July 29, 2019

3064 words 15 mins read

Paper Group ANR 109

Generative diffeomorphic atlas construction from brain and spinal cord MRI data. On the idea of a new artificial intelligence based optimization algorithm inspired from the nature of vortex. Learning of Gaussian Processes in Distributed and Communication Limited Systems. Learning with Options that Terminate Off-Policy. A decentralized route to the …

Generative diffeomorphic atlas construction from brain and spinal cord MRI data


Title	Generative diffeomorphic atlas construction from brain and spinal cord MRI data
Authors	Claudia Blaiotta, Patrick Freund, M. Jorge Cardoso, John Ashburner
Abstract	In this paper we will focus on the potential and on the challenges associated with the development of an integrated brain and spinal cord modelling framework for processing MR neuroimaging data. The aim of the work is to explore how a hierarchical generative model of imaging data, which captures simultaneously the distribution of signal intensities and the variability of anatomical shapes across a large population of subjects, can serve to quantitatively investigate, in vivo, the morphology of the central nervous system (CNS). In fact, the generality of the proposed Bayesian approach, which extends the hierarchical structure of the segmentation method implemented in the SPM software, allows processing simultaneously information relative to different compartments of the CNS, namely the brain and the spinal cord, without having to resort to organ specific solutions (e.g. tools optimised only for the brain, or only for the spinal cord), which are inevitably harder to integrate and generalise.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01342v1
PDF	http://arxiv.org/pdf/1707.01342v1.pdf
PWC	https://paperswithcode.com/paper/generative-diffeomorphic-atlas-construction
Repo
Framework

On the idea of a new artificial intelligence based optimization algorithm inspired from the nature of vortex


Title	On the idea of a new artificial intelligence based optimization algorithm inspired from the nature of vortex
Authors	Utku Kose, Ahmet Arslan
Abstract	In this paper, the idea of a new artificial intelligence based optimization algorithm, which is inspired from the nature of vortex, has been provided briefly. As also a bio-inspired computation algorithm, the idea is generally focused on a typical vortex flow / behavior in nature and inspires from some dynamics that are occurred in the sense of vortex nature. Briefly, the algorithm is also a swarm-oriented evolutional problem solution approach; because it includes many methods related to elimination of weak swarm members and trying to improve the solution process by supporting the solution space via new swarm members. In order have better idea about success of the algorithm; it has been tested via some benchmark functions. At this point, the obtained results show that the algorithm can be an alternative to the literature in terms of single-objective optimization solution ways. Vortex Optimization Algorithm (VOA) is the name suggestion by the authors; for this new idea of intelligent optimization approach.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00797v1
PDF	http://arxiv.org/pdf/1704.00797v1.pdf
PWC	https://paperswithcode.com/paper/on-the-idea-of-a-new-artificial-intelligence
Repo
Framework

Learning of Gaussian Processes in Distributed and Communication Limited Systems


Title	Learning of Gaussian Processes in Distributed and Communication Limited Systems
Authors	Mostafa Tavassolipour, Seyed Abolfazl Motahari, Mohammad-Taghi Manzuri Shalmani
Abstract	It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of Gaussian Processes (GPs) in distributed systems as a pivotal example. We first address a very basic problem: how many bits are required to estimate the inner-products of Gaussian vectors across distributed machines? Using information theoretic bounds, we obtain an optimal solution for the problem which is based on vector quantization. Two suboptimal and more practical schemes are also presented as substitute for the vector quantization scheme. In particular, it is shown that the performance of one of the practical schemes which is called per-symbol quantization is very close to the optimal one. Schemes provided for the inner-product calculations are incorporated into our proposed distributed learning methods for GPs. Experimental results show that with spending few bits per symbol in our communication scheme, our proposed methods outperform previous zero rate distributed GP learning schemes such as Bayesian Committee Model (BCM) and Product of experts (PoE).
Tasks	Gaussian Processes, Quantization
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02627v1
PDF	http://arxiv.org/pdf/1705.02627v1.pdf
PWC	https://paperswithcode.com/paper/learning-of-gaussian-processes-in-distributed
Repo
Framework

Learning with Options that Terminate Off-Policy


Title	Learning with Options that Terminate Off-Policy
Authors	Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowe
Abstract	A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the termination condition roughly determines its length. Generally, learning with longer options (like learning with multi-step returns) is known to be more efficient. However, if the option set for the task is not ideal, and cannot express the primitive optimal policy exactly, shorter options offer more flexibility and can yield a better solution. Thus, the termination condition puts learning efficiency at odds with solution quality. We propose to resolve this dilemma by decoupling the behavior and target terminations, just like it is done with policies in off-policy learning. To this end, we give a new algorithm, Q(\beta), that learns the solution with respect to any termination condition, regardless of how the options actually terminate. We derive Q(\beta) by casting learning with options into a common framework with well-studied multi-step off-policy learning. We validate our algorithm empirically, and show that it holds up to its motivating claims.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03817v2
PDF	http://arxiv.org/pdf/1711.03817v2.pdf
PWC	https://paperswithcode.com/paper/learning-with-options-that-terminate-off
Repo
Framework

