July 27, 2019

3126 words 15 mins read

Paper Group ANR 588

Rapid parametric density estimation. Tensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localization. The Parallel Algorithm for the 2-D Discrete Wavelet Transform. Approximating meta-heuristics with homotopic recurrent neural networks. Towards co-evolution of fitness predictors and Deep Neural …

Rapid parametric density estimation


Title	Rapid parametric density estimation
Authors	Jarek Duda
Abstract	Parametric density estimation, for example as Gaussian distribution, is the base of the field of statistics. Machine learning requires inexpensive estimation of much more complex densities, and the basic approach is relatively costly maximum likelihood estimation (MLE). There will be discussed inexpensive density estimation, for example literally fitting a polynomial (or Fourier series) to the sample, which coefficients are calculated by just averaging monomials (or sine/cosine) over the sample. Another discussed basic application is fitting distortion to some standard distribution like Gaussian - analogously to ICA, but additionally allowing to reconstruct the disturbed density. Finally, by using weighted average, it can be also applied for estimation of non-probabilistic densities, like modelling mass distribution, or for various clustering problems by using negative (or complex) weights: fitting a function which sign (or argument) determines clusters. The estimated parameters are approaching the optimal values with error dropping like $1/\sqrt{n}$, where $n$ is the sample size.
Tasks	Density Estimation
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02144v2
PDF	http://arxiv.org/pdf/1702.02144v2.pdf
PWC	https://paperswithcode.com/paper/rapid-parametric-density-estimation
Repo
Framework

Tensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localization


Title	Tensor-Generative Adversarial Network with Two-dimensional Sparse Coding: Application to Real-time Indoor Localization
Authors	Chenxiao Zhu, Lingqing Xu, Xiao-Yang Liu, Feng Qian
Abstract	Localization technology is important for the development of indoor location-based services (LBS). Global Positioning System (GPS) becomes invalid in indoor environments due to the non-line-of-sight issue, so it is urgent to develop a real-time high-accuracy localization approach for smartphones. However, accurate localization is challenging due to issues such as real-time response requirements, limited fingerprint samples and mobile device storage. To address these problems, we propose a novel deep learning architecture: Tensor-Generative Adversarial Network (TGAN). We first introduce a transform-based 3D tensor to model fingerprint samples. Instead of those passive methods that construct a fingerprint database as a prior, our model applies artificial neural network with deep learning to train network classifiers and then gives out estimations. Then we propose a novel tensor-based super-resolution scheme using the generative adversarial network (GAN) that adopts sparse coding as the generator network and a residual learning network as the discriminator. Further, we analyze the performance of tensor-GAN and implement a trace-based localization experiment, which achieves better performance. Compared to existing methods for smartphones indoor positioning, that are energy-consuming and high demands on devices, TGAN can give out an improved solution in localization accuracy, response time and implementation complexity.
Tasks	Super-Resolution
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02666v1
PDF	http://arxiv.org/pdf/1711.02666v1.pdf
PWC	https://paperswithcode.com/paper/tensor-generative-adversarial-network-with
Repo
Framework

The Parallel Algorithm for the 2-D Discrete Wavelet Transform


Title	The Parallel Algorithm for the 2-D Discrete Wavelet Transform
Authors	David Barina, Pavel Najman, Petr Kleparnik, Michal Kula, Pavel Zemcik
Abstract	The discrete wavelet transform can be found at the heart of many image-processing algorithms. Until now, the transform on general-purpose processors (CPUs) was mostly computed using a separable lifting scheme. As the lifting scheme consists of a small number of operations, it is preferred for processing using single-core CPUs. However, considering a parallel processing using multi-core processors, this scheme is inappropriate due to a large number of steps. On such architectures, the number of steps corresponds to the number of points that represent the exchange of data. Consequently, these points often form a performance bottleneck. Our approach appropriately rearranges calculations inside the transform, and thereby reduces the number of steps. In other words, we propose a new scheme that is friendly to parallel environments. When evaluating on multi-core CPUs, we consistently overcome the original lifting scheme. The evaluation was performed on 61-core Intel Xeon Phi and 8-core Intel Xeon processors.
Tasks
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07853v3
PDF	http://arxiv.org/pdf/1708.07853v3.pdf
PWC	https://paperswithcode.com/paper/the-parallel-algorithm-for-the-2-d-discrete
Repo
Framework

