May 7, 2019

3002 words 15 mins read

Paper Group ANR 127

Fuzzy Statistical Matrices for Cell Classification. Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning. Leveraging Unstructured Data to Detect Emerging Reliability Issues. Scalable Approximations for Generalized Linear Problems. Bibliographic Analysis with the Citation Network Topic Model. Towards Neural Knowledge DNA. …

Fuzzy Statistical Matrices for Cell Classification


Title	Fuzzy Statistical Matrices for Cell Classification
Authors	Guillaume Thibault, Izhak Shafran
Abstract	In this paper, we generalize image (texture) statistical descriptors and propose algorithms that improve their efficacy. Recently, a new method showed how the popular Co-Occurrence Matrix (COM) can be modified into a fuzzy version (FCOM) which is more effective and robust to noise. Here, we introduce new fuzzy versions of two additional higher order statistical matrices: the Run Length Matrix (RLM) and the Size Zone Matrix (SZM). We define the fuzzy zones and propose an efficient algorithm to compute the descriptors. We demonstrate the advantage of the proposed improvements over several state-of-the-art methods on three tasks from quantitative cell biology: analyzing and classifying Human Epithelial type 2 (HEp-2) cells using Indirect Immunofluorescence protocol (IFF).
Tasks
Published	2016-11-18
URL	http://arxiv.org/abs/1611.06009v1
PDF	http://arxiv.org/pdf/1611.06009v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-statistical-matrices-for-cell
Repo
Framework

Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning


Title	Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning
Authors	Qiangui Huang, Weiyue Wang, Kevin Zhou, Suya You, Ulrich Neumann
Abstract	Recurrent neural network (RNN), as a powerful contextual dependency modeling framework, has been widely applied to scene labeling problems. However, this work shows that directly applying traditional RNN architectures, which unfolds a 2D lattice grid into a sequence, is not sufficient to model structure dependencies in images due to the “impact vanishing” problem. First, we give an empirical analysis about the “impact vanishing” problem. Then, a new RNN unit named Recurrent Neural Network with explicit long range conditioning (RNN-ELC) is designed to alleviate this problem. A novel neural network architecture is built for scene labeling tasks where one of the variants of the new RNN unit, Gated Recurrent Unit with Explicit Long-range Conditioning (GRU-ELC), is used to model multi scale contextual dependencies in images. We validate the use of GRU-ELC units with state-of-the-art performance on three standard scene labeling datasets. Comprehensive experiments demonstrate that the new GRU-ELC unit benefits scene labeling problem a lot as it can encode longer contextual dependencies in images more effectively than traditional RNN units.
Tasks	Scene Labeling
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07485v2
PDF	http://arxiv.org/pdf/1611.07485v2.pdf
PWC	https://paperswithcode.com/paper/scene-labeling-using-gated-recurrent-units
Repo
Framework

Leveraging Unstructured Data to Detect Emerging Reliability Issues


Title	Leveraging Unstructured Data to Detect Emerging Reliability Issues
Authors	Deovrat Kakde, Arin Chaudhuri
Abstract	Unstructured data refers to information that does not have a predefined data model or is not organized in a pre-defined manner. Loosely speaking, unstructured data refers to text data that is generated by humans. In after-sales service businesses, there are two main sources of unstructured data: customer complaints, which generally describe symptoms, and technician comments, which outline diagnostics and treatment information. A legitimate customer complaint can eventually be tracked to a failure or a claim. However, there is a delay between the time of a customer complaint and the time of a failure or a claim. A proactive strategy aimed at analyzing customer complaints for symptoms can help service providers detect reliability problems in advance and initiate corrective actions such as recalls. This paper introduces essential text mining concepts in the context of reliability analysis and a method to detect emerging reliability issues. The application of the method is illustrated using a case study.
Tasks
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07745v1
PDF	http://arxiv.org/pdf/1607.07745v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-unstructured-data-to-detect
Repo
Framework