A decentralized route to the origins of scaling in human language


Title	A decentralized route to the origins of scaling in human language
Authors	Felipe Urbina, Javier Vera
Abstract	The Zipf’s law establishes that if the words of a (large) text are ordered by decreasing frequency, the frequency versus the rank decreases as a power law with exponent close to $-1$. Previous work has stressed that this pattern arises from a conflict of interests of the participants of communication. The challenge here is to define a computational multi-agent language game, mainly based on a parameter that measures the relative participant’s interests. Numerical simulations suggest that at critical values of the parameter a human-like vocabulary, exhibiting scaling properties, seems to appear. The appearance of an intermediate distribution of frequencies at some critical values of the parameter suggests that on a population of artificial agents the emergence of scaling partly arises as a self-organized process only from local interactions between agents.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05762v2
PDF	http://arxiv.org/pdf/1705.05762v2.pdf
PWC	https://paperswithcode.com/paper/agent-based-model-for-the-origins-of-scaling
Repo
Framework

Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation


Title	Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation
Authors	Jindong Jiang, Zhijun Zhang, Yongqian Huang, Lunan Zheng
Abstract	To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF). First, a DFCN architecture which fuses depth information into the early layers and applies dilated convolution for later contextual reasoning is designed. Then, a depth-sensitive fully-connected conditional random field (DCRF) is proposed and combined with the previous DFCN to refine the preliminary result. Comparative experiments show that the proposed DFCN-DCRF has the best performance compared with most state-of-the-art methods.
Tasks	Semantic Segmentation
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07383v4
PDF	http://arxiv.org/pdf/1705.07383v4.pdf
PWC	https://paperswithcode.com/paper/incorporating-depth-into-both-cnn-and-crf-for
Repo
Framework

Mass Displacement Networks


Title	Mass Displacement Networks
Authors	Natalia Neverova, Iasonas Kokkinos
Abstract	Despite the large improvements in performance attained by using deep learning in computer vision, one can often further improve results with some additional post-processing that exploits the geometric nature of the underlying task. This commonly involves displacing the posterior distribution of a CNN in a way that makes it more appropriate for the task at hand, e.g. better aligned with local image features, or more compact. In this work we integrate this geometric post-processing within a deep architecture, introducing a differentiable and probabilistically sound counterpart to the common geometric voting technique used for evidence accumulation in vision. We refer to the resulting neural models as Mass Displacement Networks (MDNs), and apply them to human pose estimation in two distinct setups: (a) landmark localization, where we collapse a distribution to a point, allowing for precise localization of body keypoints and (b) communication across body parts, where we transfer evidence from one part to the other, allowing for a globally consistent pose estimate. We evaluate on large-scale pose estimation benchmarks, such as MPII Human Pose and COCO datasets, and report systematic improvements when compared to strong baselines.
Tasks	Pose Estimation
Published	2017-08-12
URL	http://arxiv.org/abs/1708.03816v1
PDF	http://arxiv.org/pdf/1708.03816v1.pdf
PWC	https://paperswithcode.com/paper/mass-displacement-networks
Repo
Framework

A learning-based approach for automatic image and video colorization


Title	A learning-based approach for automatic image and video colorization
Authors	Raj Kumar Gupta, Alex Yong-Sang Chia, Deepu Rajan, Huang Zhiyong
Abstract	In this paper, we present a color transfer algorithm to colorize a broad range of gray images without any user intervention. The algorithm uses a machine learning-based approach to automatically colorize grayscale images. The algorithm uses the superpixel representation of the reference color images to learn the relationship between different image features and their corresponding color values. We use this learned information to predict the color value of each grayscale image superpixel. As compared to processing individual image pixels, our use of superpixels helps us to achieve a much higher degree of spatial consistency as well as speeds up the colorization process. The predicted color values of the gray-scale image superpixels are used to provide a ‘micro-scribble’ at the centroid of the superpixels. These color scribbles are refined by using a voting based approach. To generate the final colorization result, we use an optimization-based approach to smoothly spread the color scribble across all pixels within a superpixel. Experimental results on a broad range of images and the comparison with existing state-of-the-art colorization methods demonstrate the greater effectiveness of the proposed algorithm.
Tasks	Colorization
Published	2017-04-15
URL	http://arxiv.org/abs/1704.04610v1
PDF	http://arxiv.org/pdf/1704.04610v1.pdf
PWC	https://paperswithcode.com/paper/a-learning-based-approach-for-automatic-image
Repo
Framework

