May 7, 2019

3403 words 16 mins read

Paper Group ANR 109

Visual place recognition using landmark distribution descriptors. 2D Visual Place Recognition for Domestic Service Robots at Night. Digitizing Municipal Street Inspections Using Computer Vision. KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm. Joint mean and covariance estimation with unreplicated matrix-varia …

Visual place recognition using landmark distribution descriptors


Title	Visual place recognition using landmark distribution descriptors
Authors	Pilailuck Panphattarasap, Andrew Calway
Abstract	Recent work by Suenderhauf et al. [1] demonstrated improved visual place recognition using proposal regions coupled with features from convolutional neural networks (CNN) to match landmarks between views. In this work we extend the approach by introducing descriptors built from landmark features which also encode the spatial distribution of the landmarks within a view. Matching descriptors then enforces consistency of the relative positions of landmarks between views. This has a significant impact on performance. For example, in experiments on 10 image-pair datasets, each consisting of 200 urban locations with significant differences in viewing positions and conditions, we recorded average precision of around 70% (at 100% recall), compared with 58% obtained using whole image CNN features and 50% for the method in [1].
Tasks	Visual Place Recognition
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04274v1
PDF	http://arxiv.org/pdf/1608.04274v1.pdf
PWC	https://paperswithcode.com/paper/visual-place-recognition-using-landmark
Repo
Framework

2D Visual Place Recognition for Domestic Service Robots at Night


Title	2D Visual Place Recognition for Domestic Service Robots at Night
Authors	James Mount, Michael Milford
Abstract	Domestic service robots such as lawn mowing and vacuum cleaning robots are the most numerous consumer robots in existence today. While early versions employed random exploration, recent systems fielded by most of the major manufacturers have utilized range-based and visual sensors and user-placed beacons to enable robots to map and localize. However, active range and visual sensing solutions have the disadvantages of being intrusive, expensive, or only providing a 1D scan of the environment, while the requirement for beacon placement imposes other practical limitations. In this paper we present a passive and potentially cheap vision-based solution to 2D localization at night that combines easily obtainable day-time maps with low resolution contrast-normalized image matching algorithms, image sequence-based matching in two-dimensions, place match interpolation and recent advances in conventional low light camera technology. In a range of experiments over a domestic lawn and in a lounge room, we demonstrate that the proposed approach enables 2D localization at night, and analyse the effect on performance of varying odometry noise levels, place match interpolation and sequence matching length. Finally we benchmark the new low light camera technology and show how it can enable robust place recognition even in an environment lit only by a moonless sky, raising the tantalizing possibility of being able to apply all conventional vision algorithms, even in the darkest of nights.
Tasks	Visual Place Recognition
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07708v1
PDF	http://arxiv.org/pdf/1605.07708v1.pdf
PWC	https://paperswithcode.com/paper/2d-visual-place-recognition-for-domestic
Repo
Framework

Digitizing Municipal Street Inspections Using Computer Vision


Title	Digitizing Municipal Street Inspections Using Computer Vision
Authors	Varun Adibhatla, Shi Fan, Krystof Litomisky, Patrick Atwater
Abstract	“People want an authority to tell them how to value things. But they chose this authority not based on facts or results. They chose it because it seems authoritative and familiar.” - The Big Short The pavement condition index is one such a familiar measure used by many US cities to measure street quality and justify billions of dollars spent every year on street repair. These billion-dollar decisions are based on evaluation criteria that are subjective and not representative. In this paper, we build upon our initial submission to D4GX 2015 that approaches this problem of information asymmetry in municipal decision-making. We describe a process to identify street-defects using computer vision techniques on data collected using the Street Quality Identification Device (SQUID). A User Interface to host a large quantity of image data towards digitizing the street inspection process and enabling actionable intelligence for a core public service is also described. This approach of combining device, data and decision-making around street repair enables cities make targeted decisions about street repair and could lead to an anticipatory response which can result in significant cost savings. Lastly, we share lessons learnt from the deployment of SQUID in the city of Syracuse, NY.
Tasks	Decision Making
Published	2016-09-30
URL	http://arxiv.org/abs/1609.09582v1
PDF	http://arxiv.org/pdf/1609.09582v1.pdf
PWC	https://paperswithcode.com/paper/digitizing-municipal-street-inspections-using
Repo
Framework

KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm


Title	KSR: A Semantic Representation of Knowledge Graph within a Novel Unsupervised Paradigm
Authors	Han Xiao, Minlie Huang, Xiaoyan Zhu
Abstract	Knowledge representation is a long-history topic in AI, which is very important. A variety of models have been proposed for knowledge graph embedding, which projects symbolic entities and relations into continuous vector space. However, most related methods merely focus on the data-fitting of knowledge graph, and ignore the interpretable semantic expression. Thus, traditional embedding methods are not friendly for applications that require semantic analysis, such as question answering and entity retrieval. To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments show that our model outperforms other state-of-the-art baselines substantially.
Tasks	Graph Embedding, Knowledge Graph Embedding, Question Answering
Published	2016-08-27
URL	https://arxiv.org/abs/1608.07685v8
PDF	https://arxiv.org/pdf/1608.07685v8.pdf
PWC	https://paperswithcode.com/paper/ksr-a-semantic-representation-of-knowledge
Repo
Framework

Joint mean and covariance estimation with unreplicated matrix-variate data


Title	Joint mean and covariance estimation with unreplicated matrix-variate data
Authors	Michael Hornstein, Roger Fan, Kerby Shedden, Shuheng Zhou
Abstract	It has been proposed that complex populations, such as those that arise in genomics studies, may exhibit dependencies among observations as well as among variables. This gives rise to the challenging problem of analyzing unreplicated high-dimensional data with unknown mean and dependence structures. Matrix-variate approaches that impose various forms of (inverse) covariance sparsity allow flexible dependence structures to be estimated, but cannot directly be applied when the mean and covariance matrices are estimated jointly. We present a practical method utilizing generalized least squares and penalized (inverse) covariance estimation to address this challenge. We establish consistency and obtain rates of convergence for estimating the mean parameters and covariance matrices. The advantages of our approaches are: (i) dependence graphs and covariance structures can be estimated in the presence of unknown mean structure, (ii) the mean structure becomes more efficiently estimated when accounting for the dependence structure among observations; and (iii) inferences about the mean parameters become correctly calibrated. We use simulation studies and analysis of genomic data from a twin study of ulcerative colitis to illustrate the statistical convergence and the performance of our methods in practical settings. Several lines of evidence show that the test statistics for differential gene expression produced by our methods are correctly calibrated and improve power over conventional methods.
Tasks
Published	2016-11-13
URL	http://arxiv.org/abs/1611.04208v4
PDF	http://arxiv.org/pdf/1611.04208v4.pdf
PWC	https://paperswithcode.com/paper/joint-mean-and-covariance-estimation-with
Repo
Framework

Bayesian Optimization for Machine Learning : A Practical Guidebook


Title	Bayesian Optimization for Machine Learning : A Practical Guidebook
Authors	Ian Dewancker, Michael McCourt, Scott Clark
Abstract	The engineering of machine learning systems is still a nascent field; relying on a seemingly daunting collection of quickly evolving tools and best practices. It is our hope that this guidebook will serve as a useful resource for machine learning practitioners looking to take advantage of Bayesian optimization techniques. We outline four example machine learning problems that can be solved using open source machine learning libraries, and highlight the benefits of using Bayesian optimization in the context of these common machine learning applications.
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04858v1
PDF	http://arxiv.org/pdf/1612.04858v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-for-machine-learning-a
Repo
Framework

Inference of Haemoglobin Concentration From Stereo RGB


Title	Inference of Haemoglobin Concentration From Stereo RGB
Authors	Geoffrey Jones, Neil T. Clancy, Yusuf Helo, Simon Arridge, Daniel S. Elson, Danail Stoyanov
Abstract	Multispectral imaging (MSI) can provide information about tissue oxygenation, perfusion and potentially function during surgery. In this paper we present a novel, near real-time technique for intrinsic measurements of total haemoglobin (THb) and blood oxygenation (SO2) in tissue using only RGB images from a stereo laparoscope. The high degree of spectral overlap between channels makes inference of haemoglobin concentration challenging, non-linear and under constrained. We decompose the problem into two constrained linear sub-problems and show that with Tikhonov regularisation the estimation significantly improves, giving robust estimation of the Thb. We demonstrate by using the co-registered stereo image data from two cameras it is possible to get robust SO2 estimation as well. Our method is closed from, providing computational efficiency even with multiple cameras. The method we present requires only spectral response calibration of each camera, without modification of existing laparoscopic imaging hardware. We validate our technique on synthetic data from Monte Carlo simulation % of light transport through soft tissue containing submerged blood vessels and further, in vivo, on a multispectral porcine data set.
Tasks	Calibration
Published	2016-07-11
URL	http://arxiv.org/abs/1607.02936v2
PDF	http://arxiv.org/pdf/1607.02936v2.pdf
PWC	https://paperswithcode.com/paper/inference-of-haemoglobin-concentration-from
Repo
Framework