Scalable Approximations for Generalized Linear Problems


Title	Scalable Approximations for Generalized Linear Problems
Authors	Murat A. Erdogdu, Mohsen Bayati, Lee H. Dicker
Abstract	In stochastic optimization, the population risk is generally approximated by the empirical risk. However, in the large-scale setting, minimization of the empirical risk may be computationally restrictive. In this paper, we design an efficient algorithm to approximate the population risk minimizer in generalized linear problems such as binary classification with surrogate losses and generalized linear regression models. We focus on large-scale problems, where the iterative minimization of the empirical risk is computationally intractable, i.e., the number of observations $n$ is much larger than the dimension of the parameter $p$, i.e. $n \gg p \gg 1$. We show that under random sub-Gaussian design, the true minimizer of the population risk is approximately proportional to the corresponding ordinary least squares (OLS) estimator. Using this relation, we design an algorithm that achieves the same accuracy as the empirical risk minimizer through iterations that attain up to a cubic convergence rate, and that are cheaper than any batch optimization algorithm by at least a factor of $\mathcal{O}(p)$. We provide theoretical guarantees for our algorithm, and analyze the convergence behavior in terms of data dimensions. Finally, we demonstrate the performance of our algorithm on well-known classification and regression problems, through extensive numerical studies on large-scale datasets, and show that it achieves the highest performance compared to several other widely used and specialized optimization algorithms.
Tasks	Stochastic Optimization
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06686v1
PDF	http://arxiv.org/pdf/1611.06686v1.pdf
PWC	https://paperswithcode.com/paper/scalable-approximations-for-generalized
Repo
Framework

Bibliographic Analysis with the Citation Network Topic Model


Title	Bibliographic Analysis with the Citation Network Topic Model
Authors	Kar Wai Lim, Wray Buntine
Abstract	Bibliographic analysis considers author’s research areas, the citation network and paper content among other things. In this paper, we combine these three in a topic model that produces a bibliographic model of authors, topics and documents using a non-parametric extension of a combination of the Poisson mixed-topic link model and the author-topic model. We propose a novel and efficient inference algorithm for the model to explore subsets of research publications from CiteSeerX. Our model demonstrates improved performance in both model fitting and a clustering task compared to several baselines.
Tasks
Published	2016-09-22
URL	http://arxiv.org/abs/1609.06826v1
PDF	http://arxiv.org/pdf/1609.06826v1.pdf
PWC	https://paperswithcode.com/paper/bibliographic-analysis-with-the-citation
Repo
Framework

Towards Neural Knowledge DNA


Title	Towards Neural Knowledge DNA
Authors	Haoxi Zhang, Cesar Sanin, Edward Szczerbicki
Abstract	In this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicate to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and organisation. It is constructed in a similar fashion of how DNA formed: built up by four essential elements. As the DNA produces phenotypes, the Neural Knowledge DNA carries information and knowledge via its four essential elements, namely, Networks, Experiences, States, and Actions.
Tasks
Published	2016-02-27
URL	http://arxiv.org/abs/1602.08571v1
PDF	http://arxiv.org/pdf/1602.08571v1.pdf
PWC	https://paperswithcode.com/paper/towards-neural-knowledge-dna
Repo
Framework

Single- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016


Title	Single- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016
Authors	Andru P. Twinanda, Didier Mutter, Jacques Marescaux, Michel de Mathelin, Nicolas Padoy
Abstract	The surgical workflow challenge at M2CAI 2016 consists of identifying 8 surgical phases in cholecystectomy procedures. Here, we propose to use deep architectures that are based on our previous work where we presented several architectures to perform multiple recognition tasks on laparoscopic videos. In this technical report, we present the phase recognition results using two architectures: (1) a single-task architecture designed to perform solely the surgical phase recognition task and (2) a multi-task architecture designed to perform jointly phase recognition and tool presence detection. On top of these architectures we propose to use two different approaches to enforce the temporal constraints of the surgical workflow: (1) HMM-based and (2) LSTM-based pipelines. The results show that the LSTM-based approach is able to outperform the HMM-based approach and also to properly enforce the temporal constraints into the recognition process.
Tasks
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08844v2
PDF	http://arxiv.org/pdf/1610.08844v2.pdf
PWC	https://paperswithcode.com/paper/single-and-multi-task-architectures-for-1
Repo
Framework

Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision


Title	Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision
Authors	Dapeng Luo, Zhipeng Zeng, Nong Sang, Xiang Wu, Longsheng Wei, Quanzheng Mou, Jun Cheng, Chen Luo
Abstract	One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many modern approaches model deep hierarchical appearance representations for object detection. Most of these methods require a timeconsuming training process on large manual labelling sample set. In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion. First, a scene-specific objector is obtained from a fully autonomous learning process triggered by marking several bounding boxes around the object in the first video frame via a mouse. Here the human labeled training data or a generic detector are not needed. Second, this learning process is conveniently replicated many times in different surveillance scenes and results in particular detectors under various camera viewpoints. Thus, the proposed framework can be employed in multi-scene object detection applications with minimal supervision. Obviously, the initial scene-specific detector, initialized by several bounding boxes, exhibits poor detection performance and is difficult to improve with traditional online learning algorithm. Consequently, we propose Generative-Discriminative model to partition detection response space and assign each partition an individual descriptor that progressively achieves high classification accuracy. A novel online gradual optimized process is proposed to optimize the Generative-Discriminative model and focus on the hard samples.Experimental results on six video datasets show our approach achieves comparable performance to robust supervised methods, and outperforms the state of the art self-learning methods under varying imaging conditions.
Tasks	Object Detection
Published	2016-11-12
URL	http://arxiv.org/abs/1611.03968v4
PDF	http://arxiv.org/pdf/1611.03968v4.pdf
PWC	https://paperswithcode.com/paper/learning-scene-specific-object-detectors
Repo
Framework

