October 17, 2019

3234 words 16 mins read

Paper Group ANR 795

Estimating Small Differences in Car-Pose from Orbits. Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks. Multitask Painting Categorization by Deep Multibranch Neural Network. DeepSIC: Deep Semantic Image Compression. Slice Sampling Particle Belief Propagation. Leveraging Adiabatic Quantum Computation for Elect …

Estimating Small Differences in Car-Pose from Orbits


Title	Estimating Small Differences in Car-Pose from Orbits
Authors	Berkay Kicanaoglu, Ran Tao, Arnold W. M. Smeulders
Abstract	Distinction among nearby poses and among symmetries of an object is challenging. In this paper, we propose a unified, group-theoretic approach to tackle both. Different from existing works which directly predict absolute pose, our method measures the pose of an object relative to another pose, i.e., the pose difference. The proposed method generates the complete orbit of an object from a single view of the object with respect to the subgroup of SO(3) of rotations around the z-axis, and compares the orbit of the object with another orbit using a novel orbit metric to estimate the pose difference. The generated orbit in the latent space records all the differences in pose in the original observational space, and as a result, the method is capable of finding subtle differences in pose. We demonstrate the effectiveness of the proposed method on cars, where identifying the subtle pose differences is vital.
Tasks
Published	2018-09-03
URL	http://arxiv.org/abs/1809.00720v1
PDF	http://arxiv.org/pdf/1809.00720v1.pdf
PWC	https://paperswithcode.com/paper/estimating-small-differences-in-car-pose-from
Repo
Framework

Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks


Title	Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks
Authors	Lijun Zhao, Huihui Bai, Feng Li, Anhong Wang, Yao Zhao
Abstract	In this paper, we propose an end-to-end mixed-resolution image compression framework with convolutional neural networks. Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard codec, as compared to the input image. Furthermore, we use post-processing neural network (PPNN) to remove the coding artifacts caused by quantization of codec. Secondly, low-resolution image representation is adopted for high efficiency compression in terms of most of bit spent by image’s structures under low bit-rate. However, more bits should be assigned to image details in the high-resolution, when most of structures have been kept after compression at the high bit-rate. This comes from a fact that the low-resolution image representation can’t burden more information than high-resolution representation beyond a certain bit-rate. Finally, to resolve the problem of error back-propagation from the PPNN network to the FDNN network, we introduce to learn a virtual codec neural network to imitate two continuous procedures of standard compression and post-processing. The objective experimental results have demonstrated the proposed method has a large margin improvement, when comparing with several state-of-the-art approaches.
Tasks	Image Compression, Quantization
Published	2018-02-02
URL	http://arxiv.org/abs/1802.01447v2
PDF	http://arxiv.org/pdf/1802.01447v2.pdf
PWC	https://paperswithcode.com/paper/mixed-resolution-image-representation-and
Repo
Framework

Multitask Painting Categorization by Deep Multibranch Neural Network


Title	Multitask Painting Categorization by Deep Multibranch Neural Network
Authors	Simone Bianco, Davide Mazzini, Paolo Napoletano, Raimondo Schettini
Abstract	In this work we propose a new deep multibranch neural network to solve the tasks of artist, style, and genre categorization in a multitask formulation. In order to gather clues from low-level texture details and, at the same time, exploit the coarse layout of the painting, the branches of the proposed networks are fed with crops at different resolutions. We propose and compare two different crop strategies: the first one is a random-crop strategy that permits to manage the tradeoff between accuracy and speed; the second one is a smart extractor based on Spatial Transformer Networks trained to extract the most representative subregions. Furthermore, inspired by the results obtained in other domains, we experiment the joint use of hand-crafted features directly computed on the input images along with neural ones. Experiments are performed on a new dataset originally sourced from wikiart.org and hosted by Kaggle, and made suitable for artist, style and genre multitask learning. The dataset here proposed, named MultitaskPainting100k, is composed by 100K paintings, 1508 artists, 125 styles and 41 genres. Our best method, tested on the MultitaskPainting100k dataset, achieves accuracy levels of 56.5%, 57.2%, and 63.6% on the tasks of artist, style and genre prediction respectively.
Tasks
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08052v1
PDF	http://arxiv.org/pdf/1812.08052v1.pdf
PWC	https://paperswithcode.com/paper/multitask-painting-categorization-by-deep
Repo
Framework