Approximating meta-heuristics with homotopic recurrent neural networks


Title	Approximating meta-heuristics with homotopic recurrent neural networks
Authors	Alessandro Bay, Biswa Sengupta
Abstract	Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a graph. Meta-heuristic algorithms such as $A^{*}$ along with mixed-integer programming (MIP) methods are often employed for these problems. Our work demonstrates that it is possible to approximate solutions generated by a meta-heuristic algorithm using a deep recurrent neural network. We compare different methodologies based on reinforcement learning (RL) and recurrent neural networks (RNN) to gauge their respective quality of approximation. We show the viability of recurrent neural network solutions on a graph that has over 300 nodes and argue that a sequence-to-sequence network rather than other recurrent networks has improved approximation quality. Additionally, we argue that homotopy continuation – that increases chances of hitting an extremum – further improves the estimate generated by a vanilla RNN.
Tasks
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02194v1
PDF	http://arxiv.org/pdf/1709.02194v1.pdf
PWC	https://paperswithcode.com/paper/approximating-meta-heuristics-with-homotopic
Repo
Framework

Towards co-evolution of fitness predictors and Deep Neural Networks


Title	Towards co-evolution of fitness predictors and Deep Neural Networks
Authors	Włodzimierz Funika, Paweł Koperek
Abstract	Deep neural networks proved to be a very useful and powerful tool with many practical applications. They especially excel at learning from large data sets with labeled samples. However, in order to achieve good learning results, the network architecture has to be carefully designed. Creating an optimal topology requires a lot of experience and knowledge. Unfortunately there are no practically applicable algorithms which could help in this situation. Using an evolutionary process to develop new network topologies might solve this problem. The limiting factor in this case is the speed of evaluation of a single specimen (a single network architecture), which includes learning based on the whole large dataset. In this paper we propose to overcome this problem by using a fitness prediction technique: use subsets of the original training set to conduct the training process and use its results as an approximation of specimen’s fitness. We discuss the feasibility of this approach in context of the desired fitness predictor features and analyze whether subsets obtained in an evolutionary process can be used to estimate the fitness of the network topology. Finally we draw conclusions from our experiments and outline plans for future work.
Tasks
Published	2017-12-30
URL	http://arxiv.org/abs/1801.00119v1
PDF	http://arxiv.org/pdf/1801.00119v1.pdf
PWC	https://paperswithcode.com/paper/towards-co-evolution-of-fitness-predictors
Repo
Framework

A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network


Title	A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network
Authors	Xuanyang Xi, Yongkang Luo, Fengfu Li, Peng Wang, Hong Qiao
Abstract	Visual saliency detection aims at identifying the most visually distinctive parts in an image, and serves as a pre-processing step for a variety of computer vision and image processing tasks. To this end, the saliency detection procedure must be as fast and compact as possible and optimally processes input images in a real time manner. It is an essential application requirement for the saliency detection task. However, contemporary detection methods often utilize some complicated procedures to pursue feeble improvements on the detection precession, which always take hundreds of milliseconds and make them not easy to be applied practically. In this paper, we tackle this problem by proposing a fast and compact saliency score regression network which employs fully convolutional network, a special deep convolutional neural network, to estimate the saliency of objects in images. It is an extremely simplified end-to-end deep neural network without any pre-processings and post-processings. When given an image, the network can directly predict a dense full-resolution saliency map (image-to-image prediction). It works like a compact pipeline which effectively simplifies the detection procedure. Our method is evaluated on six public datasets, and experimental results show that it can achieve comparable or better precision performance than the state-of-the-art methods while get a significant improvement in detection speed (35 FPS, processing in real time).
Tasks	Saliency Detection
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00615v2
PDF	http://arxiv.org/pdf/1702.00615v2.pdf
PWC	https://paperswithcode.com/paper/a-fast-and-compact-saliency-score-regression
Repo
Framework

