July 27, 2019

3322 words 16 mins read

Paper Group ANR 471

Y-net: 3D intracranial artery segmentation using a convolutional autoencoder. Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries. UAV and Service Robot Coordination for Indoor Object Search Tasks. Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resoluti …

Y-net: 3D intracranial artery segmentation using a convolutional autoencoder


Title	Y-net: 3D intracranial artery segmentation using a convolutional autoencoder
Authors	Li Chen, Yanjun Xie, Jie Sun, Niranjan Balu, Mahmud Mossa-Basha, Kristi Pimentel, Thomas S. Hatsukami, Jenq-Neng Hwang, Chun Yuan
Abstract	Automated segmentation of intracranial arteries on magnetic resonance angiography (MRA) allows for quantification of cerebrovascular features, which provides tools for understanding aging and pathophysiological adaptations of the cerebrovascular system. Using a convolutional autoencoder (CAE) for segmentation is promising as it takes advantage of the autoencoder structure in effective noise reduction and feature extraction by representing high dimensional information with low dimensional latent variables. In this report, an optimized CAE model (Y-net) was trained to learn a 3D segmentation model of intracranial arteries from 49 cases of MRA data. The trained model was shown to perform better than the three traditional segmentation methods in both binary classification and visual evaluation.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07194v1
PDF	http://arxiv.org/pdf/1712.07194v1.pdf
PWC	https://paperswithcode.com/paper/y-net-3d-intracranial-artery-segmentation
Repo
Framework

Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries


Title	Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries
Authors	Rui Zhang, Quanyan Zhu
Abstract	With a large number of sensors and control units in networked systems, distributed support vector machines (DSVMs) play a fundamental role in scalable and efficient multi-sensor classification and prediction tasks. However, DSVMs are vulnerable to adversaries who can modify and generate data to deceive the system to misclassification and misprediction. This work aims to design defense strategies for DSVM learner against a potential adversary. We establish a game-theoretic framework to capture the conflicting interests between the DSVM learner and the attacker. The Nash equilibrium of the game allows predicting the outcome of learning algorithms in adversarial environments, and enhancing the resilience of the machine learning through dynamic distributed learning algorithms. We show that the DSVM learner is less vulnerable when he uses a balanced network with fewer nodes and higher degree. We also show that adding more training samples is an efficient defense strategy against an attacker. We present secure and resilient DSVM algorithms with verification method and rejection method, and show their resiliency against adversary with numerical experiments.
Tasks
Published	2017-10-12
URL	http://arxiv.org/abs/1710.04677v1
PDF	http://arxiv.org/pdf/1710.04677v1.pdf
PWC	https://paperswithcode.com/paper/game-theoretic-design-of-secure-and-resilient
Repo
Framework

UAV and Service Robot Coordination for Indoor Object Search Tasks


Title	UAV and Service Robot Coordination for Indoor Object Search Tasks
Authors	Sandeep Konam, Stephanie Rosenthal, Manuela Veloso
Abstract	Our CoBot robots have successfully performed a variety of service tasks in our multi-building environment including accompanying people to meetings and delivering objects to offices due to its navigation and localization capabilities. However, they lack the capability to visually search over desks and other confined locations for an object of interest. Conversely, an inexpensive GPS-denied quadcopter platform such as the Parrot ARDrone 2.0 could perform this object search task if it had access to reasonable localization. In this paper, we propose the concept of coordination between CoBot and the Parrot ARDrone 2.0 to perform service-based object search tasks, in which CoBot localizes and navigates to the general search areas carrying the ARDrone and the ARDrone searches locally for objects. We propose a vision-based moving target navigation algorithm that enables the ARDrone to localize with respect to CoBot, search for objects, and return to the CoBot for future searches. We demonstrate our algorithm in indoor environments on several search trajectories.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08831v1
PDF	http://arxiv.org/pdf/1709.08831v1.pdf
PWC	https://paperswithcode.com/paper/uav-and-service-robot-coordination-for-indoor
Repo
Framework

Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations


Title	Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations
Authors	Tapio Schneider, Shiwei Lan, Andrew Stuart, João Teixeira
Abstract	Climate projections continue to be marred by large uncertainties, which originate in processes that need to be parameterized, such as clouds, convection, and ecosystems. But rapid progress is now within reach. New computational tools and methods from data assimilation and machine learning make it possible to integrate global observations and local high-resolution simulations in an Earth system model (ESM) that systematically learns from both. Here we propose a blueprint for such an ESM. We outline how parameterization schemes can learn from global observations and targeted high-resolution simulations, for example, of clouds and convection, through matching low-order statistics between ESMs, observations, and high-resolution simulations. We illustrate learning algorithms for ESMs with a simple dynamical system that shares characteristics of the climate system; and we discuss the opportunities the proposed framework presents and the challenges that remain to realize it.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1709.00037v3
PDF	http://arxiv.org/pdf/1709.00037v3.pdf
PWC	https://paperswithcode.com/paper/earth-system-modeling-20-a-blueprint-for
Repo
Framework

Multi-Objective Maximization of Monotone Submodular Functions with Cardinality Constraint


Title	Multi-Objective Maximization of Monotone Submodular Functions with Cardinality Constraint
Authors	Rajan Udwani
Abstract	We consider the problem of multi-objective maximization of monotone submodular functions subject to cardinality constraint, often formulated as $\max_{A=k}\min_{i\in{1,\dots,m}}f_i(A)$. While it is widely known that greedy methods work well for a single objective, the problem becomes much harder with multiple objectives. In fact, Krause et al.\ (2008) showed that when the number of objectives $m$ grows as the cardinality $k$ i.e., $m=\Omega(k)$, the problem is inapproximable (unless $P=NP$). On the other hand, when $m$ is constant Chekuri et al.\ (2010) showed a randomized $(1-1/e)-\epsilon$ approximation with runtime (number of queries to function oracle) $n^{m/\epsilon^3}$. %In fact, the result of Chekuri et al.\ (2010) is for the far more general case of matroid constant. We focus on finding a fast and practical algorithm that has (asymptotic) approximation guarantees even when $m$ is super constant. We first modify the algorithm of Chekuri et al.\ (2010) to achieve a $(1-1/e)$ approximation for $m=o(\frac{k}{\log^3 k})$. This demonstrates a steep transition from constant factor approximability to inapproximability around $m=\Omega(k)$. Then using Multiplicative-Weight-Updates (MWU), we find a much faster $\tilde{O}(n/\delta^3)$ time asymptotic $(1-1/e)^2-\delta$ approximation. While the above results are all randomized, we also give a simple deterministic $(1-1/e)-\epsilon$ approximation with runtime $kn^{m/\epsilon^4}$. Finally, we run synthetic experiments using Kronecker graphs and find that our MWU inspired heuristic outperforms existing heuristics.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06428v2
PDF	http://arxiv.org/pdf/1711.06428v2.pdf
PWC	https://paperswithcode.com/paper/multi-objective-maximization-of-monotone
Repo
Framework

Deep Reinforcement Learning Boosted by External Knowledge


Title	Deep Reinforcement Learning Boosted by External Knowledge
Authors	Nicolas Bougie, Ryutaro Ichise
Abstract	Recent improvements in deep reinforcement learning have allowed to solve problems in many 2D domains such as Atari games. However, in complex 3D environments, numerous learning episodes are required which may be too time consuming or even impossible especially in real-world scenarios. We present a new architecture to combine external knowledge and deep reinforcement learning using only visual input. A key concept of our system is augmenting image input by adding environment feature information and combining two sources of decision. We evaluate the performances of our method in a 3D partially-observable environment from the Microsoft Malmo platform. Experimental evaluation exhibits higher performance and faster learning compared to a single reinforcement learning model.
Tasks	Atari Games
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04101v1
PDF	http://arxiv.org/pdf/1712.04101v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-boosted-by
Repo
Framework

Exact Learning of Juntas from Membership Queries


Title	Exact Learning of Juntas from Membership Queries
Authors	Nader H. Bshouty, Areej Costa
Abstract	In this paper, we study adaptive and non-adaptive exact learning of Juntas from membership queries. We use new techniques to find new bounds, narrow some of the gaps between the lower bounds and upper bounds and find new deterministic and randomized algorithms with small query and time complexities. Some of the bounds are tight in the sense that finding better ones either gives a breakthrough result in some long-standing combinatorial open problem or needs a new technique that is beyond the existing ones.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06934v1
PDF	http://arxiv.org/pdf/1706.06934v1.pdf
PWC	https://paperswithcode.com/paper/exact-learning-of-juntas-from-membership
Repo
Framework

