Paper Group ANR 516
Accelerated Variance Reduced Block Coordinate Descent. Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching. A globally-applicable disease ontology for biosurveillance; Anthology of Biosurveillance Diseases (ABD). From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generator …
Accelerated Variance Reduced Block Coordinate Descent
| Title | Accelerated Variance Reduced Block Coordinate Descent |
| Authors | Zebang Shen, Hui Qian, Chao Zhang, Tengfei Zhou |
| Abstract | Algorithms with fast convergence, small number of data access, and low per-iteration complexity are particularly favorable in the big data era, due to the demand for obtaining \emph{highly accurate solutions} to problems with \emph{a large number of samples} in \emph{ultra-high} dimensional space. Existing algorithms lack at least one of these qualities, and thus are inefficient in handling such big data challenge. In this paper, we propose a method enjoying all these merits with an accelerated convergence rate $O(\frac{1}{k^2})$. Empirical studies on large scale datasets with more than one million features are conducted to show the effectiveness of our methods in practice. |
| Tasks | |
| Published | 2016-11-13 |
| URL | http://arxiv.org/abs/1611.04149v1 |
| http://arxiv.org/pdf/1611.04149v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-variance-reduced-block-coordinate |
| Repo | |
| Framework | |
Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching
| Title | Identifying Designs from Incomplete, Fragmented Cultural Heritage Objects by Curve-Pattern Matching |
| Authors | Jun Zhou, Haozhou Yu, Karen Smith, Colin Wilder, Hongkai Yu, Song Wang |
| Abstract | Study of cultural-heritage objects with embellished realistic and abstract designs made up of connected and intertwined curves crosscuts a number of related disciplines, including archaeology, art history, and heritage management. However, many objects, such as pottery sherds found in the archaeological record, are fragmentary, making the underlying complete designs unknowable at the scale of the sherd fragment. The challenge to reconstruct and study complete designs is stymied because 1) most fragmentary cultural-heritage objects contain only a small portion of the underlying full design, 2) in the case of a stamping application, the same design may be applied multiple times with spatial overlap on one object, and 3) curve patterns detected on an object are usually incomplete and noisy. As a result, classical curve-pattern matching algorithms, such as Chamfer matching, may perform poorly in identifying the underlying design. In this paper, we develop a new partial-to-global curve matching algorithm to address these challenges and better identify the full design from a fragmented cultural heritage object. Specifically, we develop the algorithm to identify the designs of the carved wooden paddles of the Southeastern Woodlands from unearthed pottery sherds. A set of pottery sherds from the Snow Collection, curated at Georgia Southern University, are used to test the proposed algorithm, with promising results. |
| Tasks | |
| Published | 2016-08-05 |
| URL | http://arxiv.org/abs/1608.02023v2 |
| http://arxiv.org/pdf/1608.02023v2.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-designs-from-incomplete |
| Repo | |
| Framework | |
A globally-applicable disease ontology for biosurveillance; Anthology of Biosurveillance Diseases (ABD)
| Title | A globally-applicable disease ontology for biosurveillance; Anthology of Biosurveillance Diseases (ABD) |
| Authors | A. R. Daughton, R. Priedhorsky, G. Fairchild, N. Generous, A. Hengartner, E. Abeyta, N. Velappan, A. Lillo, K. Stark, A. Deshpande |
| Abstract | Biosurveillance, a relatively young field, has recently increased in importance because of its relevance to national security and global health. Databases and tools describing particular subsets of disease are becoming increasingly common in the field. However, a common method to describe those diseases is lacking. Here, we present the Anthology of Biosurveillance Diseases (ABD), an ontology of infectious diseases of biosurveillance relevance. |
| Tasks | |
| Published | 2016-08-25 |
| URL | http://arxiv.org/abs/1609.05774v1 |
| http://arxiv.org/pdf/1609.05774v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-globally-applicable-disease-ontology-for |
| Repo | |
| Framework | |
From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