ChromaTag: A Colored Marker and Fast Detection Algorithm


Title	ChromaTag: A Colored Marker and Fast Detection Algorithm
Authors	Joseph DeGol, Timothy Bretl, Derek Hoiem
Abstract	Current fiducial marker detection algorithms rely on marker IDs for false positive rejection. Time is wasted on potential detections that will eventually be rejected as false positives. We introduce ChromaTag, a fiducial marker and detection algorithm designed to use opponent colors to limit and quickly reject initial false detections and grayscale for precise localization. Through experiments, we show that ChromaTag is significantly faster than current fiducial markers while achieving similar or better detection accuracy. We also show how tag size and viewing direction effect detection accuracy. Our contribution is significant because fiducial markers are often used in real-time applications (e.g. marker assisted robot navigation) where heavy computation is required by other parts of the system.
Tasks	Robot Navigation
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02982v1
PDF	http://arxiv.org/pdf/1708.02982v1.pdf
PWC	https://paperswithcode.com/paper/chromatag-a-colored-marker-and-fast-detection
Repo
Framework

Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning


Title	Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning
Authors	Dongyu Zhang, Liang Lin, Tianshui Chen, Xian Wu, Wenwei Tan, Ebroul Izquierdo
Abstract	Sketch portrait generation benefits a wide range of applications such as digital entertainment and law enforcement. Although plenty of efforts have been dedicated to this task, several issues still remain unsolved for generating vivid and detail-preserving personal sketch portraits. For example, quite a few artifacts may exist in synthesizing hairpins and glasses, and textural details may be lost in the regions of hair or mustache. Moreover, the generalization ability of current systems is somewhat limited since they usually require elaborately collecting a dictionary of examples or carefully tuning features/components. In this paper, we present a novel representation learning framework that generates an end-to-end photo-sketch mapping through structure and texture decomposition. In the training stage, we first decompose the input face photo into different components according to their representational contents (i.e., structural and textural parts) by using a pre-trained Convolutional Neural Network (CNN). Then, we utilize a Branched Fully Convolutional Neural Network (BFCN) for learning structural and textural representations, respectively. In addition, we design a Sorted Matching Mean Square Error (SM-MSE) metric to measure texture patterns in the loss function. In the stage of sketch rendering, our approach automatically generates structural and textural representations for the input photo and produces the final result via a probabilistic fusion scheme. Extensive experiments on several challenging benchmarks suggest that our approach outperforms example-based synthesis algorithms in terms of both perceptual and objective metrics. In addition, the proposed method also has better generalization ability across dataset without additional training.
Tasks	Representation Learning
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01453v1
PDF	http://arxiv.org/pdf/1710.01453v1.pdf
PWC	https://paperswithcode.com/paper/content-adaptive-sketch-portrait-generation
Repo
Framework

Policy Optimization by Genetic Distillation


Title	Policy Optimization by Genetic Distillation
Authors	Tanmay Gangwani, Jian Peng
Abstract	Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization. However, they have not been shown useful for deep reinforcement learning, possibly due to the catastrophic consequence of parameter crossovers of neural networks. Here, we present Genetic Policy Optimization (GPO), a new genetic algorithm for sample-efficient deep policy optimization. GPO uses imitation learning for policy crossover in the state space and applies policy gradient methods for mutation. Our experiments on MuJoCo tasks show that GPO as a genetic algorithm is able to provide superior performance over the state-of-the-art policy gradient methods and achieves comparable or higher sample efficiency.
Tasks	Imitation Learning, Policy Gradient Methods
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01012v2
PDF	http://arxiv.org/pdf/1711.01012v2.pdf
PWC	https://paperswithcode.com/paper/policy-optimization-by-genetic-distillation
Repo
Framework

