May 7, 2019

3165 words 15 mins read

Paper Group ANR 61

Bag of Attributes for Video Event Retrieval. Estimating Uncertainty Online Against an Adversary. Performance Based Evaluation of Various Machine Learning Classification Techniques for Chronic Kidney Disease Diagnosis. A Fast Keypoint Based Hybrid Method for Copy Move Forgery Detection. Latent Tree Analysis. Near-optimal Bayesian Active Learning wit …

Bag of Attributes for Video Event Retrieval


Title	Bag of Attributes for Video Event Retrieval
Authors	Leonardo A. Duarte, Otávio A. B. Penatti, Jurandy Almeida
Abstract	In this paper, we present the Bag-of-Attributes (BoA) model for video representation aiming at video event retrieval. The BoA model is based on a semantic feature space for representing videos, resulting in high-level video feature vectors. For creating a semantic space, i.e., the attribute space, we can train a classifier using a labeled image dataset, obtaining a classification model that can be understood as a high-level codebook. This model is used to map low-level frame vectors into high-level vectors (e.g., classifier probability scores). Then, we apply pooling operations on the frame vectors to create the final bag of attributes for the video. In the BoA representation, each dimension corresponds to one category (or attribute) of the semantic space. Other interesting properties are: compactness, flexibility regarding the classifier, and ability to encode multiple semantic concepts in a single video representation. Our experiments considered the semantic space created by a deep convolutional neural network (OverFeat) pre-trained on 1000 object categories of ImageNet. OverFeat was then used to classify each video frame and max pooling combined the frame vectors in the BoA representation for the video. Results using BoA outperformed the baselines with statistical significance in the task of video event retrieval using the EVVE dataset.
Tasks
Published	2016-07-18
URL	http://arxiv.org/abs/1607.05208v1
PDF	http://arxiv.org/pdf/1607.05208v1.pdf
PWC	https://paperswithcode.com/paper/bag-of-attributes-for-video-event-retrieval
Repo
Framework

Estimating Uncertainty Online Against an Adversary


Title	Estimating Uncertainty Online Against an Adversary
Authors	Volodymyr Kuleshov, Stefano Ermon
Abstract	Assessing uncertainty is an important step towards ensuring the safety and reliability of machine learning systems. Existing uncertainty estimation techniques may fail when their modeling assumptions are not met, e.g. when the data distribution differs from the one seen at training time. Here, we propose techniques that assess a classification algorithm’s uncertainty via calibrated probabilities (i.e. probabilities that match empirical outcome frequencies in the long run) and which are guaranteed to be reliable (i.e. accurate and calibrated) on out-of-distribution input, including input generated by an adversary. This represents an extension of classical online learning that handles uncertainty in addition to guaranteeing accuracy under adversarial assumptions. We establish formal guarantees for our methods, and we validate them on two real-world problems: question answering and medical diagnosis from genomic data.
Tasks	Medical Diagnosis, Question Answering
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03594v2
PDF	http://arxiv.org/pdf/1607.03594v2.pdf
PWC	https://paperswithcode.com/paper/estimating-uncertainty-online-against-an
Repo
Framework

Performance Based Evaluation of Various Machine Learning Classification Techniques for Chronic Kidney Disease Diagnosis


Title	Performance Based Evaluation of Various Machine Learning Classification Techniques for Chronic Kidney Disease Diagnosis
Authors	Sahil Sharma, Vinod Sharma, Atul Sharma
Abstract	Areas where Artificial Intelligence (AI) & related fields are finding their applications are increasing day by day, moving from core areas of computer science they are finding their applications in various other domains.In recent times Machine Learning i.e. a sub-domain of AI has been widely used in order to assist medical experts and doctors in the prediction, diagnosis and prognosis of various diseases and other medical disorders. In this manuscript the authors applied various machine learning algorithms to a problem in the domain of medical diagnosis and analyzed their efficiency in predicting the results. The problem selected for the study is the diagnosis of the Chronic Kidney Disease.The dataset used for the study consists of 400 instances and 24 attributes. The authors evaluated 12 classification techniques by applying them to the Chronic Kidney Disease data. In order to calculate efficiency, results of the prediction by candidate methods were compared with the actual medical results of the subject.The various metrics used for performance evaluation are predictive accuracy, precision, sensitivity and specificity. The results indicate that decision-tree performed best with nearly the accuracy of 98.6%, sensitivity of 0.9720, precision of 1 and specificity of 1.
Tasks	Medical Diagnosis
Published	2016-06-28
URL	http://arxiv.org/abs/1606.09581v2
PDF	http://arxiv.org/pdf/1606.09581v2.pdf
PWC	https://paperswithcode.com/paper/performance-based-evaluation-of-various
Repo
Framework