Monitoring Chinese Population Migration in Consecutive Weekly Basis from Intra-city scale to Inter-province scale by Didi’s Bigdata


Title	Monitoring Chinese Population Migration in Consecutive Weekly Basis from Intra-city scale to Inter-province scale by Didi’s Bigdata
Authors	Renyu Zhao
Abstract	Population migration is valuable information which leads to proper decision in urban-planning strategy, massive investment, and many other fields. For instance, inter-city migration is a posterior evidence to see if the government’s constrain of population works, and inter-community immigration might be a prior evidence of real estate price hike. With timely data, it is also impossible to compare which city is more favorable for the people, suppose the cities release different new regulations, we could also compare the customers of different real estate development groups, where they come from, where they probably will go. Unfortunately these data was not available. In this paper, leveraging the data generated by positioning team in Didi, we propose a novel approach that timely monitoring population migration from community scale to provincial scale. Migration can be detected as soon as in a week. It could be faster, the setting of a week is for statistical purpose. A monitoring system is developed, then applied nation wide in China, some observations derived from the system will be presented in this paper. This new method of migration perception is origin from the insight that nowadays people mostly moving with their personal Access Point (AP), also known as WiFi hotspot. Assume that the ratio of AP moving to the migration of population is constant, analysis of comparative population migration would be feasible. More exact quantitative research would also be done with few sample research and model regression. The procedures of processing data includes many steps: eliminating the impact of pseudo-migration AP, for instance pocket WiFi, and second-hand traded router; distinguishing moving of population with moving of companies; identifying shifting of AP by the finger print clusters, etc..
Tasks
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01955v1
PDF	http://arxiv.org/pdf/1604.01955v1.pdf
PWC	https://paperswithcode.com/paper/monitoring-chinese-population-migration-in
Repo
Framework

Sparse Hierarchical Tucker Factorization and its Application to Healthcare


Title	Sparse Hierarchical Tucker Factorization and its Application to Healthcare
Authors	Ioakeim Perros, Robert Chen, Richard Vuduc, Jimeng Sun
Abstract	We propose a new tensor factorization method, called the Sparse Hierarchical-Tucker (Sparse H-Tucker), for sparse and high-order data tensors. Sparse H-Tucker is inspired by its namesake, the classical Hierarchical Tucker method, which aims to compute a tree-structured factorization of an input data set that may be readily interpreted by a domain expert. However, Sparse H-Tucker uses a nested sampling technique to overcome a key scalability problem in Hierarchical Tucker, which is the creation of an unwieldy intermediate dense core tensor; the result of our approach is a faster, more space-efficient, and more accurate method. We extensively test our method on a real healthcare dataset, which is collected from 30K patients and results in an 18th order sparse data tensor. Unlike competing methods, Sparse H-Tucker can analyze the full data set on a single multi-threaded machine. It can also do so more accurately and in less time than the state-of-the-art: on a 12th order subset of the input data, Sparse H-Tucker is 18x more accurate and 7.5x faster than a previously state-of-the-art method. Even for analyzing low order tensors (e.g., 4-order), our method requires close to an order of magnitude less time and over two orders of magnitude less memory, as compared to traditional tensor factorization methods such as CP and Tucker. Moreover, we observe that Sparse H-Tucker scales nearly linearly in the number of non-zero tensor elements. The resulting model also provides an interpretable disease hierarchy, which is confirmed by a clinical expert.
Tasks
Published	2016-10-25
URL	http://arxiv.org/abs/1610.07722v1
PDF	http://arxiv.org/pdf/1610.07722v1.pdf
PWC	https://paperswithcode.com/paper/sparse-hierarchical-tucker-factorization-and
Repo
Framework

