arXiv subjects

Ke Sun

Publications and source records attributed to Ke Sun.

176 records · Page 10Linked to original sources

arXiv2017

Fast, Autonomous Flight in GPS-Denied and Cluttered Environments

One of the most challenging tasks for a flying robot is to autonomously navigate between target locations quickly and reliably while avoiding obstacles in its path, and with little to no a-priori knowledge of the operating environment. This challenge is addressed in the present paper. We describe the system design and software architecture of our proposed solution, and showcase how all the distinct components can be integrated to enable smooth robot operation. We provide critical insight on hardware and software component selection and development, and present results from extensive experimental testing in real-world warehouse environments. Experimental testing reveals that our proposed solution can deliver fast and robust aerial robot autonomous navigation in cluttered, GPS-denied environments.

cs.RO↗

arXiv2017

Human Pose Estimation using Global and Local Normalization

In this paper, we address the problem of estimating the positions of human joints, i.e., articulated pose estimation. Recent state-of-the-art solutions model two key issues, joint detection and spatial configuration refinement, together using convolutional neural networks. Our work mainly focuses on spatial configuration refinement by reducing variations of human poses statistically, which is motivated by the observation that the scattered distribution of the relative locations of joints e.g., the left wrist is distributed nearly uniformly in a circular area around the left shoulder) makes the learning of convolutional spatial models hard. We present a two-stage normalization scheme, human body normalization and limb normalization, to make the distribution of the relative joint locations compact, resulting in easier learning of convolutional spatial models and more accurate pose estimation. In addition, our empirical results show that incorporating multi-scale supervision and multi-scale fusion into the joint detection network is beneficial. Experiment results demonstrate that our method consistently outperforms state-of-the-art methods on the benchmarks.

cs.CV↗

arXiv2017

Information-Theoretic Attacks in the Smart Grid

Gaussian random attacks that jointly minimize the amount of information obtained by the operator from the grid and the probability of attack detection are presented. The construction of the attack is posed as an optimization problem with a utility function that captures two effects: firstly, minimizing the mutual information between the measurements and the state variables; secondly, minimizing the probability of attack detection via the Kullback-Leibler divergence between the distribution of the measurements with an attack and the distribution of the measurements without an attack. Additionally, a lower bound on the utility function achieved by the attacks constructed with imperfect knowledge of the second order statistics of the state variables is obtained. The performance of the attack construction using the sample covariance matrix of the state variables is numerically evaluated. The above results are tested in the IEEE 30-Bus test system.

cs.IT↗

arXiv2017

Coarse Grained Exponential Variational Autoencoders

Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process. This puts a limit on variational learning because this simplified assumption does not match the true posterior distribution, which is usually much more sophisticated. To break this limitation and apply arbitrary parametric distribution during inference, this paper derives a \emph{semi-continuous} latent representation, which approximates a continuous density up to a prescribed precision, and is much easier to analyze than its continuous counterpart because it is fundamentally discrete. We showcase the proposition by applying polynomial exponential family distributions as the posterior, which are universal probability density function generators. Our experimental results show consistent improvements over commonly used VAE models.

cs.LG↗

arXiv2017

On Hölder projective divergences

We describe a framework to build distances by measuring the tightness of inequalities, and introduce the notion of proper statistical divergences and improper pseudo-divergences. We then consider the Hölder ordinary and reverse inequalities, and present two novel classes of Hölder divergences and pseudo-divergences that both encapsulate the special case of the Cauchy-Schwarz divergence. We report closed-form formulas for those statistical dissimilarities when considering distributions belonging to the same exponential family provided that the natural parameter space is a cone (e.g., multivariate Gaussians), or affine (e.g., categorical distributions). Those new classes of Hölder distances are invariant to rescaling, and thus do not require distributions to be normalized. Finally, we show how to compute statistical Hölder centroids with respect to those divergences, and carry out center-based clustering toy experiments on a set of Gaussian distributions that demonstrate empirically that symmetrized Hölder divergences outperform the symmetric Cauchy-Schwarz divergence.