On the Duality Between Retinex and Image Dehazing


Title	On the Duality Between Retinex and Image Dehazing
Authors	Adrian Galdran, Aitor Alvarez-Gila, Alessandro Bria, Javier Vazquez-Corral, Marcelo Bertalmio
Abstract	Image dehazing deals with the removal of undesired loss of visibility in outdoor images due to the presence of fog. Retinex is a color vision model mimicking the ability of the Human Visual System to robustly discount varying illuminations when observing a scene under different spectral lighting conditions. Retinex has been widely explored in the computer vision literature for image enhancement and other related tasks. While these two problems are apparently unrelated, the goal of this work is to show that they can be connected by a simple linear relationship. Specifically, most Retinex-based algorithms have the characteristic feature of always increasing image brightness, which turns them into ideal candidates for effective image dehazing by directly applying Retinex to a hazy image whose intensities have been inverted. In this paper, we give theoretical proof that Retinex on inverted intensities is a solution to the image dehazing problem. Comprehensive qualitative and quantitative results indicate that several classical and modern implementations of Retinex can be transformed into competing image dehazing algorithms performing on pair with more complex fog removal methods, and can overcome some of the main challenges associated with this problem.
Tasks	Image Dehazing, Image Enhancement
Published	2017-12-07
URL	http://arxiv.org/abs/1712.02754v2
PDF	http://arxiv.org/pdf/1712.02754v2.pdf
PWC	https://paperswithcode.com/paper/on-the-duality-between-retinex-and-image
Repo
Framework

An Evolutionary Stochastic-Local-Search Framework for One-Dimensional Cutting-Stock Problems


Title	An Evolutionary Stochastic-Local-Search Framework for One-Dimensional Cutting-Stock Problems
Authors	Georgios C. Chasparis, Michael Rossbory, Verena Haunschmid
Abstract	We introduce an evolutionary stochastic-local-search (SLS) algorithm for addressing a generalized version of the so-called 1/V/D/R cutting-stock problem. Cutting-stock problems are encountered often in industrial environments and the ability to address them efficiently usually results in large economic benefits. Traditionally linear-programming-based techniques have been utilized to address such problems, however their flexibility might be limited when nonlinear constraints and objective functions are introduced. To this end, this paper proposes an evolutionary SLS algorithm for addressing one-dimensional cutting-stock problems. The contribution lies in the introduction of a flexible structural framework of the optimization that may accommodate a large family of diversification strategies including a novel parallel pattern appropriate for SLS algorithms (not necessarily restricted to cutting-stock problems). We finally demonstrate through experiments in a real-world manufacturing problem the benefit in cost reduction of the considered diversification strategies.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08776v1
PDF	http://arxiv.org/pdf/1707.08776v1.pdf
PWC	https://paperswithcode.com/paper/an-evolutionary-stochastic-local-search
Repo
Framework

Nonparametric regression using deep neural networks with ReLU activation function


Title	Nonparametric regression using deep neural networks with ReLU activation function
Authors	Johannes Schmidt-Hieber
Abstract	Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of convergence (up to $\log n$-factors) under a general composition assumption on the regression function. The framework includes many well-studied structural constraints such as (generalized) additive models. While there is a lot of flexibility in the network architecture, the tuning parameter is the sparsity of the network. Specifically, we consider large networks with number of potential network parameters exceeding the sample size. The analysis gives some insights into why multilayer feedforward neural networks perform well in practice. Interestingly, for ReLU activation function the depth (number of layers) of the neural network architectures plays an important role and our theory suggests that for nonparametric regression, scaling the network depth with the sample size is natural. It is also shown that under the composition assumption wavelet estimators can only achieve suboptimal rates.
Tasks
Published	2017-08-22
URL	http://arxiv.org/abs/1708.06633v4
PDF	http://arxiv.org/pdf/1708.06633v4.pdf
PWC	https://paperswithcode.com/paper/nonparametric-regression-using-deep-neural
Repo
Framework

Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks


Title	Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks
Authors	Hokchhay Tann, Soheil Hashemi, Iris Bahar, Sherief Reda
Abstract	While Deep Neural Networks (DNNs) push the state-of-the-art in many machine learning applications, they often require millions of expensive floating-point operations for each input classification. This computation overhead limits the applicability of DNNs to low-power, embedded platforms and incurs high cost in data centers. This motivates recent interests in designing low-power, low-latency DNNs based on fixed-point, ternary, or even binary data precision. While recent works in this area offer promising results, they often lead to large accuracy drops when compared to the floating-point networks. We propose a novel approach to map floating-point based DNNs to 8-bit dynamic fixed-point networks with integer power-of-two weights with no change in network architecture. Our dynamic fixed-point DNNs allow different radix points between layers. During inference, power-of-two weights allow multiplications to be replaced with arithmetic shifts, while the 8-bit fixed-point representation simplifies both the buffer and adder design. In addition, we propose a hardware accelerator design to achieve low-power, low-latency inference with insignificant degradation in accuracy. Using our custom accelerator design with the CIFAR-10 and ImageNet datasets, we show that our method achieves significant power and energy savings while increasing the classification accuracy.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04288v1
PDF	http://arxiv.org/pdf/1705.04288v1.pdf
PWC	https://paperswithcode.com/paper/hardware-software-codesign-of-accurate
Repo
Framework

Computational Motility Tracking of Calcium Dynamics in Toxoplasma gondii


Title	Computational Motility Tracking of Calcium Dynamics in Toxoplasma gondii
Authors	Mojtaba Sedigh Fazli, Stephen Andrew Vella, Silvia N. J. Moreno, Shannon Quinn
Abstract	Toxoplasma gondii is the causative agent responsible for toxoplasmosis and serves as one of the most common parasites in the world. For a successful lytic cycle, T. gondii must traverse biological barriers in order to invade host cells, and as such, motility is critical for its virulence. Calcium signaling, governed by fluctuations in cytosolic calcium (Ca2+) concentrations, is utilized universally across life and regulates many cellular processes, including the stimulation of T. gondii virulence factors such as motility. Therefore, increases in cytosolic calcium, called calcium oscillations, serve as a means to link and quantify the intracellular signaling processes that lead to T. gondii motility and invasion. Here, we describe our work extracting, quantifying and modeling motility patterns of T. gondii before and after the addition of pharmacological drugs and/or extracellular calcium. We demonstrate a computational pipeline including a robust tracking system using optical flow and dense trajectory features to extract T. gondii motility patterns. Using this pipeline, we were able to track changes in T.gondii motility in response to cytosolic Ca2+ fluxes in extracellular parasites. This allows us to study how Ca2+ signaling via release from intracellular Ca2+ stores and/or from extracellular Ca2+ entry relates to motility patterns, a crucial first step in developing countermeasures for T. gondii virulence.
Tasks	Optical Flow Estimation
Published	2017-08-01
URL	http://arxiv.org/abs/1708.01871v2
PDF	http://arxiv.org/pdf/1708.01871v2.pdf
PWC	https://paperswithcode.com/paper/computational-motility-tracking-of-calcium
Repo
Framework

Neural Machine Translation with Extended Context


Title	Neural Machine Translation with Extended Context
Authors	Jörg Tiedemann, Yves Scherrer
Abstract	We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the use of extended source language context as well as bilingual context extensions. The models learn to distinguish between information from different segments and are surprisingly robust with respect to translation quality. In this pilot study, we observe interesting cross-sentential attention patterns that improve textual coherence in translation at least in some selected cases.
Tasks	Machine Translation
Published	2017-08-20
URL	http://arxiv.org/abs/1708.05943v1
PDF	http://arxiv.org/pdf/1708.05943v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-with-extended
Repo
Framework