A Fast Keypoint Based Hybrid Method for Copy Move Forgery Detection


Title	A Fast Keypoint Based Hybrid Method for Copy Move Forgery Detection
Authors	Sunil Kumar, J. V. Desai, Shaktidev Mukherjee
Abstract	Copy move forgery detection in digital images has become a very popular research topic in the area of image forensics. Due to the availability of sophisticated image editing tools and ever increasing hardware capabilities, it has become an easy task to manipulate the digital images. Passive forgery detection techniques are more relevant as they can be applied without the prior information about the image in question. Block based techniques are used to detect copy move forgery, but have limitations of large time complexity and sensitivity against affine operations like rotation and scaling. Keypoint based approaches are used to detect forgery in large images where the possibility of significant post processing operations like rotation and scaling is more. A hybrid approach is proposed using different methods for keypoint detection and description. Speeded Up Robust Features (SURF) are used to detect the keypoints in the image and Binary Robust Invariant Scalable Keypoints (BRISK) features are used to describe features at these keypoints. The proposed method has performed better than the existing forgery detection method using SURF significantly in terms of detection speed and is invariant to post processing operations like rotation and scaling. The proposed method is also invariant to other commonly applied post processing operations like adding Gaussian noise and JPEG compression
Tasks	Keypoint Detection
Published	2016-12-11
URL	http://arxiv.org/abs/1612.03989v1
PDF	http://arxiv.org/pdf/1612.03989v1.pdf
PWC	https://paperswithcode.com/paper/a-fast-keypoint-based-hybrid-method-for-copy
Repo
Framework

Latent Tree Analysis


Title	Latent Tree Analysis
Authors	Nevin L. Zhang, Leonard K. M. Poon
Abstract	Latent tree analysis seeks to model the correlations among a set of random variables using a tree of latent variables. It was proposed as an improvement to latent class analysis — a method widely used in social sciences and medicine to identify homogeneous subgroups in a population. It provides new and fruitful perspectives on a number of machine learning areas, including cluster analysis, topic detection, and deep probabilistic modeling. This paper gives an overview of the research on latent tree analysis and various ways it is used in practice.
Tasks
Published	2016-10-01
URL	http://arxiv.org/abs/1610.00085v1
PDF	http://arxiv.org/pdf/1610.00085v1.pdf
PWC	https://paperswithcode.com/paper/latent-tree-analysis
Repo
Framework

Near-optimal Bayesian Active Learning with Correlated and Noisy Tests


Title	Near-optimal Bayesian Active Learning with Correlated and Noisy Tests
Authors	Yuxin Chen, S. Hamed Hassani, Andreas Krause
Abstract	We consider the Bayesian active learning and experimental design problem, where the goal is to learn the value of some unknown target variable through a sequence of informative, noisy tests. In contrast to prior work, we focus on the challenging, yet practically relevant setting where test outcomes can be conditionally dependent given the hidden target variable. Under such assumptions, common heuristics, such as greedily performing tests that maximize the reduction in uncertainty of the target, often perform poorly. In this paper, we propose ECED, a novel, computationally efficient active learning algorithm, and prove strong theoretical guarantees that hold with correlated, noisy tests. Rather than directly optimizing the prediction error, at each step, ECED picks the test that maximizes the gain in a surrogate objective, which takes into account the dependencies between tests. Our analysis relies on an information-theoretic auxiliary function to track the progress of ECED, and utilizes adaptive submodularity to attain the near-optimal bound. We demonstrate strong empirical performance of ECED on two problem instances, including a Bayesian experimental design task intended to distinguish among economic theories of how people make risky decisions, and an active preference learning task via pairwise comparisons.
Tasks	Active Learning
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07334v2
PDF	http://arxiv.org/pdf/1605.07334v2.pdf
PWC	https://paperswithcode.com/paper/near-optimal-bayesian-active-learning-with
Repo
Framework