DeepSIC: Deep Semantic Image Compression


Title	DeepSIC: Deep Semantic Image Compression
Authors	Sihui Luo, Yezhou Yang, Mingli Song
Abstract	Incorporating semantic information into the codecs during image compression can significantly reduce the repetitive computation of fundamental semantic analysis (such as object recognition) in client-side applications. The same practice also enable the compressed code to carry the image semantic information during storage and transmission. In this paper, we propose a concept called Deep Semantic Image Compression (DeepSIC) and put forward two novel architectures that aim to reconstruct the compressed image and generate corresponding semantic representations at the same time. The first architecture performs semantic analysis in the encoding process by reserving a portion of the bits from the compressed code to store the semantic representations. The second performs semantic analysis in the decoding step with the feature maps that are embedded in the compressed code. In both architectures, the feature maps are shared by the compression and the semantic analytics modules. To validate our approaches, we conduct experiments on the publicly available benchmarking datasets and achieve promising results. We also provide a thorough analysis of the advantages and disadvantages of the proposed technique.
Tasks	Image Compression, Object Recognition
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09468v1
PDF	http://arxiv.org/pdf/1801.09468v1.pdf
PWC	https://paperswithcode.com/paper/deepsic-deep-semantic-image-compression
Repo
Framework

Slice Sampling Particle Belief Propagation


Title	Slice Sampling Particle Belief Propagation
Authors	Oliver Mueller, Michael Ying Yang, Bodo Rosenhahn
Abstract	Inference in continuous label Markov random fields is a challenging task. We use particle belief propagation (PBP) for solving the inference problem in continuous label space. Sampling particles from the belief distribution is typically done by using Metropolis-Hastings Markov chain Monte Carlo methods which involves sampling from a proposal distribution. This proposal distribution has to be carefully designed depending on the particular model and input data to achieve fast convergence. We propose to avoid dependence on a proposal distribution by introducing a slice sampling based PBP algorithm. The proposed approach shows superior convergence performance on an image denoising toy example. Our findings are validated on a challenging relational 2D feature tracking application.
Tasks	Denoising, Image Denoising
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03275v1
PDF	http://arxiv.org/pdf/1802.03275v1.pdf
PWC	https://paperswithcode.com/paper/slice-sampling-particle-belief-propagation
Repo
Framework

Leveraging Adiabatic Quantum Computation for Election Forecasting


Title	Leveraging Adiabatic Quantum Computation for Election Forecasting
Authors	Maxwell Henderson, John Novak, Tristan Cook
Abstract	Accurate, reliable sampling from fully-connected graphs with arbitrary correlations is a difficult problem. Such sampling requires knowledge of the probabilities of observing every possible state of a graph. As graph size grows, the number of model states becomes intractably large and efficient computation requires full sampling be replaced with heuristics and algorithms that are only approximations of full sampling. This work investigates the potential impact of adiabatic quantum computation for sampling purposes, building on recent successes training Boltzmann machines using a quantum device. We investigate the use case of quantum computation to train Boltzmann machines for predicting the 2016 Presidential election.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1802.00069v1
PDF	http://arxiv.org/pdf/1802.00069v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-adiabatic-quantum-computation-for
Repo
Framework