(DE)^2 CO: Deep Depth Colorization


Title	(DE)^2 CO: Deep Depth Colorization
Authors	F. M. Carlucci, P. Russo, B. Caputo
Abstract	The ability to classify objects is fundamental for robots. Besides knowledge about their visual appearance, captured by the RGB channel, robots heavily need also depth information to make sense of the world. While the use of deep networks on RGB robot images has benefited from the plethora of results obtained on databases like ImageNet, using convnets on depth images requires mapping them into three dimensional channels. This transfer learning procedure makes them processable by pre-trained deep architectures. Current mappings are based on heuristic assumptions over preprocessing steps and on what depth properties should be most preserved, resulting often in cumbersome data visualizations, and in sub-optimal performance in terms of generality and recognition results. Here we take an alternative route and we attempt instead to learn an optimal colorization mapping for any given pre-trained architecture, using as training data a reference RGB-D database. We propose a deep network architecture, exploiting the residual paradigm, that learns how to map depth data to three channel images. A qualitative analysis of the images obtained with this approach clearly indicates that learning the optimal mapping preserves the richness of depth information better than current hand-crafted approaches. Experiments on the Washington, JHUIT-50 and BigBIRD public benchmark databases, using CaffeNet, VGG16, GoogleNet, and ResNet50 clearly showcase the power of our approach, with gains in performance of up to 16% compared to state of the art competitors on the depth channel only, leading to top performances when dealing with RGB-D data
Tasks	Colorization, Transfer Learning
Published	2017-03-31
URL	http://arxiv.org/abs/1703.10881v3
PDF	http://arxiv.org/pdf/1703.10881v3.pdf
PWC	https://paperswithcode.com/paper/de2-co-deep-depth-colorization
Repo
Framework

ZM-Net: Real-time Zero-shot Image Manipulation Network


Title	ZM-Net: Real-time Zero-shot Image Manipulation Network
Authors	Hao Wang, Xiaodan Liang, Hao Zhang, Dit-Yan Yeung, Eric P. Xing
Abstract	Many problems in image processing and computer vision (e.g. colorization, style transfer) can be posed as ‘manipulating’ an input image into a corresponding output image given a user-specified guiding signal. A holy-grail solution towards generic image manipulation should be able to efficiently alter an input image with any personalized signals (even signals unseen during training), such as diverse paintings and arbitrary descriptive attributes. However, existing methods are either inefficient to simultaneously process multiple signals (let alone generalize to unseen signals), or unable to handle signals from other modalities. In this paper, we make the first attempt to address the zero-shot image manipulation task. We cast this problem as manipulating an input image according to a parametric model whose key parameters can be conditionally generated from any guiding signal (even unseen ones). To this end, we propose the Zero-shot Manipulation Net (ZM-Net), a fully-differentiable architecture that jointly optimizes an image-transformation network (TNet) and a parameter network (PNet). The PNet learns to generate key transformation parameters for the TNet given any guiding signal while the TNet performs fast zero-shot image manipulation according to both signal-dependent parameters from the PNet and signal-invariant parameters from the TNet itself. Extensive experiments show that our ZM-Net can perform high-quality image manipulation conditioned on different forms of guiding signals (e.g. style images and attributes) in real-time (tens of milliseconds per image) even for unseen signals. Moreover, a large-scale style dataset with over 20,000 style images is also constructed to promote further research.
Tasks	Colorization, Style Transfer
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07255v2
PDF	http://arxiv.org/pdf/1703.07255v2.pdf
PWC	https://paperswithcode.com/paper/zm-net-real-time-zero-shot-image-manipulation
Repo
Framework

Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications


Title	Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications
Authors	Rui Zhuang, Johannes Lederer
Abstract	Maximum regularized likelihood estimators (MRLEs) are arguably the most established class of estimators in high-dimensional statistics. In this paper, we derive guarantees for MRLEs in Kullback-Leibler divergence, a general measure of prediction accuracy. We assume only that the densities have a convex parametrization and that the regularization is definite and positive homogenous. The results thus apply to a very large variety of models and estimators, such as tensor regression and graphical models with convex and non-convex regularized methods. A main conclusion is that MRLEs are broadly consistent in prediction - regardless of whether restricted eigenvalues or similar conditions hold.
Tasks
Published	2017-10-09
URL	http://arxiv.org/abs/1710.02950v2
PDF	http://arxiv.org/pdf/1710.02950v2.pdf
PWC	https://paperswithcode.com/paper/maximum-regularized-likelihood-estimators-a
Repo
Framework