cs.LG↗

arXiv2016

Automatic Visual Theme Discovery from Joint Image and Text Corpora

A popular approach to semantic image understanding is to manually tag images with keywords and then learn a mapping from vi- sual features to keywords. Manually tagging images is a subjective pro- cess and the same or very similar visual contents are often tagged with different keywords. Furthermore, not all tags have the same descriptive power for visual contents and large vocabulary available from natural language could result in a very diverse set of keywords. In this paper, we propose an unsupervised visual theme discovery framework as a better (more compact, efficient and effective) alternative to semantic represen- tation of visual contents. We first show that tag based annotation lacks consistency and compactness for describing visually similar contents. We then learn the visual similarity between tags based on the visual features of the images containing the tags. At the same time, we use a natural language processing technique (word embedding) to measure the seman- tic similarity between tags. Finally, we cluster tags into visual themes based on their visual similarity and semantic similarity measures using a spectral clustering algorithm. We conduct user studies to evaluate the effectiveness and rationality of the visual themes discovered by our unsu- pervised algorithm and obtains promising result. We then design three common computer vision tasks, example based image search, keyword based image search and image labelling to explore potential applica- tion of our visual themes discovery framework. In experiments, visual themes significantly outperforms tags on semantic image understand- ing and achieve state-of-art performance in all three tasks. This again demonstrate the effectiveness and versatility of proposed framework.

cs.CV↗

arXiv2016

Object Specific Deep Learning Feature and Its Application to Face Detection

We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study. Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, we seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce an object specific channel (OSC) and systematically identifying it for the human face object has been developed. Based on the basic OSC features, we introduce a multi-resolution approach to constructing robust face heatmaps for fast face detection in unconstrained settings. We show that multi-resolution OSC can be used to develop state of the art face detectors which have the advantage of being simple and compact.

cs.CV↗

arXiv2016

Guaranteed bounds on the Kullback-Leibler divergence of univariate mixtures using piecewise log-sum-exp inequalities

Information-theoretic measures such as the entropy, cross-entropy and the Kullback-Leibler divergence between two mixture models is a core primitive in many signal processing tasks. Since the Kullback-Leibler divergence of mixtures provably does not admit a closed-form formula, it is in practice either estimated using costly Monte-Carlo stochastic integration, approximated, or bounded using various techniques. We present a fast and generic method that builds algorithmically closed-form lower and upper bounds on the entropy, the cross-entropy and the Kullback-Leibler divergence of mixtures. We illustrate the versatile method by reporting on our experiments for approximating the Kullback-Leibler divergence between univariate exponential mixtures, Gaussian mixtures, Rayleigh mixtures, and Gamma mixtures.

cs.LG↗

arXiv2016

Relative Natural Gradient for Learning Large Complex Models

Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks. However related analysis becomes more and more difficult as the learner's structure turns large and complex. This paper makes a preliminary step towards a new direction. We extract a local component of a large neuron system, and defines its relative Fisher information metric that describes accurately this small component, and is invariant to the other parts of the system. This concept is important because the geometry structure is much simplified and it can be easily applied to guide the learning of neural networks. We provide an analysis on a list of commonly used components, and demonstrate how to use this concept to further improve optimization.

cs.LG↗

arXiv2014

Two-Stage Metric Learning

In this paper, we present a novel two-stage metric learning algorithm. We first map each learning instance to a probability distribution by computing its similarities to a set of fixed anchor points. Then, we define the distance in the input data space as the Fisher information distance on the associated statistical manifold. This induces in the input data space a new family of distance metric with unique properties. Unlike kernelized metric learning, we do not require the similarity measure to be positive semi-definite. Moreover, it can also be interpreted as a local metric learning algorithm with well defined distance approximation. We evaluate its performance on a number of datasets. It outperforms significantly other metric learning methods and SVM.

cs.LG↗

arXiv2012

Full Band Gap and Defects States in Solid-in-Solid Three Dimensional Phononic Crystals

