July 27, 2019

3095 words 15 mins read

Paper Group ANR 642

Scalable Prototype Selection by Genetic Algorithms and Hashing. A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation. R-Clustering for Egocentric Video Segmentation. Convolutional neural networks for structured omics: OmicsCNN and the OmicsConv layer. Graph-based Isometry Invariant Representation Learning. A Framework for Wassers …

Scalable Prototype Selection by Genetic Algorithms and Hashing


Title	Scalable Prototype Selection by Genetic Algorithms and Hashing
Authors	Yenisel Plasencia-Calaña, Mauricio Orozco-Alzate, Heydi Méndez-Vázquez, Edel García-Reyes, Robert P. W. Duin
Abstract	Classification in the dissimilarity space has become a very active research area since it provides a possibility to learn from data given in the form of pairwise non-metric dissimilarities, which otherwise would be difficult to cope with. The selection of prototypes is a key step for the further creation of the space. However, despite previous efforts to find good prototypes, how to select the best representation set remains an open issue. In this paper we proposed scalable methods to select the set of prototypes out of very large datasets. The methods are based on genetic algorithms, dissimilarity-based hashing, and two different unsupervised and supervised scalable criteria. The unsupervised criterion is based on the Minimum Spanning Tree of the graph created by the prototypes as nodes and the dissimilarities as edges. The supervised criterion is based on counting matching labels of objects and their closest prototypes. The suitability of these type of algorithms is analyzed for the specific case of dissimilarity representations. The experimental results showed that the methods select good prototypes taking advantage of the large datasets, and they do so at low runtimes.
Tasks
Published	2017-12-26
URL	http://arxiv.org/abs/1712.09277v1
PDF	http://arxiv.org/pdf/1712.09277v1.pdf
PWC	https://paperswithcode.com/paper/scalable-prototype-selection-by-genetic
Repo
Framework

A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation


Title	A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation
Authors	Zhuotun Zhu, Yingda Xia, Wei Shen, Elliot K. Fishman, Alan L. Yuille
Abstract	In this paper, we adopt 3D Convolutional Neural Networks to segment volumetric medical images. Although deep neural networks have been proven to be very effective on many 2D vision tasks, it is still challenging to apply them to 3D tasks due to the limited amount of annotated 3D data and limited computational resources. We propose a novel 3D-based coarse-to-fine framework to effectively and efficiently tackle these challenges. The proposed 3D-based framework outperforms the 2D counterpart to a large margin since it can leverage the rich spatial infor- mation along all three axes. We conduct experiments on two datasets which include healthy and pathological pancreases respectively, and achieve the current state-of-the-art in terms of Dice-S{\o}rensen Coefficient (DSC). On the NIH pancreas segmentation dataset, we outperform the previous best by an average of over 2%, and the worst case is improved by 7% to reach almost 70%, which indicates the reliability of our framework in clinical applications.
Tasks	Medical Image Segmentation, Pancreas Segmentation, Semantic Segmentation, Volumetric Medical Image Segmentation
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00201v2
PDF	http://arxiv.org/pdf/1712.00201v2.pdf
PWC	https://paperswithcode.com/paper/a-3d-coarse-to-fine-framework-for-volumetric
Repo
Framework

R-Clustering for Egocentric Video Segmentation


Title	R-Clustering for Egocentric Video Segmentation
Authors	Estefania Talavera, Mariella Dimiccoli, Marc Bolaños, Maedeh Aghaei, Petia Radeva
Abstract	In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework. Given the tendency of most AC methods to oversegment video sequences when clustering their frames, we combine the clustering with a concept drift detection technique (ADWIN) that has rigorous guarantee of performances. ADWIN serves as a statistical upper bound for the clustering-based video segmentation. We integrate both techniques in an energy-minimization framework that serves to disambiguate the decision of both techniques and to complete the segmentation taking into account the temporal continuity of video frames descriptors. We present experiments over egocentric sets of more than 13.000 images acquired with different wearable cameras, showing that our method outperforms state-of-the-art clustering methods.
Tasks	Video Semantic Segmentation
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02809v1
PDF	http://arxiv.org/pdf/1704.02809v1.pdf
PWC	https://paperswithcode.com/paper/r-clustering-for-egocentric-video
Repo
Framework

Convolutional neural networks for structured omics: OmicsCNN and the OmicsConv layer


Title	Convolutional neural networks for structured omics: OmicsCNN and the OmicsConv layer
Authors	Giuseppe Jurman, Valerio Maggio, Diego Fioravanti, Ylenia Giarratano, Isotta Landi, Margherita Francescatto, Claudio Agostinelli, Marco Chierici, Manlio De Domenico, Cesare Furlanello
Abstract	Convolutional Neural Networks (CNNs) are a popular deep learning architecture widely applied in different domains, in particular in classifying over images, for which the concept of convolution with a filter comes naturally. Unfortunately, the requirement of a distance (or, at least, of a neighbourhood function) in the input feature space has so far prevented its direct use on data types such as omics data. However, a number of omics data are metrizable, i.e., they can be endowed with a metric structure, enabling to adopt a convolutional based deep learning framework, e.g., for prediction. We propose a generalized solution for CNNs on omics data, implemented through a dedicated Keras layer. In particular, for metagenomics data, a metric can be derived from the patristic distance on the phylogenetic tree. For transcriptomics data, we combine Gene Ontology semantic similarity and gene co-expression to define a distance; the function is defined through a multilayer network where 3 layers are defined by the GO mutual semantic similarity while the fourth one by gene co-expression. As a general tool, feature distance on omics data is enabled by OmicsConv, a novel Keras layer, obtaining OmicsCNN, a dedicated deep learning framework. Here we demonstrate OmicsCNN on gut microbiota sequencing data, for Inflammatory Bowel Disease (IBD) 16S data, first on synthetic data and then a metagenomics collection of gut microbiota of 222 IBD patients.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05918v1
PDF	http://arxiv.org/pdf/1710.05918v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-structured
Repo
Framework