| Title | From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators |
| Authors | Paul Upchurch, Noah Snavely, Kavita Bala |
| Abstract | We propose a new neural network architecture for solving single-image analogies - the generation of an entire set of stylistically similar images from just a single input image. Solving this problem requires separating image style from content. Our network is a modified variational autoencoder (VAE) that supports supervised training of single-image analogies and in-network evaluation of outputs with a structured similarity objective that captures pixel covariances. On the challenging task of generating a 62-letter font from a single example letter we produce images with 22.4% lower dissimilarity to the ground truth than state-of-the-art. |
| Tasks | |
| Published | 2016-03-07 |
| URL | http://arxiv.org/abs/1603.02003v1 |
| http://arxiv.org/pdf/1603.02003v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-a-to-z-supervised-transfer-of-style-and |
| Repo | |
| Framework | |
Wisdom of Crowds cluster ensemble
| Title | Wisdom of Crowds cluster ensemble |
| Authors | Hosein Alizadeh, Muhammad Yousefnezhad, Behrouz Minaei Bidgoli |
| Abstract | The Wisdom of Crowds is a phenomenon described in social science that suggests four criteria applicable to groups of people. It is claimed that, if these criteria are satisfied, then the aggregate decisions made by a group will often be better than those of its individual members. Inspired by this concept, we present a novel feedback framework for the cluster ensemble problem, which we call Wisdom of Crowds Cluster Ensemble (WOCCE). Although many conventional cluster ensemble methods focusing on diversity have recently been proposed, WOCCE analyzes the conditions necessary for a crowd to exhibit this collective wisdom. These include decentralization criteria for generating primary results, independence criteria for the base algorithms, and diversity criteria for the ensemble members. We suggest appropriate procedures for evaluating these measures, and propose a new measure to assess the diversity. We evaluate the performance of WOCCE against some other traditional base algorithms as well as state-of-the-art ensemble methods. The results demonstrate the efficiency of WOCCE’s aggregate decision-making compared to other algorithms. |
| Tasks | Decision Making |
| Published | 2016-05-13 |
| URL | http://arxiv.org/abs/1605.04074v1 |
| http://arxiv.org/pdf/1605.04074v1.pdf | |
| PWC | https://paperswithcode.com/paper/wisdom-of-crowds-cluster-ensemble |
| Repo | |
| Framework | |
Sparse Representation-Based Classification: Orthogonal Least Squares or Orthogonal Matching Pursuit?
| Title | Sparse Representation-Based Classification: Orthogonal Least Squares or Orthogonal Matching Pursuit? |
| Authors | Minshan Cui, Saurabh Prasad |
| Abstract | Spare representation of signals has received significant attention in recent years. Based on these developments, a sparse representation-based classification (SRC) has been proposed for a variety of classification and related tasks, including face recognition. Recently, a class dependent variant of SRC was proposed to overcome the limitations of SRC for remote sensing image classification. Traditionally, greedy pursuit based method such as orthogonal matching pursuit (OMP) are used for sparse coefficient recovery due to their simplicity as well as low time-complexity. However, orthogonal least square (OLS) has not yet been widely used in classifiers that exploit the sparse representation properties of data. Since OLS produces lower signal reconstruction error than OMP under similar conditions, we hypothesize that more accurate signal estimation will further improve the classification performance of classifiers that exploiting the sparsity of data. In this paper, we present a classification method based on OLS, which implements OLS in a classwise manner to perform the classification. We also develop and present its kernelized variant to handle nonlinearly separable data. Based on two real-world benchmarking hyperspectral datasets, we demonstrate that class dependent OLS based methods outperform several baseline methods including traditional SRC and the support vector machine classifier. |
| Tasks | Face Recognition, Image Classification, Remote Sensing Image Classification, Sparse Representation-based Classification |
| Published | 2016-07-18 |