Title	Algorithmic Social Intervention
Authors	Bryan Wilder
Abstract	Social and behavioral interventions are a critical tool for governments and communities to tackle deep-rooted societal challenges such as homelessness, disease, and poverty. However, real-world interventions are almost always plagued by limited resources and limited data, which creates a computational challenge: how can we use algorithmic techniques to enhance the targeting and delivery of social and behavioral interventions? The goal of my thesis is to provide a unified study of such questions, collectively considered under the name “algorithmic social intervention”. This proposal introduces algorithmic social intervention as a distinct area with characteristic technical challenges, presents my published research in the context of these challenges, and outlines open problems for future work. A common technical theme is decision making under uncertainty: how can we find actions which will impact a social system in desirable ways under limitations of knowledge and resources? The primary application area for my work thus far is public health, e.g. HIV or tuberculosis prevention. For instance, I have developed a series of algorithms which optimize social network interventions for HIV prevention. Two of these algorithms have been pilot-tested in collaboration with LA-area service providers for homeless youth, with preliminary results showing substantial improvement over status-quo approaches. My work also spans other topics in infectious disease prevention and underlying algorithmic questions in robust and risk-aware submodular optimization.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2018-03-14
URL	http://arxiv.org/abs/1803.05098v1
PDF	http://arxiv.org/pdf/1803.05098v1.pdf
PWC	https://paperswithcode.com/paper/algorithmic-social-intervention
Repo
Framework

An Optimal Control View of Adversarial Machine Learning


Title	An Optimal Control View of Adversarial Machine Learning
Authors	Xiaojin Zhu
Abstract	I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary’s goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, including test-item attacks, training-data poisoning, and adversarial reward shaping. The view encourages adversarial machine learning researcher to utilize advances in control theory and reinforcement learning.
Tasks	data poisoning
Published	2018-11-11
URL	http://arxiv.org/abs/1811.04422v1
PDF	http://arxiv.org/pdf/1811.04422v1.pdf
PWC	https://paperswithcode.com/paper/an-optimal-control-view-of-adversarial
Repo
Framework

Modular Architecture for StarCraft II with Deep Reinforcement Learning


Title	Modular Architecture for StarCraft II with Deep Reinforcement Learning
Authors	Dennis Lee, Haoran Tang, Jeffrey O Zhang, Huazhe Xu, Trevor Darrell, Pieter Abbeel
Abstract	We present a novel modular architecture for StarCraft II AI. The architecture splits responsibilities between multiple modules that each control one aspect of the game, such as build-order selection or tactics. A centralized scheduler reviews macros suggested by all modules and decides their order of execution. An updater keeps track of environment changes and instantiates macros into series of executable actions. Modules in this framework can be optimized independently or jointly via human design, planning, or reinforcement learning. We apply deep reinforcement learning techniques to training two out of six modules of a modular agent with self-play, achieving 94% or 87% win rates against the “Harder” (level 5) built-in Blizzard bot in Zerg vs. Zerg matches, with or without fog-of-war.
Tasks	Starcraft, Starcraft II
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03555v1
PDF	http://arxiv.org/pdf/1811.03555v1.pdf
PWC	https://paperswithcode.com/paper/modular-architecture-for-starcraft-ii-with
Repo
Framework

Learning Implicit Brain MRI Manifolds with Deep Learning


Title	Learning Implicit Brain MRI Manifolds with Deep Learning
Authors	Camilo Bermudez, Andrew J. Plassard, Larry T. Davis, Allen T. Newton, Susan M Resnick, Bennett A. Landman
Abstract	An important task in image processing and neuroimaging is to extract quantitative information from the acquired images in order to make observations about the presence of disease or markers of development in populations. Having a lowdimensional manifold of an image allows for easier statistical comparisons between groups and the synthesis of group representatives. Previous studies have sought to identify the best mapping of brain MRI to a low-dimensional manifold, but have been limited by assumptions of explicit similarity measures. In this work, we use deep learning techniques to investigate implicit manifolds of normal brains and generate new, high-quality images. We explore implicit manifolds by addressing the problems of image synthesis and image denoising as important tools in manifold learning. First, we propose the unsupervised synthesis of T1-weighted brain MRI using a Generative Adversarial Network (GAN) by learning from 528 examples of 2D axial slices of brain MRI. Synthesized images were first shown to be unique by performing a crosscorrelation with the training set. Real and synthesized images were then assessed in a blinded manner by two imaging experts providing an image quality score of 1-5. The quality score of the synthetic image showed substantial overlap with that of the real images. Moreover, we use an autoencoder with skip connections for image denoising, showing that the proposed method results in higher PSNR than FSL SUSAN after denoising. This work shows the power of artificial networks to synthesize realistic imaging data, which can be used to improve image processing techniques and provide a quantitative framework to structural changes in the brain.
Tasks	Denoising, Image Denoising, Image Generation
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01847v1
PDF	http://arxiv.org/pdf/1801.01847v1.pdf
PWC	https://paperswithcode.com/paper/learning-implicit-brain-mri-manifolds-with
Repo
Framework

Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing


Title	Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing
Authors	Jetic Gū, Hassan S. Shavarani, Anoop Sarkar
Abstract	The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure. We exploit a top-down tree-structured model called DRNN (Doubly-Recurrent Neural Networks) first proposed by Alvarez-Melis and Jaakola (2017) to create an NMT model called Seq2DRNN that combines a sequential encoder with tree-structured decoding augmented with a syntax-aware attention model. Unlike previous approaches to syntax-based NMT which use dependency parsing models our method uses constituency parsing which we argue provides useful information for translation. In addition, we use the syntactic structure of the sentence to add new connections to the tree-structured decoder neural network (Seq2DRNN+SynC). We compare our NMT model with sequential and state of the art syntax-based NMT models and show that our model produces more fluent translations with better reordering. Since our model is capable of doing translation and constituency parsing at the same time we also compare our parsing accuracy against other neural parsing models.
Tasks	Constituency Parsing, Dependency Parsing, Machine Translation, Text Generation
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01854v1
PDF	http://arxiv.org/pdf/1809.01854v1.pdf
PWC	https://paperswithcode.com/paper/top-down-tree-structured-decoding-with
Repo
Framework

Real Time Sentiment Change Detection of Twitter Data Streams


Title	Real Time Sentiment Change Detection of Twitter Data Streams
Authors	Sotiris K. Tasoulis, Aristidis G. Vrahatis, Spiros V. Georgakopoulos, Vassilis P. Plagianakos
Abstract	In the past few years, there has been a huge growth in Twitter sentiment analysis having already provided a fair amount of research on sentiment detection of public opinion among Twitter users. Given the fact that Twitter messages are generated constantly with dizzying rates, a huge volume of streaming data is created, thus there is an imperative need for accurate methods for knowledge discovery and mining of this information. Although there exists a plethora of twitter sentiment analysis methods in the recent literature, the researchers have shifted to real-time sentiment identification on twitter streaming data, as expected. A major challenge is to deal with the Big Data challenges arising in Twitter streaming applications concerning both Volume and Velocity. Under this perspective, in this paper, a methodological approach based on open source tools is provided for real-time detection of changes in sentiment that is ultra efficient with respect to both memory consumption and computational cost. This is achieved by iteratively collecting tweets in real time and discarding them immediately after their process. For this purpose, we employ the Lexicon approach for sentiment characterizations, while change detection is achieved through appropriate control charts that do not require historical information. We believe that the proposed methodology provides the trigger for a potential large-scale monitoring of threads in an attempt to discover fake news spread or propaganda efforts in their early stages. Our experimental real-time analysis based on a recent hashtag provides evidence that the proposed approach can detect meaningful sentiment changes across a hashtags lifetime.
Tasks	Sentiment Analysis, Twitter Sentiment Analysis
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00482v1
PDF	http://arxiv.org/pdf/1804.00482v1.pdf
PWC	https://paperswithcode.com/paper/real-time-sentiment-change-detection-of
Repo
Framework

Optimally rotated coordinate systems for adaptive least-squares regression on sparse grids