Multiscale Segmentation via Bregman Distances and Nonlinear Spectral Analysis


Title	Multiscale Segmentation via Bregman Distances and Nonlinear Spectral Analysis
Authors	Leonie Zeune, Guus van Dalum, Leon W. M. M. Terstappen, S. A. van Gils, Christoph Brune
Abstract	In biomedical imaging reliable segmentation of objects (e.g. from small cells up to large organs) is of fundamental importance for automated medical diagnosis. New approaches for multi-scale segmentation can considerably improve performance in case of natural variations in intensity, size and shape. This paper aims at segmenting objects of interest based on shape contours and automatically finding multiple objects with different scales. The overall strategy of this work is to combine nonlinear segmentation with scales spaces and spectral decompositions recently introduced in literature. For this we generalize a variational segmentation model based on total variation using Bregman distances to construct an inverse scale space. This offers the new model to be accomplished by a scale analysis approach based on a spectral decomposition of the total variation. As a result we obtain a very efficient, (nearly) parameter-free multiscale segmentation method that comes with an adaptive regularization parameter choice. The added benefit of our method is demonstrated by systematic synthetic tests and its usage in a new biomedical toolbox for identifying and classifying circulating tumor cells. Due to the nature of nonlinear diffusion underlying, the mathematical concepts in this work offer promising extensions to nonlocal classification problems.
Tasks	Medical Diagnosis
Published	2016-04-22
URL	http://arxiv.org/abs/1604.06665v2
PDF	http://arxiv.org/pdf/1604.06665v2.pdf
PWC	https://paperswithcode.com/paper/multiscale-segmentation-via-bregman-distances
Repo
Framework

A comparison of semi-deterministic and stochastic search techniques


Title	A comparison of semi-deterministic and stochastic search techniques
Authors	Andy M. Connor, Kristina Shea
Abstract	This paper presents an investigation of two search techniques, tabu search (TS) and simulated annealing (SA), to assess their relative merits when applied to engineering design optimisation. Design optimisation problems are generally characterised as having multi-modal search spaces and discontinuities making global optimisation techniques beneficial. Both techniques claim to be capable of locating globally optimum solutions on a range of problems but this capability is derived from different underlying philosophies. While tabu search uses a semi-deterministic approach to escape local optima, simulated annealing uses a complete stochastic approach. The performance of each technique is investigated using a structural optimisation problem. These performances are then compared to each other as and to a steepest descent (SD) method.
Tasks
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05782v1
PDF	http://arxiv.org/pdf/1605.05782v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-semi-deterministic-and
Repo
Framework

Distributional Inclusion Hypothesis for Tensor-based Composition


Title	Distributional Inclusion Hypothesis for Tensor-based Composition
Authors	Dimitri Kartsaklis, Mehrnoosh Sadrzadeh
Abstract	According to the distributional inclusion hypothesis, entailment between words can be measured via the feature inclusions of their distributional vectors. In recent work, we showed how this hypothesis can be extended from words to phrases and sentences in the setting of compositional distributional semantics. This paper focuses on inclusion properties of tensors; its main contribution is a theoretical and experimental analysis of how feature inclusion works in different concrete models of verb tensors. We present results for relational, Frobenius, projective, and holistic methods and compare them to the simple vector addition, multiplication, min, and max models. The degrees of entailment thus obtained are evaluated via a variety of existing word-based measures, such as Weed’s and Clarke’s, KL-divergence, APinc, balAPinc, and two of our previously proposed metrics at the phrase/sentence level. We perform experiments on three entailment datasets, investigating which version of tensor-based composition achieves the highest performance when combined with the sentence-level measures.
Tasks
Published	2016-10-14
URL	http://arxiv.org/abs/1610.04416v1
PDF	http://arxiv.org/pdf/1610.04416v1.pdf
PWC	https://paperswithcode.com/paper/distributional-inclusion-hypothesis-for
Repo
Framework

Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information


Title	Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information
Authors	Yuanzhe Zhang, Kang Liu, Shizhu He, Guoliang Ji, Zhanyi Liu, Hua Wu, Jun Zhao
Abstract	With the rapid growth of knowledge bases (KBs) on the web, how to take full advantage of them becomes increasingly important. Knowledge base-based question answering (KB-QA) is one of the most promising approaches to access the substantial knowledge. Meantime, as the neural network-based (NN-based) methods develop, NN-based KB-QA has already achieved impressive results. However, previous work did not put emphasis on question representation, and the question is converted into a fixed vector regardless of its candidate answers. This simple representation strategy is unable to express the proper information of the question. Hence, we present a neural attention-based model to represent the questions dynamically according to the different focuses of various candidate answer aspects. In addition, we leverage the global knowledge inside the underlying KB, aiming at integrating the rich KB information into the representation of the answers. And it also alleviates the out of vocabulary (OOV) problem, which helps the attention model to represent the question more precisely. The experimental results on WEBQUESTIONS demonstrate the effectiveness of the proposed approach.
Tasks	Question Answering
Published	2016-06-03
URL	http://arxiv.org/abs/1606.00979v1
PDF	http://arxiv.org/pdf/1606.00979v1.pdf
PWC	https://paperswithcode.com/paper/question-answering-over-knowledge-base-with
Repo
Framework

Effective Backscatter Approximation for Photometry in Murky Water


Title	Effective Backscatter Approximation for Photometry in Murky Water
Authors	Chourmouzios Tsiotsios, Maria E. Angelopoulou, Andrew J. Davison, Tae-Kyun Kim
Abstract	Shading-based approaches like Photometric Stereo assume that the image formation model can be effectively optimized for the scene normals. However, in murky water this is a very challenging problem. The light from artificial sources is not only reflected by the scene but it is also scattered by the medium particles, yielding the backscatter component. Backscatter corresponds to a complex term with several unknown variables, and makes the problem of normal estimation hard. In this work, we show that instead of trying to optimize the complex backscatter model or use previous unrealistic simplifications, we can approximate the per-pixel backscatter signal directly from the captured images. Our method is based on the observation that backscatter is saturated beyond a certain distance, i.e. it becomes scene-depth independent, and finally corresponds to a smoothly varying signal which depends strongly on the light position with respect to each pixel. Our backscatter approximation method facilitates imaging and scene reconstruction in murky water when the illumination is artificial as in Photometric Stereo. Specifically, we show that it allows accurate scene normal estimation and offers potentials like single image restoration. We evaluate our approach using numerical simulations and real experiments within both the controlled environment of a big water-tank and real murky port-waters.
Tasks	Image Restoration
Published	2016-04-29
URL	http://arxiv.org/abs/1604.08789v1
PDF	http://arxiv.org/pdf/1604.08789v1.pdf
PWC	https://paperswithcode.com/paper/effective-backscatter-approximation-for
Repo
Framework

A Classification Framework for Partially Observed Dynamical Systems


Title	A Classification Framework for Partially Observed Dynamical Systems
Authors	Yuan Shen, Peter Tino, Krasimira Tsaneva-Atanasova
Abstract	We present a general framework for classifying partially observed dynamical systems based on the idea of learning in the model space. In contrast to the existing approaches using model point estimates to represent individual data items, we employ posterior distributions over models, thus taking into account in a principled manner the uncertainty due to both the generative (observational and/or dynamic noise) and observation (sampling in time) processes. We evaluate the framework on two testbeds - a biological pathway model and a stochastic double-well system. Crucially, we show that the classifier performance is not impaired when the model class used for inferring posterior distributions is much more simple than the observation-generating model class, provided the reduced complexity inferential model class captures the essential characteristics needed for the given classification task.
Tasks
Published	2016-07-07
URL	http://arxiv.org/abs/1607.02085v1
PDF	http://arxiv.org/pdf/1607.02085v1.pdf
PWC	https://paperswithcode.com/paper/a-classification-framework-for-partially
Repo
Framework

Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples


Title	Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples
Authors	Yuan Gao, Jiayi Ma, Alan L. Yuille
Abstract	This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that we wish to recognize. Moreover, these examples are typically corrupted by nuisance variables, both linear (i.e., additive nuisance variables such as bad lighting, wearing of glasses) and non-linear (i.e., non-additive pixel-wise nuisance variables such as expression changes). The small number of labeled examples means that it is hard to remove these nuisance variables between the training and testing faces to obtain good recognition performance. To address the problem we propose a method called Semi-Supervised Sparse Representation based Classification (S$^3$RC). This is based on recent work on sparsity where faces are represented in terms of two dictionaries: a gallery dictionary consisting of one or more examples of each person, and a variation dictionary representing linear nuisance variables (e.g., different lighting conditions, different glasses). The main idea is that (i) we use the variation dictionary to characterize the linear nuisance variables via the sparsity framework, then (ii) prototype face images are estimated as a gallery dictionary via a Gaussian Mixture Model (GMM), with mixed labeled and unlabeled samples in a semi-supervised manner, to deal with the non-linear nuisance variations between labeled and unlabeled samples. We have done experiments with insufficient labeled samples, even when there is only a single labeled sample per person. Our results on the AR, Multi-PIE, CAS-PEAL, and LFW databases demonstrate that the proposed method is able to deliver significantly improved performance over existing methods.
Tasks	Face Recognition, Sparse Representation-based Classification
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03279v2
PDF	http://arxiv.org/pdf/1609.03279v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-sparse-representation-based
Repo
Framework

Towards the Design of an End-to-End Automated System for Image and Video-based Recognition


Title	Towards the Design of an End-to-End Automated System for Image and Video-based Recognition
Authors	Rama Chellappa, Jun-Cheng Chen, Rajeev Ranjan, Swami Sankaranarayanan, Amit Kumar, Vishal M. Patel, Carlos D. Castillo
Abstract	Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output the labels of objects in the input data. Computer vision methods that use representations derived based on geometric, radiometric and neural considerations and statistical and structural matchers and artificial neural network-based methods where a multi-layer network learns the mapping from inputs to class labels have provided competing approaches for image recognition problems. Over the last four years, methods based on Deep Convolutional Neural Networks (DCNNs) have shown impressive performance improvements on object detection/recognition challenge problems. This has been made possible due to the availability of large annotated data, a better understanding of the non-linear mapping between image and class labels as well as the affordability of GPUs. In this paper, we present a brief history of developments in computer vision and artificial neural networks over the last forty years for the problem of image-based recognition. We then present the design details of a deep learning system for end-to-end unconstrained face verification/recognition. Some open issues regarding DCNNs for object recognition problems are then discussed. We caution the readers that the views expressed in this paper are from the authors and authors only!
Tasks	Face Verification, Object Detection, Object Recognition
Published	2016-01-28
URL	http://arxiv.org/abs/1601.07883v1
PDF	http://arxiv.org/pdf/1601.07883v1.pdf
PWC	https://paperswithcode.com/paper/towards-the-design-of-an-end-to-end-automated
Repo
Framework

Universum Learning for Multiclass SVM


Title	Universum Learning for Multiclass SVM
Authors	Sauptik Dhar, Naveen Ramakrishnan, Vladimir Cherkassky, Mohak Shah
Abstract	We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose a span bound for MU-SVM that can be used for model selection thereby avoiding resampling. Empirical results demonstrate the effectiveness of MU-SVM and the proposed bound.
Tasks	Model Selection
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09162v1
PDF	http://arxiv.org/pdf/1609.09162v1.pdf
PWC	https://paperswithcode.com/paper/universum-learning-for-multiclass-svm
Repo
Framework