Effects of Additional Data on Bayesian Clustering


Title	Effects of Additional Data on Bayesian Clustering
Authors	Keisuke Yamazaki
Abstract	Hierarchical probabilistic models, such as mixture models, are used for cluster analysis. These models have two types of variables: observable and latent. In cluster analysis, the latent variable is estimated, and it is expected that additional information will improve the accuracy of the estimation of the latent variable. Many proposed learning methods are able to use additional data; these include semi-supervised learning and transfer learning. However, from a statistical point of view, a complex probabilistic model that encompasses both the initial and additional data might be less accurate due to having a higher-dimensional parameter. The present paper presents a theoretical analysis of the accuracy of such a model and clarifies which factor has the greatest effect on its accuracy, the advantages of obtaining additional data, and the disadvantages of increasing the complexity.
Tasks	Transfer Learning
Published	2016-07-13
URL	http://arxiv.org/abs/1607.03574v4
PDF	http://arxiv.org/pdf/1607.03574v4.pdf
PWC	https://paperswithcode.com/paper/effects-of-additional-data-on-bayesian
Repo
Framework

High-resolution LIDAR-based Depth Mapping using Bilateral Filter


Title	High-resolution LIDAR-based Depth Mapping using Bilateral Filter
Authors	C. Premebida, L. Garrote, A. Asvadi, A. Pedro Ribeiro, U. Nunes
Abstract	High resolution depth-maps, obtained by upsampling sparse range data from a 3D-LIDAR, find applications in many fields ranging from sensory perception to semantic segmentation and object detection. Upsampling is often based on combining data from a monocular camera to compensate the low-resolution of a LIDAR. This paper, on the other hand, introduces a novel framework to obtain dense depth-map solely from a single LIDAR point cloud; which is a research direction that has been barely explored. The formulation behind the proposed depth-mapping process relies on local spatial interpolation, using sliding-window (mask) technique, and on the Bilateral Filter (BF) where the variable of interest, the distance from the sensor, is considered in the interpolation problem. In particular, the BF is conveniently modified to perform depth-map upsampling such that the edges (foreground-background discontinuities) are better preserved by means of a proposed method which influences the range-based weighting term. Other methods for spatial upsampling are discussed, evaluated and compared in terms of different error measures. This paper also researches the role of the mask’s size in the performance of the implemented methods. Quantitative and qualitative results from experiments on the KITTI Database, using LIDAR point clouds only, show very satisfactory performance of the approach introduced in this work.
Tasks	Object Detection, Semantic Segmentation
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05614v1
PDF	http://arxiv.org/pdf/1606.05614v1.pdf
PWC	https://paperswithcode.com/paper/high-resolution-lidar-based-depth-mapping
Repo
Framework

Embedding Deep Metric for Person Re-identication A Study Against Large Variations


Title	Embedding Deep Metric for Person Re-identication A Study Against Large Variations
Authors	Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, Stan Z. Li
Abstract	Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)‘s capability of feature extraction. However, the distribution is unknown, so it is difficult to use the geodesic distance when comparing two samples. In practice, the current deep embedding methods use the Euclidean distance for the training and test. On the other hand, the manifold learning methods suggest to use the Euclidean distance in the local range, combining with the graphical relationship between samples, for approximating the geodesic distance. From this point of view, selecting suitable positive i.e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations. In this paper, we propose a novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation. In addition, we improve the learning by a metric weight constraint, so that the learned metric has a better generalization ability. Experiments show that these two strategies are effective in learning robust deep metrics for person re-identification, and accordingly our deep model significantly outperforms the state-of-the-art methods on several benchmarks of person re-identification. Therefore, the study presented in this paper may be useful in inspiring new designs of deep models for person re-identification.
Tasks	Person Re-Identification
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00137v1
PDF	http://arxiv.org/pdf/1611.00137v1.pdf
PWC	https://paperswithcode.com/paper/embedding-deep-metric-for-person-re
Repo
Framework