| URL | http://arxiv.org/abs/1607.04942v1 |
| http://arxiv.org/pdf/1607.04942v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-representation-based-classification |
| Repo | |
| Framework | |
OnionNet: Sharing Features in Cascaded Deep Classifiers
| Title | OnionNet: Sharing Features in Cascaded Deep Classifiers |
| Authors | Martin Simonovsky, Nikos Komodakis |
| Abstract | The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples. We propose to replace a monolithic network with our novel cascade of feature-sharing deep classifiers, called OnionNet, where subsequent stages may add both new layers as well as new feature channels to the previous ones. Importantly, intermediate feature maps are shared among classifiers, preventing them from the necessity of being recomputed. To accomplish this, the model is trained end-to-end in a principled way under a joint loss. We validate our approach in theory and on a synthetic benchmark. As a result demonstrated in three applications (patch matching, object detection, and image retrieval), our cascade can operate significantly faster than both monolithic networks and traditional cascades without sharing at the cost of marginal decrease in precision. |
| Tasks | Image Retrieval, Object Detection |
| Published | 2016-08-09 |
| URL | http://arxiv.org/abs/1608.02728v1 |
| http://arxiv.org/pdf/1608.02728v1.pdf | |
| PWC | https://paperswithcode.com/paper/onionnet-sharing-features-in-cascaded-deep |
| Repo | |
| Framework | |
A new recurrent neural network based predictive model for Faecal Calprotectin analysis: A retrospective study
| Title | A new recurrent neural network based predictive model for Faecal Calprotectin analysis: A retrospective study |
| Authors | Zeeshan Khawar Malik, Zain U. Hussain, Ziad Kobti, Charlie W. Lees, Newton Howard, Amir Hussain |
| Abstract | Faecal Calprotectin (FC) is a surrogate marker for intestinal inflammation, termed Inflammatory Bowel Disease (IBD), but not for cancer. In this retrospective study of 804 patients, an enhanced benchmark predictive model for analyzing FC is developed, based on a novel state-of-the-art Echo State Network (ESN), an advanced dynamic recurrent neural network which implements a biologically plausible architecture, and a supervised learning mechanism. The proposed machine learning driven predictive model is benchmarked against a conventional logistic regression model, demonstrating statistically significant performance improvements. |
| Tasks | |
| Published | 2016-12-17 |
| URL | http://arxiv.org/abs/1612.05794v1 |
| http://arxiv.org/pdf/1612.05794v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-recurrent-neural-network-based |
| Repo | |
| Framework | |
The Matrix Generalized Inverse Gaussian Distribution: Properties and Applications
| Title | The Matrix Generalized Inverse Gaussian Distribution: Properties and Applications |
| Authors | Farideh Fazayeli, Arindam Banerjee |
| Abstract | While the Matrix Generalized Inverse Gaussian ($\mathcal{MGIG}$) distribution arises naturally in some settings as a distribution over symmetric positive semi-definite matrices, certain key properties of the distribution and effective ways of sampling from the distribution have not been carefully studied. In this paper, we show that the $\mathcal{MGIG}$ is unimodal, and the mode can be obtained by solving an Algebraic Riccati Equation (ARE) equation [7]. Based on the property, we propose an importance sampling method for the $\mathcal{MGIG}$ where the mode of the proposal distribution matches that of the target. The proposed sampling method is more efficient than existing approaches [32, 33], which use proposal distributions that may have the mode far from the $\mathcal{MGIG}$'s mode. Further, we illustrate that the the posterior distribution in latent factor models, such as probabilistic matrix factorization (PMF) [25], when marginalized over one latent factor has the $\mathcal{MGIG}$ distribution. The characterization leads to a novel Collapsed Monte Carlo (CMC) inference algorithm for such latent factor models. We illustrate that CMC has a lower log loss or perplexity than MCMC, and needs fewer samples. |
| Tasks | |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03463v2 |
| http://arxiv.org/pdf/1604.03463v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-matrix-generalized-inverse-gaussian |
| Repo | |
| Framework | |
Person Re-identification with Hyperspectral Multi-Camera Systems — A Pilot Study
