May 7, 2019

3158 words 15 mins read

Paper Group ANR 87

Automated Resolution Selection for Image Segmentation. Deep CNNs for HEp-2 Cells Classification : A Cross-specimen Analysis. Reconstructing Neural Parameters and Synapses of arbitrary interconnected Neurons from their Simulated Spiking Activity. Features Fusion for Classification of Logos. DiffSharp: An AD Library for .NET Languages. Real time erro …

Automated Resolution Selection for Image Segmentation


Title	Automated Resolution Selection for Image Segmentation
Authors	Fares Al-Qunaieer, Hamid R. Tizhoosh, Shahryar Rahnamayan
Abstract	It is well-known in image processing that computational cost increases rapidly with the number and dimensions of the images to be processed. Several fields, such as medical imaging, routinely use numerous very large images, which might also be 3D and/or captured at several frequency bands, all adding to the computational expense. Multiresolution analysis is a method of increasing the efficiency of the segmentation process. One multiresolution approach is the coarse-to-fine segmentation strategy, whereby the segmentation starts at a coarse resolution and is then fine-tuned during subsequent steps. The starting resolution for segmentation is generally selected arbitrarily with no clear selection criteria. The research reported in this paper showed that starting from different resolutions for image segmentation results in different accuracies and computational times, even for images of the same category (depicting similar scenes or objects). An automated method for resolution selection for an input image would thus be beneficial. This paper introduces a framework for the automated selection of the best resolution for image segmentation. We propose a measure for defining the best resolution based on user/system criteria, offering a trade-off between accuracy and computation time. A learning approach is then introduced for the selection of the resolution, whereby extracted image features are mapped to the previously determined best resolution. In the learning process, class (i.e., resolution) distribution is generally imbalanced, making effective learning from the data difficult. Experiments conducted with three datasets using two different segmentation algorithms show that the resolutions selected through learning enable much faster segmentation than the original ones, while retaining at least the original accuracy.
Tasks	Semantic Segmentation
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06820v1
PDF	http://arxiv.org/pdf/1605.06820v1.pdf
PWC	https://paperswithcode.com/paper/automated-resolution-selection-for-image
Repo
Framework

Deep CNNs for HEp-2 Cells Classification : A Cross-specimen Analysis


Title	Deep CNNs for HEp-2 Cells Classification : A Cross-specimen Analysis
Authors	Hongwei Li, Wei-Shi Zheng, Jianguo Zhang
Abstract	Automatic classification of Human Epithelial Type-2 (HEp-2) cells staining patterns is an important and yet a challenging problem. Although both shallow and deep methods have been applied, the study of deep convolutional networks (CNNs) on this topic is shallow to date, thus failed to claim its top position for this problem. In this paper, we propose a novel study of using CNNs for HEp-2 cells classification focusing on cross-specimen analysis, a key evaluation for generalization. For the first time, our study reveals several key factors of using CNNs for HEp-2 cells classification. Our proposed system achieves state-of-the-art classification accuracy on public benchmark dataset. Comparative experiments on different training data reveals that adding different specimens,rather than increasing in numbers by affine transformations, helps to train a good deep model. This opens a new avenue for adopting deep CNNs to HEp-2 cells classification.
Tasks
Published	2016-04-20
URL	http://arxiv.org/abs/1604.05816v3
PDF	http://arxiv.org/pdf/1604.05816v3.pdf
PWC	https://paperswithcode.com/paper/deep-cnns-for-hep-2-cells-classification-a
Repo
Framework

Reconstructing Neural Parameters and Synapses of arbitrary interconnected Neurons from their Simulated Spiking Activity