Time-Varying Gaussian Process Bandit Optimization


Title	Time-Varying Gaussian Process Bandit Optimization
Authors	Ilija Bogunovic, Jonathan Scarlett, Volkan Cevher
Abstract	We consider the sequential Bayesian optimization problem with bandit feedback, adopting a formulation that allows for the reward function to vary with time. We model the reward function using a Gaussian process whose evolution obeys a simple Markov model. We introduce two natural extensions of the classical Gaussian process upper confidence bound (GP-UCB) algorithm. The first, R-GP-UCB, resets GP-UCB at regular intervals. The second, TV-GP-UCB, instead forgets about old data in a smooth fashion. Our main contribution comprises of novel regret bounds for these algorithms, providing an explicit characterization of the trade-off between the time horizon and the rate at which the function varies. We illustrate the performance of the algorithms on both synthetic and real data, and we find the gradual forgetting of TV-GP-UCB to perform favorably compared to the sharp resetting of R-GP-UCB. Moreover, both algorithms significantly outperform classical GP-UCB, since it treats stale and fresh data equally.
Tasks
Published	2016-01-25
URL	http://arxiv.org/abs/1601.06650v1
PDF	http://arxiv.org/pdf/1601.06650v1.pdf
PWC	https://paperswithcode.com/paper/time-varying-gaussian-process-bandit
Repo
Framework

Near-Data Processing for Differentiable Machine Learning Models


Title	Near-Data Processing for Differentiable Machine Learning Models
Authors	Hyeokjun Choe, Seil Lee, Hyunha Nam, Seongsik Park, Seijoon Kim, Eui-Young Chung, Sungroh Yoon
Abstract	Near-data processing (NDP) refers to augmenting memory or storage with processing power. Despite its potential for acceleration computing and reducing power requirements, only limited progress has been made in popularizing NDP for various reasons. Recently, two major changes have occurred that have ignited renewed interest and caused a resurgence of NDP. The first is the success of machine learning (ML), which often demands a great deal of computation for training, requiring frequent transfers of big data. The second is the popularity of NAND flash-based solid-state drives (SSDs) containing multicore processors that can accommodate extra computation for data processing. In this paper, we evaluate the potential of NDP for ML using a new SSD platform that allows us to simulate instorage processing (ISP) of ML workloads. Our platform (named ISP-ML) is a full-fledged simulator of a realistic multi-channel SSD that can execute various ML algorithms using data stored in the SSD. To conduct a thorough performance analysis and an in-depth comparison with alternative techniques, we focus on a specific algorithm: stochastic gradient descent (SGD), which is the de facto standard for training differentiable models such as logistic regression and neural networks. We implement and compare three SGD variants (synchronous, Downpour, and elastic averaging) using ISP-ML, exploiting the multiple NAND channels to parallelize SGD. In addition, we compare the performance of ISP and that of conventional in-host processing, revealing the advantages of ISP. Based on the advantages and limitations identified through our experiments, we further discuss directions for future research on ISP for accelerating ML.
Tasks
Published	2016-10-06
URL	http://arxiv.org/abs/1610.02273v3
PDF	http://arxiv.org/pdf/1610.02273v3.pdf
PWC	https://paperswithcode.com/paper/near-data-processing-for-differentiable
Repo
Framework

Brain-Inspired Deep Networks for Image Aesthetics Assessment


Title	Brain-Inspired Deep Networks for Image Aesthetics Assessment
Authors	Zhangyang Wang, Shiyu Chang, Florin Dolcos, Diane Beck, Ding Liu, Thomas S. Huang
Abstract	Image aesthetics assessment has been challenging due to its subjective nature. Inspired by the scientific advances in the human visual perception and neuroaesthetics, we design Brain-Inspired Deep Networks (BDN) for this task. BDN first learns attributes through the parallel supervised pathways, on a variety of selected feature dimensions. A high-level synthesis network is trained to associate and transform those attributes into the overall aesthetics rating. We then extend BDN to predicting the distribution of human ratings, since aesthetics ratings are often subjective. Another highlight is our first-of-its-kind study of label-preserving transformations in the context of aesthetics assessment, which leads to an effective data augmentation approach. Experimental results on the AVA dataset show that our biological inspired and task-specific BDN model gains significantly performance improvement, compared to other state-of-the-art models with the same or higher parameter capacity.
Tasks	Data Augmentation
Published	2016-01-16
URL	http://arxiv.org/abs/1601.04155v2
PDF	http://arxiv.org/pdf/1601.04155v2.pdf
PWC	https://paperswithcode.com/paper/brain-inspired-deep-networks-for-image
Repo
Framework