A full band gap of the longitudinal mode of elastic waves centered near 2.8 MHz with a width of ~ 1 MHz has been observed in the phononic crystals made of body centered tetragonal tungsten carbide spheres imbedded in aluminum matrix. Two defects states in the band gap due to a 7-sphere defect cluster with silicon nitride spheres have also been observed. Transmitted pressure field pattern clearly shows that at the defect state frequencies the ultrasonic waves transmitted through the doped crystal are emitted from the defect cluster.

cond-mat.mtrl-sci↗

arXiv2010

Registration-based Compensation using Sparse Representation in Conformal-array STAP

Space-time adaptive processing (STAP) is a well-known technique in detecting slow-moving targets in the presence of a clutter-spreading environment. When considering the STAP system deployed with conformal radar array (CFA), the training data are range-dependent, which results in poor detection performance of traditional statistical-based algorithms. Current registration-based compensation (RBC) is implemented based on a sub-snapshot spectrum using temporal smoothing. In this case, the estimation accuracy of the configuration parameters and the clutter power distribution is limited. In this paper, the technique of sparse representation is introduced into the spectral estimation, and a new compensation method is proposed, namely RBC with sparse representation (SR-RBC). This method first converts the clutter spectral estimation into an ill-posed problem with the constraint of sparsity. Then, the technique of sparse representation, like iterative reweighted least squares (IRLS), is utilized to solve this problem. Then, the transform matrix is designed so that the processed training data behaves nearly stationary with the test cell. Because the configuration parameters and the clutter spectral response are obtained with full-snapshot using sparse representation, SR-RBC provides more accurate clutter spectral estimation, and the transformed training data are more stationary so that better signal-clutter-ratio (SCR) improvement is expected.

cs.IT↗

arXiv2010

Direct Data Domain STAP using Sparse Representation of Clutter Spectrum

Space-time adaptive processing (STAP) is an effective tool for detecting a moving target in the airborne radar system. Due to the fast-changing clutter scenario and/or non side-looking configuration, the stationarity of the training data is destroyed such that the statistical-based methods suffer performance degradation. Direct data domain (D3) methods avoid non-stationary training data and can effectively suppress the clutter within the test cell. However, this benefit comes at the cost of a reduced system degree of freedom (DOF), which results in performance loss. In this paper, by exploiting the intrinsic sparsity of the spectral distribution, a new direct data domain approach using sparse representation (D3SR) is proposed, which seeks to estimate the high-resolution space-time spectrum with only the test cell. The simulation of both side-looking and non side-looking cases has illustrated the effectiveness of the D3SR spectrum estimation using focal underdetermined system solution (FOCUSS) and norm minimization. Then the clutter covariance matrix (CCM) and the corresponding adaptive filter can be effectively obtained. Since D3SR maintains the full system DOF, it can achieve better performance of output signal-clutter-ratio (SCR) and minimum detectable velocity (MDV) than current D3 methods, e.g., direct data domain least squares (D3LS). Thus D3SR is more effective against the range-dependent clutter and interference in the non-stationary clutter scenario.

cs.IT↗

arXiv2010

Airborne Radar STAP using Sparse Recovery of Clutter Spectrum

Space-time adaptive processing (STAP) is an effective tool for detecting a moving target in spaceborne or airborne radar systems. Statistical-based STAP methods generally need sufficient statistically independent and identically distributed (IID) training data to estimate the clutter characteristics. However, most actual clutter scenarios appear only locally stationary and lack sufficient IID training data. In this paper, by exploiting the intrinsic sparsity of the clutter distribution in the angle-Doppler domain, a new STAP algorithm called SR-STAP is proposed, which uses the technique of sparse recovery to estimate the clutter space-time spectrum. Joint sparse recovery with several training samples is also used to improve the estimation performance. Finally, an effective clutter covariance matrix (CCM) estimate and the corresponding STAP filter are designed based on the estimated clutter spectrum. Both the Mountaintop data and simulated experiments have illustrated the fast convergence rate of this approach. Moreover, SR-STAP is less dependent on prior knowledge, so it is more robust to the mismatch in the prior knowledge than knowledge-based STAP methods. Due to these advantages, SR-STAP has great potential for application in actual clutter scenarios.

cs.IT↗