| Title | Person Re-identification with Hyperspectral Multi-Camera Systems — A Pilot Study |
| Authors | Saurabh Prasad, Tanu Priya, Minshan Cui, Shishir Shah |
| Abstract | Person re-identification in a multi-camera environment is an important part of modern surveillance systems. Person re-identification from color images has been the focus of much active research, due to the numerous challenges posed with such analysis tasks, such as variations in illumination, pose and viewpoints. In this paper, we suggest that hyperspectral imagery has the potential to provide unique information that is expected to be beneficial for the re-identification task. Specifically, we assert that by accurately characterizing the unique spectral signature for each person’s skin, hyperspectral imagery can provide very useful descriptors (e.g. spectral signatures from skin pixels) for re-identification. Towards this end, we acquired proof-of-concept hyperspectral re-identification data under challenging (practical) conditions from 15 people. Our results indicate that hyperspectral data result in a substantially enhanced re-identification performance compared to color (RGB) images, when using spectral signatures over skin as the feature descriptor. |
| Tasks | Person Re-Identification |
| Published | 2016-07-15 |
| URL | http://arxiv.org/abs/1607.04609v1 |
| http://arxiv.org/pdf/1607.04609v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-with-hyperspectral |
| Repo | |
| Framework | |
Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
| Title | Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection |
| Authors | Youbao Tang, Xiangqian Wu, Wei Bu |
| Abstract | This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global, and contextual information of salient objects is important to obtain a high quality salient map. To achieve this goal, the DSRCNN is designed based on VGGNet-16. Firstly, the recurrent connections are incorporated into each convolutional layer, which can make the model more powerful for learning the contextual information. Secondly, side-output layers are added to conduct the deeply-supervised operation, which can make the model learn more discriminative and robust features by effecting the intermediate layers. Finally, all of the side-outputs are fused to integrate the local and global information to get the final saliency detection results. Therefore, the DSRCNN combines the advantages of recurrent convolutional neural networks and deeply-supervised nets. The DSRCNN model is tested on five benchmark datasets, and experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art saliency detection approaches on all test datasets. |
| Tasks | Saliency Detection, Saliency Prediction |
| Published | 2016-08-18 |
| URL | http://arxiv.org/abs/1608.05177v1 |
| http://arxiv.org/pdf/1608.05177v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeply-supervised-recurrent-convolutional |
| Repo | |
| Framework | |
Zero-shot object prediction using semantic scene knowledge
| Title | Zero-shot object prediction using semantic scene knowledge |
| Authors | Rene Grzeszick, Gernot A. Fink |
| Abstract | This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These scenarios are referred to as zero-shot or few-shot recognition and often build on visual attributes. Here, instead of relying on various visual attributes, a more direct way is pursued: after recognizing the scene that is depicted in an image, semantic relations between scenes and objects are used for predicting the presence of objects in an unsupervised manner. Most importantly, relations between scenes and objects can easily be obtained from external sources such as large scale text corpora from the web and, therefore, do not require tremendous manual labeling efforts. It will be shown that in cluttered scenes, where visual recognition is difficult, scene knowledge is an important cue for predicting objects. |
| Tasks | Object Recognition |
| Published | 2016-04-27 |
| URL | http://arxiv.org/abs/1604.07952v3 |
| http://arxiv.org/pdf/1604.07952v3.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-object-prediction-using-semantic |
| Repo | |
| Framework | |
Extended Object Tracking: Introduction, Overview and Applications
| Title | Extended Object Tracking: Introduction, Overview and Applications |
| Authors | Karl Granstrom, Marcus Baum, Stephan Reuter |
