706.05928v2.pdf
PWC	https://paperswithcode.com/paper/modified-frank-wolfe-algorithm-for-enhanced
Repo
Framework

FPGA Architecture for Deep Learning and its application to Planetary Robotics


Title	FPGA Architecture for Deep Learning and its application to Planetary Robotics
Authors	Pranay Gankidi, Jekan Thangavelautham
Abstract	Autonomous control systems onboard planetary rovers and spacecraft benefit from having cognitive capabilities like learning so that they can adapt to unexpected situations in-situ. Q-learning is a form of reinforcement learning and it has been efficient in solving certain class of learning problems. However, embedded systems onboard planetary rovers and spacecraft rarely implement learning algorithms due to the constraints faced in the field, like processing power, chip size, convergence rate and costs due to the need for radiation hardening. These challenges present a compelling need for a portable, low-power, area efficient hardware accelerator to make learning algorithms practical onboard space hardware. This paper presents a FPGA implementation of Q-learning with Artificial Neural Networks (ANN). This method matches the massive parallelism inherent in neural network software with the fine-grain parallelism of an FPGA hardware thereby dramatically reducing processing time. Mars Science Laboratory currently uses Xilinx-Space-grade Virtex FPGA devices for image processing, pyrotechnic operation control and obstacle avoidance. We simulate and program our architecture on a Xilinx Virtex 7 FPGA. The architectural implementation for a single neuron Q-learning and a more complex Multilayer Perception (MLP) Q-learning accelerator has been demonstrated. The results show up to a 43-fold speed up by Virtex 7 FPGAs compared to a conventional Intel i5 2.3 GHz CPU. Finally, we simulate the proposed architecture using the Symphony simulator and compiler from Xilinx, and evaluate the performance and power consumption.
Tasks	Q-Learning
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07543v1
PDF	http://arxiv.org/pdf/1701.07543v1.pdf
PWC	https://paperswithcode.com/paper/fpga-architecture-for-deep-learning-and-its
Repo
Framework

English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor


Title	English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor
Authors	Yukio Matsumura, Takayuki Sato, Mamoru Komachi
Abstract	Neural machine translation (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an encoder-decoder-reconstructor framework for NMT using back-translation. In this method, they selected the best forward translation model in the same manner as Bahdanau et al. (2015), and then trained a bi-directional translation model as fine-tuning. Their experiments show that it offers significant improvement in BLEU scores in Chinese-English translation task. We confirm that our re-implementation also shows the same tendency and alleviates the problem of repeating and missing words in the translation on a English-Japanese task too. In addition, we evaluate the effectiveness of pre-training by comparing it with a jointly-trained model of forward translation and back-translation.
Tasks	Machine Translation
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08198v1
PDF	http://arxiv.org/pdf/1706.08198v1.pdf
PWC	https://paperswithcode.com/paper/english-japanese-neural-machine-translation
Repo
Framework

Study of Set-Membership Kernel Adaptive Algorithms and Applications


Title	Study of Set-Membership Kernel Adaptive Algorithms and Applications
Authors	R. C. de Lamare, André Flores
Abstract	Adaptive algorithms based on kernel structures have been a topic of significant research over the past few years. The main advantage is that they form a family of universal approximators, offering an elegant solution to problems with nonlinearities. Nevertheless these methods deal with kernel expansions, creating a growing structure also known as dictionary, whose size depends on the number of new inputs. In this paper we derive the set-membership kernel-based normalized least-mean square (SM-NKLMS) algorithm, which is capable of limiting the size of the dictionary created in stationary environments. We also derive as an extension the set-membership kernelized affine projection (SM-KAP) algorithm. Finally several experiments are presented to compare the proposed SM-NKLMS and SM-KAP algorithms to the existing methods.
Tasks
Published	2017-08-27
URL	http://arxiv.org/abs/1708.08142v1
PDF	http://arxiv.org/pdf/1708.08142v1.pdf
PWC	https://paperswithcode.com/paper/study-of-set-membership-kernel-adaptive
Repo
Framework

Snake: a Stochastic Proximal Gradient Algorithm for Regularized Problems over Large Graphs


Title	Snake: a Stochastic Proximal Gradient Algorithm for Regularized Problems over Large Graphs
Authors	Adil Salim, Pascal Bianchi, Walid Hachem
Abstract	A regularized optimization problem over a large unstructured graph is studied, where the regularization term is tied to the graph geometry. Typical regularization examples include the total variation and the Laplacian regularizations over the graph. When applying the proximal gradient algorithm to solve this problem, there exist quite affordable methods to implement the proximity operator (backward step) in the special case where the graph is a simple path without loops. In this paper, an algorithm, referred to as “Snake”, is proposed to solve such regularized problems over general graphs, by taking benefit of these fast methods. The algorithm consists in properly selecting random simple paths in the graph and performing the proximal gradient algorithm over these simple paths. This algorithm is an instance of a new general stochastic proximal gradient algorithm, whose convergence is proven. Applications to trend filtering and graph inpainting are provided among others. Numerical experiments are conducted over large graphs.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07027v1
PDF	http://arxiv.org/pdf/1712.07027v1.pdf
PWC	https://paperswithcode.com/paper/snake-a-stochastic-proximal-gradient
Repo
Framework

YoTube: Searching Action Proposal via Recurrent and Static Regression Networks


Title	YoTube: Searching Action Proposal via Recurrent and Static Regression Networks
Authors	Hongyuan Zhu, Romain Vial, Shijian Lu, Yonghong Tian, Xianbin Cao
Abstract	In this paper, we present YoTube-a novel network fusion framework for searching action proposals in untrimmed videos, where each action proposal corresponds to a spatialtemporal video tube that potentially locates one human action. Our method consists of a recurrent YoTube detector and a static YoTube detector, where the recurrent YoTube explores the regression capability of RNN for candidate bounding boxes predictions using learnt temporal dynamics and the static YoTube produces the bounding boxes using rich appearance cues in a single frame. Both networks are trained using rgb and optical flow in order to fully exploit the rich appearance, motion and temporal context, and their outputs are fused to produce accurate and robust proposal boxes. Action proposals are finally constructed by linking these boxes using dynamic programming with a novel trimming method to handle the untrimmed video effectively and efficiently. Extensive experiments on the challenging UCF-101 and UCF-Sports datasets show that our proposed technique obtains superior performance compared with the state-of-the-art.
Tasks	Optical Flow Estimation
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08218v1
PDF	http://arxiv.org/pdf/1706.08218v1.pdf
PWC	https://paperswithcode.com/paper/yotube-searching-action-proposal-via
Repo
Framework