Title	Reconstructing Neural Parameters and Synapses of arbitrary interconnected Neurons from their Simulated Spiking Activity
Authors	J. Fischer, P. Manoonpong, S. Lackner
Abstract	To understand the behavior of a neural circuit it is a presupposition that we have a model of the dynamical system describing this circuit. This model is determined by several parameters, including not only the synaptic weights, but also the parameters of each neuron. Existing works mainly concentrate on either the synaptic weights or the neural parameters. In this paper we present an algorithm to reconstruct all parameters including the synaptic weights of a spiking neuron model. The model based on works of Eugene M. Izhikevich (Izhikevich 2007) consists of two differential equations and covers different types of cortical neurons. It combines the dynamical properties of Hodgkin-Huxley-type dynamics with a high computational efficiency. The presented algorithm uses the recordings of the corresponding membrane potentials of the model for the reconstruction and consists of two main components. The first component is a rank based Genetic Algorithm (GA) which is used to find the neural parameters of the model. The second one is a Least Mean Squares approach which computes the synaptic weights of all interconnected neurons by minimizing the squared error between the calculated and the measured membrane potentials for each time step. In preparation for the reconstruction of the neural parameters and of the synaptic weights from real measured membrane potentials, promising results based on simulated data generated with a randomly parametrized Izhikevich model are presented. The reconstruction does not only converge to a global minimum of neural parameters, but also approximates the synaptic weights with high precision.
Tasks
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06132v1
PDF	http://arxiv.org/pdf/1608.06132v1.pdf
PWC	https://paperswithcode.com/paper/reconstructing-neural-parameters-and-synapses
Repo
Framework

Features Fusion for Classification of Logos


Title	Features Fusion for Classification of Logos
Authors	N. Vinay Kumar, Pratheek, V. Vijaya Kantha, K. N. Govindaraju, D. S. Guru
Abstract	In this paper, a logo classification system based on the appearance of logo images is proposed. The proposed classification system makes use of global characteristics of logo images for classification. Color, texture, and shape of a logo wholly describe the global characteristics of logo images. The various combinations of these characteristics are used for classification. The combination contains only with single feature or with fusion of two features or fusion of all three features considered at a time respectively. Further, the system categorizes the logo image into: a logo image with fully text or with fully symbols or containing both symbols and texts.. The K-Nearest Neighbour (K-NN) classifier is used for classification. Due to the lack of color logo image dataset in the literature, the same is created consisting 5044 color logo images. Finally, the performance of the classification system is evaluated through accuracy, precision, recall and F-measure computed from the confusion matrix. The experimental results show that the most promising results are obtained for fusion of features.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01414v1
PDF	http://arxiv.org/pdf/1609.01414v1.pdf
PWC	https://paperswithcode.com/paper/features-fusion-for-classification-of-logos
Repo
Framework

DiffSharp: An AD Library for .NET Languages


Title	DiffSharp: An AD Library for .NET Languages
Authors	Atılım Güneş Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind
Abstract	DiffSharp is an algorithmic differentiation or automatic differentiation (AD) library for the .NET ecosystem, which is targeted by the C# and F# languages, among others. The library has been designed with machine learning applications in mind, allowing very succinct implementations of models and optimization routines. DiffSharp is implemented in F# and exposes forward and reverse AD operators as general nestable higher-order functions, usable by any .NET language. It provides high-performance linear algebra primitives—scalars, vectors, and matrices, with a generalization to tensors underway—that are fully supported by all the AD operators, and which use a BLAS/LAPACK backend via the highly optimized OpenBLAS library. DiffSharp currently uses operator overloading, but we are developing a transformation-based version of the library using F#‘s “code quotation” metaprogramming facility. Work on a CUDA-based GPU backend is also underway.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03423v1
PDF	http://arxiv.org/pdf/1611.03423v1.pdf
PWC	https://paperswithcode.com/paper/diffsharp-an-ad-library-for-net-languages
Repo
Framework

Real time error detection in metal arc welding process using Artificial Neural Netwroks