| Abstract | This article provides an elaborate overview of current research in extended object tracking. We provide a clear definition of the extended object tracking problem and discuss its delimitation to other types of object tracking. Next, different aspects of extended object modelling are extensively discussed. Subsequently, we give a tutorial introduction to two basic and well used extended object tracking approaches - the random matrix approach and the Kalman filter-based approach for star-convex shapes. The next part treats the tracking of multiple extended objects and elaborates how the large number of feasible association hypotheses can be tackled using both Random Finite Set (RFS) and Non-RFS multi-object trackers. The article concludes with a summary of current applications, where four example applications involving camera, X-band radar, light detection and ranging (lidar), red-green-blue-depth (RGB-D) sensors are highlighted. |
| Tasks | Object Tracking |
| Published | 2016-03-14 |
| URL | http://arxiv.org/abs/1604.00970v3 |
| http://arxiv.org/pdf/1604.00970v3.pdf | |
| PWC | https://paperswithcode.com/paper/extended-object-tracking-introduction |
| Repo | |
| Framework | |
Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition
| Title | Salient Region Detection and Segmentation in Images using Dynamic Mode Decomposition |
| Authors | Sikha O K, Sachin Kumar S, K P Soman |
| Abstract | Visual Saliency is the capability of vision system to select distinctive parts of scene and reduce the amount of visual data that need to be processed. The presentpaper introduces (1) a novel approach to detect salient regions by considering color and luminance based saliency scores using Dynamic Mode Decomposition (DMD), (2) a new interpretation to use DMD approach in static image processing. This approach integrates two data analysis methods: (1) Fourier Transform, (2) Principle Component Analysis.The key idea of our work is to create a color based saliency map. This is based on the observation thatsalient part of an image usually have distinct colors compared to the remaining portion of the image. We have exploited the power of different color spaces to model the complex and nonlinear behavior of human visual system to generate a color based saliency map. To further improve the effect of final saliency map, weutilized luminance information exploiting the fact that human eye is more sensitive towards brightness than color.The experimental results shows that our method based on DMD theory is effective in comparison with previous state-of-art saliency estimation approaches. The approach presented in this paperis evaluated using ROC curve, F-measure rate, Precision-Recall rate, AUC score etc. |
| Tasks | Saliency Prediction |
| Published | 2016-07-11 |
| URL | http://arxiv.org/abs/1607.03021v1 |
| http://arxiv.org/pdf/1607.03021v1.pdf | |
| PWC | https://paperswithcode.com/paper/salient-region-detection-and-segmentation-in |
| Repo | |
| Framework | |
Founded Semantics and Constraint Semantics of Logic Rules
| Title | Founded Semantics and Constraint Semantics of Logic Rules |
| Authors | Yanhong A. Liu, Scott D. Stoller |
| Abstract | Logic rules and inference are fundamental in computer science and have been studied extensively. However, prior semantics of logic languages can have subtle implications and can disagree significantly, on even very simple programs, including in attempting to solve the well-known Russell’s paradox. These semantics are often non-intuitive and hard-to-understand when unrestricted negation is used in recursion. This paper describes a simple new semantics for logic rules, founded semantics, and its straightforward extension to another simple new semantics, constraint semantics, that unify the core of different prior semantics. The new semantics support unrestricted negation, as well as unrestricted existential and universal quantifications. They are uniquely expressive and intuitive by allowing assumptions about the predicates, rules, and reasoning to be specified explicitly, as simple and precise binary choices. They are completely declarative and relate cleanly to prior semantics. In addition, founded semantics can be computed in linear time in the size of the ground program. |
| Tasks | |
| Published | 2016-06-20 |
| URL | https://arxiv.org/abs/1606.06269v4 |
| https://arxiv.org/pdf/1606.06269v4.pdf | |
| PWC | https://paperswithcode.com/paper/founded-semantics-and-constraint-semantics-of |
| Repo | |
| Framework | |