Supervised Q-walk for Learning Vector Representation of Nodes in Networks


Title	Supervised Q-walk for Learning Vector Representation of Nodes in Networks
Authors	Naimish Agarwal, G. C. Nandi
Abstract	Automatic feature learning algorithms are at the forefront of modern day machine learning research. We present a novel algorithm, supervised Q-walk, which applies Q-learning to generate random walks on graphs such that the walks prove to be useful for learning node features suitable for tackling with the node classification problem. We present another novel algorithm, k-hops neighborhood based confidence values learner, which learns confidence values of labels for unlabelled nodes in the network without first learning the node embedding. These confidence values aid in learning an apt reward function for Q-learning. We demonstrate the efficacy of supervised Q-walk approach over existing state-of-the-art random walk based node embedding learners in solving the single / multi-label multi-class node classification problem using several real world datasets. Summarising, our approach represents a novel state-of-the-art technique to learn features, for nodes in networks, tailor-made for dealing with the node classification problem.
Tasks	Node Classification, Q-Learning
Published	2017-10-03
URL	http://arxiv.org/abs/1710.00978v1
PDF	http://arxiv.org/pdf/1710.00978v1.pdf
PWC	https://paperswithcode.com/paper/supervised-q-walk-for-learning-vector
Repo
Framework

On Hashing-Based Approaches to Approximate DNF-Counting


Title	On Hashing-Based Approaches to Approximate DNF-Counting
Authors	Kuldeep S. Meel, Aditya A. Shrotri, Moshe Y. Vardi
Abstract	Propositional model counting is a fundamental problem in artificial intelligence with a wide variety of applications, such as probabilistic inference, decision making under uncertainty, and probabilistic databases. Consequently, the problem is of theoretical as well as practical interest. When the constraints are expressed as DNF formulas, Monte Carlo-based techniques have been shown to provide a fully polynomial randomized approximation scheme (FPRAS). For CNF constraints, hashing-based approximation techniques have been demonstrated to be highly successful. Furthermore, it was shown that hashing-based techniques also yield an FPRAS for DNF counting without usage of Monte Carlo sampling. Our analysis, however, shows that the proposed hashing-based approach to DNF counting provides poor time complexity compared to the Monte Carlo-based DNF counting techniques. Given the success of hashing-based techniques for CNF constraints, it is natural to ask: Can hashing-based techniques provide an efficient FPRAS for DNF counting? In this paper, we provide a positive answer to this question. To this end, we introduce two novel algorithmic techniques: \emph{Symbolic Hashing} and \emph{Stochastic Cell Counting}, along with a new hash family of \emph{Row-Echelon hash functions}. These innovations allow us to design a hashing-based FPRAS for DNF counting of similar complexity (up to polylog factors) as that of prior works. Furthermore, we expect these techniques to have potential applications beyond DNF counting.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05247v1
PDF	http://arxiv.org/pdf/1710.05247v1.pdf
PWC	https://paperswithcode.com/paper/on-hashing-based-approaches-to-approximate
Repo
Framework

Joint Person Re-identification and Camera Network Topology Inference in Multiple Cameras


Title	Joint Person Re-identification and Camera Network Topology Inference in Multiple Cameras
Authors	Yeong-Jun Cho, Su-A Kim, Jae-Han Park, Kyuewang Lee, Kuk-Jin Yoon
Abstract	Person re-identification is the task of recognizing or identifying a person across multiple views in multi-camera networks. Although there has been much progress in person re-identification, person re-identification in large-scale multi-camera networks still remains a challenging task because of the large spatio-temporal uncertainty and high complexity due to a large number of cameras and people. To handle these difficulties, additional information such as camera network topology should be provided, which is also difficult to automatically estimate, unfortunately. In this study, we propose a unified framework which jointly solves both person re-identification and camera network topology inference problems with minimal prior knowledge about the environments. The proposed framework takes general multi-camera network environments into account and can be applied to online person re-identification in large-scale multi-camera networks. In addition, to effectively show the superiority of the proposed framework, we provide a new person re-identification dataset with full annotations, named SLP, captured in the multi-camera network consisting of nine non-overlapping cameras. Experimental results using our person re-identification and public datasets show that the proposed methods are promising for both person re-identification and camera topology inference tasks.
Tasks	Person Re-Identification
Published	2017-10-03
URL	http://arxiv.org/abs/1710.00983v1
PDF	http://arxiv.org/pdf/1710.00983v1.pdf
PWC	https://paperswithcode.com/paper/joint-person-re-identification-and-camera
Repo
Framework

Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions


Title	Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions
Authors	Miao Liu, Kavinayan Sivakumar, Shayegan Omidshafiei, Christopher Amato, Jonathan P. How
Abstract	This paper presents a data-driven approach for multi-robot coordination in partially-observable domains based on Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) and macro-actions (MAs). Dec-POMDPs provide a general framework for cooperative sequential decision making under uncertainty and MAs allow temporally extended and asynchronous action execution. To date, most methods assume the underlying Dec-POMDP model is known a priori or a full simulator is available during planning time. Previous methods which aim to address these issues suffer from local optimality and sensitivity to initial conditions. Additionally, few hardware demonstrations involving a large team of heterogeneous robots and with long planning horizons exist. This work addresses these gaps by proposing an iterative sampling based Expectation-Maximization algorithm (iSEM) to learn polices using only trajectory data containing observations, MAs, and rewards. Our experiments show the algorithm is able to achieve better solution quality than the state-of-the-art learning-based methods. We implement two variants of multi-robot Search and Rescue (SAR) domains (with and without obstacles) on hardware to demonstrate the learned policies can effectively control a team of distributed robots to cooperate in a partially observable stochastic environment.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07399v2
PDF	http://arxiv.org/pdf/1707.07399v2.pdf
PWC	https://paperswithcode.com/paper/learning-for-multi-robot-cooperation-in
Repo
Framework

Structured signal recovery from quadratic measurements: Breaking sample complexity barriers via nonconvex optimization


Title	Structured signal recovery from quadratic measurements: Breaking sample complexity barriers via nonconvex optimization
Authors	Mahdi Soltanolkotabi
Abstract	This paper concerns the problem of recovering an unknown but structured signal $x \in R^n$ from $m$ quadratic measurements of the form $y_r=<a_r,x>^2$ for $r=1,2,…,m$. We focus on the under-determined setting where the number of measurements is significantly smaller than the dimension of the signal ($m«n$). We formulate the recovery problem as a nonconvex optimization problem where prior structural information about the signal is enforced through constrains on the optimization variables. We prove that projected gradient descent, when initialized in a neighborhood of the desired signal, converges to the unknown signal at a linear rate. These results hold for any constraint set (convex or nonconvex) providing convergence guarantees to the global optimum even when the objective function and constraint set is nonconvex. Furthermore, these results hold with a number of measurements that is only a constant factor away from the minimal number of measurements required to uniquely identify the unknown signal. Our results provide the first provably tractable algorithm for this data-poor regime, breaking local sample complexity barriers that have emerged in recent literature. In a companion paper we demonstrate favorable properties for the optimization problem that may enable similar results to continue to hold more globally (over the entire ambient space). Collectively these two papers utilize and develop powerful tools for uniform convergence of empirical processes that may have broader implications for rigorous understanding of constrained nonconvex optimization heuristics. The mathematical results in this paper also pave the way for a new generation of data-driven phase-less imaging systems that can utilize prior information to significantly reduce acquisition time and enhance image reconstruction, enabling nano-scale imaging at unprecedented speeds and resolutions.
Tasks	Image Reconstruction
Published	2017-02-20
URL	http://arxiv.org/abs/1702.06175v1
PDF	http://arxiv.org/pdf/1702.06175v1.pdf
PWC	https://paperswithcode.com/paper/structured-signal-recovery-from-quadratic
Repo
Framework

CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices


Title	CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
Authors	Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yipeng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan
Abstract	Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the lack of rigorous guarantee of compression ratio and inference accuracy. To overcome these limitations, this paper proposes CirCNN, a principled approach to represent weights and process neural networks using block-circulant matrices. CirCNN utilizes the Fast Fourier Transform (FFT)-based fast multiplication, simultaneously reducing the computational complexity (both in inference and training) from O(n2) to O(nlogn) and the storage complexity from O(n2) to O(n), with negligible accuracy loss. Compared to other approaches, CirCNN is distinct due to its mathematical rigor: it can converge to the same effectiveness as DNNs without compression. The CirCNN architecture, a universal DNN inference engine that can be implemented on various hardware/software platforms with configurable network architecture. To demonstrate the performance and energy efficiency, we test CirCNN in FPGA, ASIC and embedded processors. Our results show that CirCNN architecture achieves very high energy efficiency and performance with a small hardware footprint. Based on the FPGA implementation and ASIC synthesis results, CirCNN achieves 6-102X energy efficiency improvements compared with the best state-of-the-art results.
Tasks
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08917v1
PDF	http://arxiv.org/pdf/1708.08917v1.pdf
PWC	https://paperswithcode.com/paper/circnn-accelerating-and-compressing-deep
Repo
Framework

Group Sparsity Residual Constraint for Image Denoising


Title	Group Sparsity Residual Constraint for Image Denoising
Authors	Zhiyuan Zha, Xinggan Zhang, Qiong Wang, Lan Tang, Xin Liu
Abstract	Group-based sparse representation has shown great potential in image denoising. However, most existing methods only consider the nonlocal self-similarity (NSS) prior of noisy input image. That is, the similar patches are collected only from degraded input, which makes the quality of image denoising largely depend on the input itself. However, such methods often suffer from a common drawback that the denoising performance may degrade quickly with increasing noise levels. In this paper we propose a new prior model, called group sparsity residual constraint (GSRC). Unlike the conventional group-based sparse representation denoising methods, two kinds of prior, namely, the NSS priors of noisy and pre-filtered images, are used in GSRC. In particular, we integrate these two NSS priors through the mechanism of sparsity residual, and thus, the task of image denoising is converted to the problem of reducing the group sparsity residual. To this end, we first obtain a good estimation of the group sparse coefficients of the original image by pre-filtering, and then the group sparse coefficients of the noisy image are used to approximate this estimation. To improve the accuracy of the nonlocal similar patch selection, an adaptive patch search scheme is designed. Furthermore, to fuse these two NSS prior better, an effective iterative shrinkage algorithm is developed to solve the proposed GSRC model. Experimental results demonstrate that the proposed GSRC modeling outperforms many state-of-the-art denoising methods in terms of the objective and the perceptual metrics.
Tasks	Denoising, Image Denoising
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00297v6
PDF	http://arxiv.org/pdf/1703.00297v6.pdf
PWC	https://paperswithcode.com/paper/group-sparsity-residual-constraint-for-image
Repo
Framework

Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions


Title	Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions
Authors	Benjamin Busam, Tolga Birdal, Nassir Navab
Abstract	Time-varying, smooth trajectory estimation is of great interest to the vision community for accurate and well behaving 3D systems. In this paper, we propose a novel principal component local regression filter acting directly on the Riemannian manifold of unit dual quaternions $\mathbb{D} \mathbb{H}_1$. We use a numerically stable Lie algebra of the dual quaternions together with $\exp$ and $\log$ operators to locally linearize the 6D pose space. Unlike state of the art path smoothing methods which either operate on $SO\left(3\right)$ of rotation matrices or the hypersphere $\mathbb{H}_1$ of quaternions, we treat the orientation and translation jointly on the dual quaternion quadric in the 7-dimensional real projective space $\mathbb{R}\mathbb{P}^7$. We provide an outlier-robust IRLS algorithm for generic pose filtering exploiting this manifold structure. Besides our theoretical analysis, our experiments on synthetic and real data show the practical advantages of the manifold aware filtering on pose tracking and smoothing.
Tasks	Pose Tracking
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07072v4
PDF	http://arxiv.org/pdf/1704.07072v4.pdf
PWC	https://paperswithcode.com/paper/camera-pose-filtering-with-local-regression
Repo
Framework