Title	Real time error detection in metal arc welding process using Artificial Neural Netwroks
Authors	Prashant Sharma, Shaju K. Albert, S. Rajeswari
Abstract	Quality assurance in production line demands reliable weld joints. Human made errors is a major cause of faulty production. Promptly Identifying errors in the weld while welding is in progress will decrease the post inspection cost spent on the welding process. Electrical parameters generated during welding, could able to characterize the process efficiently. Parameter values are collected using high speed data acquisition system. Time series analysis tasks such as filtering, pattern recognition etc. are performed over the collected data. Filtering removes the unwanted noisy signal components and pattern recognition task segregate error patterns in the time series based upon similarity, which is performed by Self Organized mapping clustering algorithm. Welder quality is thus compared by detecting and counting number of error patterns appeared in his parametric time series. Moreover, Self Organized mapping algorithm provides the database in which patterns are segregated into two classes either desirable or undesirable. Database thus generated is used to train the classification algorithms, and thereby automating the real time error detection task. Multi Layer Perceptron and Radial basis function are the two classification algorithms used, and their performance has been compared based on metrics such as specificity, sensitivity, accuracy and time required in training.
Tasks	Time Series, Time Series Analysis
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03149v1
PDF	http://arxiv.org/pdf/1603.03149v1.pdf
PWC	https://paperswithcode.com/paper/real-time-error-detection-in-metal-arc
Repo
Framework

Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images


Title	Center-Focusing Multi-task CNN with Injected Features for Classification of Glioma Nuclear Images
Authors	Veda Murthy, Le Hou, Dimitris Samaras, Tahsin M. Kurc, Joel H. Saltz
Abstract	Classifying the various shapes and attributes of a glioma cell nucleus is crucial for diagnosis and understanding the disease. We investigate automated classification of glioma nuclear shapes and visual attributes using Convolutional Neural Networks (CNNs) on pathology images of automatically segmented nuclei. We propose three methods that improve the performance of a previously-developed semi-supervised CNN. First, we propose a method that allows the CNN to focus on the most important part of an image- the image’s center containing the nucleus. Second, we inject (concatenate) pre-extracted VGG features into an intermediate layer of our Semi-Supervised CNN so that during training, the CNN can learn a set of complementary features. Third, we separate the losses of the two groups of target classes (nuclear shapes and attributes) into a single-label loss and a multi-label loss so that the prior knowledge of inter-label exclusiveness can be incorporated. On a dataset of 2078 images, the proposed methods combined reduce the error rate of attribute and shape classification by 21.54% and 15.07% respectively compared to the existing state-of-the-art method on the same dataset.
Tasks
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06825v2
PDF	http://arxiv.org/pdf/1612.06825v2.pdf
PWC	https://paperswithcode.com/paper/center-focusing-multi-task-cnn-with-injected
Repo
Framework

Real-time Online Action Detection Forests using Spatio-temporal Contexts


Title	Real-time Online Action Detection Forests using Spatio-temporal Contexts
Authors	Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
Abstract	Online action detection (OAD) is challenging since 1) robust yet computationally expensive features cannot be straightforwardly used due to the real-time processing requirements and 2) the localization and classification of actions have to be performed even before they are fully observed. We propose a new random forest (RF)-based online action detection framework that addresses these challenges. Our algorithm uses computationally efficient skeletal joint features. High accuracy is achieved by using robust convolutional neural network (CNN)-based features which are extracted from the raw RGBD images, plus the temporal relationships between the current frame of interest, and the past and future frames. While these high-quality features are not available in real-time testing scenario, we demonstrate that they can be effectively exploited in training RF classifiers: We use these spatio-temporal contexts to craft RF’s new split functions improving RFs’ leaf node statistics. Experiments with challenging MSRAction3D, G3D, and OAD datasets demonstrate that our algorithm significantly improves the accuracy over the state-of-the-art online action detection algorithms while achieving the real-time efficiency of existing skeleton-based RF classifiers.
Tasks	Action Detection
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09334v1
PDF	http://arxiv.org/pdf/1610.09334v1.pdf
PWC	https://paperswithcode.com/paper/real-time-online-action-detection-forests
Repo
Framework

Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion


Title	Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion
Authors	Mehrdad J. Gangeh, Safaa M. A. Bedawi, Ali Ghodsi, Fakhri Karray
Abstract	In this paper, a novel semi-supervised dictionary learning and sparse representation (SS-DLSR) is proposed. The proposed method benefits from the supervisory information by learning the dictionary in a space where the dependency between the data and class labels is maximized. This maximization is performed using Hilbert-Schmidt independence criterion (HSIC). On the other hand, the global distribution of the underlying manifolds were learned from the unlabeled data by minimizing the distances between the unlabeled data and the corresponding nearest labeled data in the space of the dictionary learned. The proposed SS-DLSR algorithm has closed-form solutions for both the dictionary and sparse coefficients, and therefore does not have to learn the two iteratively and alternately as is common in the literature of the DLSR. This makes the solution for the proposed algorithm very fast. The experiments confirm the improvement in classification performance on benchmark datasets by including the information from both labeled and unlabeled data, particularly when there are many unlabeled data.
Tasks	Dictionary Learning
Published	2016-04-25
URL	http://arxiv.org/abs/1604.07319v1
PDF	http://arxiv.org/pdf/1604.07319v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-dictionary-learning-based-on
Repo
Framework

Confidence Intervals for Algorithmic Leveraging in Linear Regression


Title	Confidence Intervals for Algorithmic Leveraging in Linear Regression
Authors	Katelyn Gao
Abstract	The age of big data has produced data sets that are computationally expensive to analyze and store. Algorithmic leveraging proposes that we sample observations from the original data set to generate a representative data set and then perform analysis on the representative data set. In this paper, we present efficient algorithms for constructing finite sample confidence intervals for each algorithmic leveraging estimated regression coefficient, with asymptotic coverage guarantees. In simulations, we confirm empirically that the confidence intervals have the desired coverage probabilities, while bootstrap confidence intervals may not.
Tasks
Published	2016-06-05
URL	http://arxiv.org/abs/1606.01473v4
PDF	http://arxiv.org/pdf/1606.01473v4.pdf
PWC	https://paperswithcode.com/paper/confidence-intervals-for-algorithmic
Repo
Framework

Multi-Atlas Segmentation using Partially Annotated Data: Methods and Annotation Strategies


Title	Multi-Atlas Segmentation using Partially Annotated Data: Methods and Annotation Strategies
Authors	Lisa M. Koch, Martin Rajchl, Wenjia Bai, Christian F. Baumgartner, Tong Tong, Jonathan Passerat-Palmbach, Paul Aljabar, Daniel Rueckert
Abstract	Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due to the time required for the labelling task. Segmentation methods requiring only a proportion of each atlas image to be labelled could therefore reduce the workload on expert raters tasked with annotating atlas images. To address this issue, we first re-examine the labelling problem common in many existing approaches and formulate its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image. This provides a unifying framework for multi-atlas segmentation. We then show how modifications in the graph configuration of the proposed framework enable the use of partially annotated atlas images and investigate different partial annotation strategies. The proposed method was evaluated on two Magnetic Resonance Imaging (MRI) datasets for hippocampal and cardiac segmentation. Experiments were performed aimed at (1) recreating existing segmentation techniques with the proposed framework and (2) demonstrating the potential of employing sparsely annotated atlas data for multi-atlas segmentation.
Tasks	Cardiac Segmentation
Published	2016-04-29
URL	http://arxiv.org/abs/1605.00029v1
PDF	http://arxiv.org/pdf/1605.00029v1.pdf
PWC	https://paperswithcode.com/paper/multi-atlas-segmentation-using-partially
Repo
Framework

Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm


Title	Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm
Authors	Kejun Huang, Xiao Fu, Nicholas D. Sidiropoulos
Abstract	In topic modeling, many algorithms that guarantee identifiability of the topics have been developed under the premise that there exist anchor words – i.e., words that only appear (with positive probability) in one topic. Follow-up work has resorted to three or higher-order statistics of the data corpus to relax the anchor word assumption. Reliable estimates of higher-order statistics are hard to obtain, however, and the identification of topics under those models hinges on uncorrelatedness of the topics, which can be unrealistic. This paper revisits topic modeling based on second-order moments, and proposes an anchor-free topic mining framework. The proposed approach guarantees the identification of the topics under a much milder condition compared to the anchor-word assumption, thereby exhibiting much better robustness in practice. The associated algorithm only involves one eigen-decomposition and a few small linear programs. This makes it easy to implement and scale up to very large problem instances. Experiments using the TDT2 and Reuters-21578 corpus demonstrate that the proposed anchor-free approach exhibits very favorable performance (measured using coherence, similarity count, and clustering accuracy metrics) compared to the prior art.
Tasks	Accuracy Metrics
Published	2016-11-15
URL	http://arxiv.org/abs/1611.05010v1
PDF	http://arxiv.org/pdf/1611.05010v1.pdf
PWC	https://paperswithcode.com/paper/anchor-free-correlated-topic-modeling
Repo
Framework

Region Based Approximation for High Dimensional Bayesian Network Models


Title	Region Based Approximation for High Dimensional Bayesian Network Models
Authors	Peng Lin, Martin Neil, Norman Fenton
Abstract	Performing efficient inference on Bayesian Networks (BNs), with large numbers of densely connected variables is challenging. With exact inference methods, such as the Junction Tree algorithm, clustering complexity can grow exponentially with the number of nodes and so computation becomes intractable. This paper presents a general purpose approximate inference algorithm called Triplet Region Construction (TRC) that reduces the clustering complexity for factorized models from worst case exponential to polynomial. We employ graph factorization to reduce connection complexity and produce clusters of limited size. Unlike MCMC algorithms TRC is guaranteed to converge and we present experiments that show that TRC achieves accurate results when compared with exact solutions.
Tasks
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02086v1
PDF	http://arxiv.org/pdf/1602.02086v1.pdf
PWC	https://paperswithcode.com/paper/region-based-approximation-for-high
Repo
Framework

Risk-Aware Algorithms for Adversarial Contextual Bandits


Title	Risk-Aware Algorithms for Adversarial Contextual Bandits
Authors	Wen Sun, Debadeepta Dey, Ashish Kapoor
Abstract	In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In addition to minimizing the cumulative cost, the learner also needs to satisfy long-term risk constraints – the average of the cumulative risk from all pulled arms should not be larger than a pre-defined threshold. To address this problem, we first study the full information setting where in each round the learner receives an adversarial convex loss and a convex constraint. We develop a meta algorithm leveraging online mirror descent for the full information setting and extend it to contextual bandit with risk constraints setting using expert advice. Our algorithms can achieve near-optimal regret in terms of minimizing the total cost, while successfully maintaining a sublinear growth of cumulative risk constraint violation.
Tasks	Multi-Armed Bandits
Published	2016-10-17
URL	http://arxiv.org/abs/1610.05129v1
PDF	http://arxiv.org/pdf/1610.05129v1.pdf
PWC	https://paperswithcode.com/paper/risk-aware-algorithms-for-adversarial
Repo
Framework

How to learn a graph from smooth signals


Title	How to learn a graph from smooth signals
Authors	Vassilis Kalofolias
Abstract	We propose a framework that learns the graph structure underlying a set of smooth signals. Given $X\in\mathbb{R}^{m\times n}$ whose rows reside on the vertices of an unknown graph, we learn the edge weights $w\in\mathbb{R}_+^{m(m-1)/2}$ under the smoothness assumption that $\text{tr}{X^\top LX}$ is small. We show that the problem is a weighted $\ell$-1 minimization that leads to naturally sparse solutions. We point out how known graph learning or construction techniques fall within our framework and propose a new model that performs better than the state of the art in many settings. We present efficient, scalable primal-dual based algorithms for both our model and the previous state of the art, and evaluate their performance on artificial and real data.
Tasks
Published	2016-01-11
URL	http://arxiv.org/abs/1601.02513v1
PDF	http://arxiv.org/pdf/1601.02513v1.pdf
PWC	https://paperswithcode.com/paper/how-to-learn-a-graph-from-smooth-signals
Repo
Framework