Ultra-low-power Wireless Streaming Cameras


Title	Ultra-low-power Wireless Streaming Cameras
Authors	Saman Naderiparizi, Mehrdad Hessar, Vamsi Talla, Shyamnath Gollakota, Joshua R. Smith
Abstract	Wireless video streaming has traditionally been considered an extremely power-hungry operation. Existing approaches optimize the camera and communication modules individually to minimize their power consumption. However, the joint redesign and optimization of wireless communication as well as the camera is what that provides more power saving. We present an ultra-low-power wireless video streaming camera. To achieve this, we present a novel “analog” video backscatter technique that feeds analog pixels from the photo-diodes directly to the backscatter hardware, thereby eliminating power consuming hardware components such as ADCs and amplifiers. We prototype our wireless camera using off-the-shelf hardware and show that our design can stream video at up to 13 FPS and can operate up to a distance of 150 feet from the access point. Our COTS prototype consumes 2.36mW. Finally, to demonstrate the potential of our design, we built two proof-of-concept applications: video streaming for micro-robots and security cameras for face detection.
Tasks	Face Detection
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08718v1
PDF	http://arxiv.org/pdf/1707.08718v1.pdf
PWC	https://paperswithcode.com/paper/ultra-low-power-wireless-streaming-cameras
Repo
Framework

Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification


Title	Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification
Authors	Jean Feng, Noah Simon
Abstract	Neural networks are usually not the tool of choice for nonparametric high-dimensional problems where the number of input features is much larger than the number of observations. Though neural networks can approximate complex multivariate functions, they generally require a large number of training observations to obtain reasonable fits, unless one can learn the appropriate network structure. In this manuscript, we show that neural networks can be applied successfully to high-dimensional settings if the true function falls in a low dimensional subspace, and proper regularization is used. We propose fitting a neural network with a sparse group lasso penalty on the first-layer input weights. This results in a neural net that only uses a small subset of the original features. In addition, we characterize the statistical convergence of the penalized empirical risk minimizer to the optimal neural network: we show that the excess risk of this penalized estimator only grows with the logarithm of the number of input features; and we show that the weights of irrelevant features converge to zero. Via simulation studies and data analyses, we show that these sparse-input neural networks outperform existing nonparametric high-dimensional estimation methods when the data has complex higher-order interactions.
Tasks
Published	2017-11-21
URL	https://arxiv.org/abs/1711.07592v2
PDF	https://arxiv.org/pdf/1711.07592v2.pdf
PWC	https://paperswithcode.com/paper/sparse-input-neural-networks-for-high
Repo
Framework

Strategyproof Mechanisms for Additively Separable Hedonic Games and Fractional Hedonic Games


Title	Strategyproof Mechanisms for Additively Separable Hedonic Games and Fractional Hedonic Games
Authors	Michele Flammini, Gianpiero Monaco, Qiang Zhang
Abstract	Additively separable hedonic games and fractional hedonic games have received considerable attention. They are coalition forming games of selfish agents based on their mutual preferences. Most of the work in the literature characterizes the existence and structure of stable outcomes (i.e., partitions in coalitions), assuming that preferences are given. However, there is little discussion on this assumption. In fact, agents receive different utilities if they belong to different partitions, and thus it is natural for them to declare their preferences strategically in order to maximize their benefit. In this paper we consider strategyproof mechanisms for additively separable hedonic games and fractional hedonic games, that is, partitioning methods without payments such that utility maximizing agents have no incentive to lie about their true preferences. We focus on social welfare maximization and provide several lower and upper bounds on the performance achievable by strategyproof mechanisms for general and specific additive functions. In most of the cases we provide tight or asymptotically tight results. All our mechanisms are simple and can be computed in polynomial time. Moreover, all the lower bounds are unconditional, that is, they do not rely on any computational or complexity assumptions.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1706.09007v1
PDF	http://arxiv.org/pdf/1706.09007v1.pdf
PWC	https://paperswithcode.com/paper/strategyproof-mechanisms-for-additively
Repo
Framework

WOAH: Preliminaries to Zero-shot Ontology Learning for Conversational Agents


Title	WOAH: Preliminaries to Zero-shot Ontology Learning for Conversational Agents
Authors	Gonzalo Estrán Buyo
Abstract	The present paper presents the Weighted Ontology Approximation Heuristic (WOAH), a novel zero-shot approach to ontology estimation for conversational agents development environments. This methodology extracts verbs and nouns separately from data by distilling the dependencies obtained and applying similarity and sparsity metrics to generate an ontology estimation configurable in terms of the level of generalization.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05014v2
PDF	http://arxiv.org/pdf/1709.05014v2.pdf
PWC	https://paperswithcode.com/paper/woah-preliminaries-to-zero-shot-ontology
Repo
Framework