A Non-Local Conventional Approach for Noise Removal in 3D MRI


Title	A Non-Local Conventional Approach for Noise Removal in 3D MRI
Authors	Sona Morajab, Mehregan Mahdavi
Abstract	In this paper, a filtering approach for the 3D magnetic resonance imaging (MRI) assuming a Rician model for noise is addressed. Our denoising method is based on the Conventional Approach (CA) proposed to deal with the noise issue in the squared domain of the acquired magnitude MRI, where the noise distribution follows a Chi-square model rather than the Rician one. In the CA filtering method, the local samples around each voxel is used to estimate the unknown signal value. Intrinsically, such a method fails to achieve the best results where the underlying signal values have different statistical properties. On the contrary, our proposal takes advantage of the data redundancy and self-similarity properties of real MR images to improve the noise removal performance. In other words, in our approach, the statistical momentums of the given 3D MR volume are first calculated to explore the similar patches inside a defined search volume. Then, these patches are put together to obtain the noise-free value for each voxel under processing. The experimental results on the synthetic as well as the clinical MR data show our proposed method outperforms the other compared denoising filters.
Tasks	Denoising
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06558v1
PDF	http://arxiv.org/pdf/1608.06558v1.pdf
PWC	https://paperswithcode.com/paper/a-non-local-conventional-approach-for-noise
Repo
Framework

Parametric Prediction from Parametric Agents


Title	Parametric Prediction from Parametric Agents
Authors	Yuan Luo, Nihar B. Shah, Jianwei Huang, Jean Walrand
Abstract	We consider a problem of prediction based on opinions elicited from heterogeneous rational agents with private information. Making an accurate prediction with a minimal cost requires a joint design of the incentive mechanism and the prediction algorithm. Such a problem lies at the nexus of statistical learning theory and game theory, and arises in many domains such as consumer surveys and mobile crowdsourcing. In order to elicit heterogeneous agents’ private information and incentivize agents with different capabilities to act in the principal’s best interest, we design an optimal joint incentive mechanism and prediction algorithm called COPE (COst and Prediction Elicitation), the analysis of which offers several valuable engineering insights. First, when the costs incurred by the agents are linear in the exerted effort, COPE corresponds to a “crowd contending” mechanism, where the principal only employs the agent with the highest capability. Second, when the costs are quadratic, COPE corresponds to a “crowd-sourcing” mechanism that employs multiple agents with different capabilities at the same time. Numerical simulations show that COPE improves the principal’s profit and the network profit significantly (larger than 30% in our simulations), comparing to those mechanisms that assume all agents have equal capabilities.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07435v1
PDF	http://arxiv.org/pdf/1602.07435v1.pdf
PWC	https://paperswithcode.com/paper/parametric-prediction-from-parametric-agents
Repo
Framework

Mixture Proportion Estimation via Kernel Embedding of Distributions


Title	Mixture Proportion Estimation via Kernel Embedding of Distributions
Authors	Harish G. Ramaswamy, Clayton Scott, Ambuj Tewari
Abstract	Mixture proportion estimation (MPE) is the problem of estimating the weight of a component distribution in a mixture, given samples from the mixture and component. This problem constitutes a key part in many “weakly supervised learning” problems like learning with positive and unlabelled samples, learning with label noise, anomaly detection and crowdsourcing. While there have been several methods proposed to solve this problem, to the best of our knowledge no efficient algorithm with a proven convergence rate towards the true proportion exists for this problem. We fill this gap by constructing a provably correct algorithm for MPE, and derive convergence rates under certain assumptions on the distribution. Our method is based on embedding distributions onto an RKHS, and implementing it only requires solving a simple convex quadratic programming problem a few times. We run our algorithm on several standard classification datasets, and demonstrate that it performs comparably to or better than other algorithms on most datasets.
Tasks	Anomaly Detection
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02501v2
PDF	http://arxiv.org/pdf/1603.02501v2.pdf
PWC	https://paperswithcode.com/paper/mixture-proportion-estimation-via-kernel
Repo
Framework