Title	Optimally rotated coordinate systems for adaptive least-squares regression on sparse grids
Authors	Bastian Bohn, Michael Griebel, Jens Oettershagen
Abstract	For low-dimensional data sets with a large amount of data points, standard kernel methods are usually not feasible for regression anymore. Besides simple linear models or involved heuristic deep learning models, grid-based discretizations of larger (kernel) model classes lead to algorithms, which naturally scale linearly in the amount of data points. For moderate-dimensional or high-dimensional regression tasks, these grid-based discretizations suffer from the curse of dimensionality. Here, sparse grid methods have proven to circumvent this problem to a large extent. In this context, space- and dimension-adaptive sparse grids, which can detect and exploit a given low effective dimensionality of nominally high-dimensional data, are particularly successful. They nevertheless rely on an axis-aligned structure of the solution and exhibit issues for data with predominantly skewed and rotated coordinates. In this paper we propose a preprocessing approach for these adaptive sparse grid algorithms that determines an optimized, problem-dependent coordinate system and, thus, reduces the effective dimensionality of a given data set in the ANOVA sense. We provide numerical examples on synthetic data as well as real-world data to show how an adaptive sparse grid least squares algorithm benefits from our preprocessing method.
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06749v2
PDF	http://arxiv.org/pdf/1810.06749v2.pdf
PWC	https://paperswithcode.com/paper/optimally-rotated-coordinate-systems-for
Repo
Framework

Using Quantum Mechanics to Cluster Time Series


Title	Using Quantum Mechanics to Cluster Time Series
Authors	Clark Alexander, Luke Shi, Sofya Akhmametyeva
Abstract	In this article we present a method by which we can reduce a time series into a single point in $\mathbb{R}^{13}$. We have chosen 13 dimensions so as to prevent too many points from being labeled as “noise.” When using a Euclidean (or Mahalanobis) metric, a simple clustering algorithm will with near certainty label the majority of points as “noise.” On pure physical considerations, this is not possible. Included in our 13 dimensions are four parameters which describe the coefficients of a cubic polynomial attached to a Gaussian picking up a general trend, four parameters picking up periodicity in a time series, two each for amplitude of a wave and period of a wave, and the final five report the “leftover” noise of the detrended and aperiodic time series. Of the final five parameters, four are the centralized probabilistic moments, and the final for the relative size of the series. The first main contribution of this work is to apply a theorem of quantum mechanics about the completeness of the solutions to the quantum harmonic oscillator on $L^2(\mathbb{R})$ to estimating trends in time series. The second main contribution is the method of fitting parameters. After many numerical trials, we realized that methods such a Newton-Rhaphson and Levenberg-Marquardt converge extremely fast if the initial guess is good. Thus we guessed many initial points in our parameter space and computed only a few iterations, a technique common in Keogh’s work on time series clustering. Finally, we have produced a model which gives incredibly accurate results quickly. We ackowledge that there are faster methods as well of more accurate methods, but this work shows that we can still increase computation speed with little, if any, cost to accuracy in the sense of data clustering.
Tasks	Time Series, Time Series Clustering
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01711v1
PDF	http://arxiv.org/pdf/1805.01711v1.pdf
PWC	https://paperswithcode.com/paper/using-quantum-mechanics-to-cluster-time
Repo
Framework

Variational Self-attention Model for Sentence Representation


Title	Variational Self-attention Model for Sentence Representation
Authors	Qiang Zhang, Shangsong Liang, Emine Yilmaz
Abstract	This paper proposes a variational self-attention model (VSAM) that employs variational inference to derive self-attention. We model the self-attention vector as random variables by imposing a probabilistic distribution. The self-attention mechanism summarizes source information as an attention vector by weighted sum, where the weights are a learned probabilistic distribution. Compared with conventional deterministic counterpart, the stochastic units incorporated by VSAM allow multi-modal attention distributions. Furthermore, by marginalizing over the latent variables, VSAM is more robust against overfitting. Experiments on the stance detection task demonstrate the superiority of our method.
Tasks	Stance Detection
Published	2018-12-30
URL	https://arxiv.org/abs/1812.11559v4
PDF	https://arxiv.org/pdf/1812.11559v4.pdf
PWC	https://paperswithcode.com/paper/variational-self-attention-model-for-sentence
Repo
Framework