Populations can be essential in tracking dynamic optima


Title	Populations can be essential in tracking dynamic optima
Authors	Duc-Cuong Dang, Thomas Jansen, Per Kristian Lehre
Abstract	Real-world optimisation problems are often dynamic. Previously good solutions must be updated or replaced due to changes in objectives and constraints. It is often claimed that evolutionary algorithms are particularly suitable for dynamic optimisation because a large population can contain different solutions that may be useful in the future. However, rigorous theoretical demonstrations for how populations in dynamic optimisation can be essential are sparse and restricted to special cases. This paper provides theoretical explanations of how populations can be essential in evolutionary dynamic optimisation in a general and natural setting. We describe a natural class of dynamic optimisation problems where a sufficiently large population is necessary to keep track of moving optima reliably. We establish a relationship between the population-size and the probability that the algorithm loses track of the optimum.
Tasks
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03317v1
PDF	http://arxiv.org/pdf/1607.03317v1.pdf
PWC	https://paperswithcode.com/paper/populations-can-be-essential-in-tracking
Repo
Framework

Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problems


Title	Tradeoffs between Convergence Speed and Reconstruction Accuracy in Inverse Problems
Authors	Raja Giryes, Yonina C. Eldar, Alex M. Bronstein, Guillermo Sapiro
Abstract	Solving inverse problems with iterative algorithms is popular, especially for large data. Due to time constraints, the number of possible iterations is usually limited, potentially affecting the achievable accuracy. Given an error one is willing to tolerate, an important question is whether it is possible to modify the original iterations to obtain faster convergence to a minimizer achieving the allowed error without increasing the computational cost of each iteration considerably. Relying on recent recovery techniques developed for settings in which the desired signal belongs to some low-dimensional set, we show that using a coarse estimate of this set may lead to faster convergence at the cost of an additional reconstruction error related to the accuracy of the set approximation. Our theory ties to recent advances in sparse recovery, compressed sensing, and deep learning. Particularly, it may provide a possible explanation to the successful approximation of the l1-minimization solution by neural networks with layers representing iterations, as practiced in the learned iterative shrinkage-thresholding algorithm (LISTA).
Tasks
Published	2016-05-30
URL	http://arxiv.org/abs/1605.09232v3
PDF	http://arxiv.org/pdf/1605.09232v3.pdf
PWC	https://paperswithcode.com/paper/tradeoffs-between-convergence-speed-and
Repo
Framework

Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics


Title	Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics
Authors	Xiyang Dai, Sameh Khamis, Yangmuzi Zhang, Larry S. Davis
Abstract	Sparse representations have been successfully applied to signal processing, computer vision and machine learning. Currently there is a trend to learn sparse models directly on structure data, such as region covariance. However, such methods when combined with region covariance often require complex computation. We present an approach to transform a structured sparse model learning problem to a traditional vectorized sparse modeling problem by constructing a Euclidean space representation for region covariance matrices. Our new representation has multiple advantages. Experiments on several vision tasks demonstrate competitive performance with the state-of-the-art methods.
Tasks
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02822v1
PDF	http://arxiv.org/pdf/1602.02822v1.pdf
PWC	https://paperswithcode.com/paper/parameterizing-region-covariance-an-efficient
Repo
Framework

Learning Minimum Volume Sets and Anomaly Detectors from KNN Graphs


Title	Learning Minimum Volume Sets and Anomaly Detectors from KNN Graphs
Authors	Jonathan Root, Venkatesh Saligrama, Jing Qian
Abstract	We propose a non-parametric anomaly detection algorithm for high dimensional data. We first rank scores derived from nearest neighbor graphs on $n$-point nominal training data. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as an anomaly at $\alpha$-false alarm level if the predicted score is in the $\alpha$-percentile. The resulting anomaly detector is shown to be asymptotically optimal in that for any false alarm rate $\alpha$, its decision region converges to the $\alpha$-percentile minimum volume level set of the unknown underlying density. In addition, we test both the statistical performance and computational efficiency of our algorithm on a number of synthetic and real-data experiments. Our results demonstrate the superiority of our algorithm over existing $K$-NN based anomaly detection algorithms, with significant computational savings.
Tasks	Anomaly Detection, Learning-To-Rank
Published	2016-01-22
URL	http://arxiv.org/abs/1601.06105v1
PDF	http://arxiv.org/pdf/1601.06105v1.pdf
PWC	https://paperswithcode.com/paper/learning-minimum-volume-sets-and-anomaly
Repo
Framework