Graph-based Isometry Invariant Representation Learning


Title	Graph-based Isometry Invariant Representation Learning
Authors	Renata Khasanova, Pascal Frossard
Abstract	Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have achieved only limited success in the classification of images that undergo geometric transformations. In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images. In particular, images are represented as signals on graphs, which permits to replace classical convolution and pooling layers in deep networks with graph spectral convolution and dynamic graph pooling layers that together contribute to invariance to isometric transformations. Our experiments show high performance on rotated and translated images from the test set compared to classical architectures that are very sensitive to transformations in the data. The inherent invariance properties of our framework provide key advantages, such as increased resiliency to data variability and sustained performance with limited training sets.
Tasks	Representation Learning, Video Classification
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00356v1
PDF	http://arxiv.org/pdf/1703.00356v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-isometry-invariant-representation
Repo
Framework

A Framework for Wasserstein-1-Type Metrics


Title	A Framework for Wasserstein-1-Type Metrics
Authors	Bernhard Schmitzer, Benedikt Wirth
Abstract	We propose a unifying framework for generalising the Wasserstein-1 metric to a discrepancy measure between nonnegative measures of different mass. This generalization inherits the convexity and computational efficiency from the Wasserstein-1 metric, and it includes several previous approaches from the literature as special cases. For various specific instances of the generalized Wasserstein-1 metric we furthermore demonstrate their usefulness in applications by numerical experiments.
Tasks
Published	2017-01-08
URL	http://arxiv.org/abs/1701.01945v2
PDF	http://arxiv.org/pdf/1701.01945v2.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-wasserstein-1-type-metrics
Repo
Framework

Translation of “Zur Ermittlung eines Objektes aus zwei Perspektiven mit innerer Orientierung” by Erwin Kruppa (1913)


Title	Translation of “Zur Ermittlung eines Objektes aus zwei Perspektiven mit innerer Orientierung” by Erwin Kruppa (1913)
Authors	Guillermo Gallego, Elias Mueggler, Peter Sturm
Abstract	Erwin Kruppa’s 1913 paper, Erwin Kruppa, “Zur Ermittlung eines Objektes aus zwei Perspektiven mit innerer Orientierung”, Sitzungsberichte der Mathematisch-Naturwissenschaftlichen Kaiserlichen Akademie der Wissenschaften, Vol. 122 (1913), pp. 1939-1948, which may be translated as “To determine a 3D object from two perspective views with known inner orientation”, is a landmark paper in Computer Vision because it provides the first five-point algorithm for relative pose estimation. Kruppa showed that (a finite number of solutions for) the relative pose between two calibrated images of a rigid object can be computed from five point matches between the images. Kruppa’s work also gained attention in the topic of camera self-calibration, as presented in (Maybank and Faugeras, 1992). Since the paper is still relevant today (more than a hundred citations within the last ten years) and the paper is not available online, we ordered a copy from the German National Library in Frankfurt and provide an English translation along with the German original. We also adapt the terminology to a modern jargon and provide some clarifications (highlighted in sans-serif font). For a historical review of geometric computer vision, the reader is referred to the recent survey paper (Sturm, 2011).
Tasks	Calibration, Pose Estimation
Published	2017-12-25
URL	http://arxiv.org/abs/1801.01454v1
PDF	http://arxiv.org/pdf/1801.01454v1.pdf
PWC	https://paperswithcode.com/paper/translation-of-zur-ermittlung-eines-objektes
Repo
Framework

GPU-Accelerated Algorithms for Compressed Signals Recovery with Application to Astronomical Imagery Deblurring


Title	GPU-Accelerated Algorithms for Compressed Signals Recovery with Application to Astronomical Imagery Deblurring
Authors	Attilio Fiandrotti, Sophie M. Fosson, Chiara Ravazzi, Enrico Magli
Abstract	Compressive sensing promises to enable bandwidth-efficient on-board compression of astronomical data by lifting the encoding complexity from the source to the receiver. The signal is recovered off-line, exploiting GPUs parallel computation capabilities to speedup the reconstruction process. However, inherent GPU hardware constraints limit the size of the recoverable signal and the speedup practically achievable. In this work, we design parallel algorithms that exploit the properties of circulant matrices for efficient GPU-accelerated sparse signals recovery. Our approach reduces the memory requirements, allowing us to recover very large signals with limited memory. In addition, it achieves a tenfold signal recovery speedup thanks to ad-hoc parallelization of matrix-vector multiplications and matrix inversions. Finally, we practically demonstrate our algorithms in a typical application of circulant matrices: deblurring a sparse astronomical image in the compressed domain.
Tasks	Compressive Sensing, Deblurring
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02244v1
PDF	http://arxiv.org/pdf/1707.02244v1.pdf
PWC	https://paperswithcode.com/paper/gpu-accelerated-algorithms-for-compressed
Repo
Framework

Mitigating Asymmetric Nonlinear Weight Update Effects in Hardware Neural Network based on Analog Resistive Synapse


Title	Mitigating Asymmetric Nonlinear Weight Update Effects in Hardware Neural Network based on Analog Resistive Synapse
Authors	Chih-Cheng Chang, Pin-Chun Chen, Teyuh Chou, I-Ting Wang, Boris Hudec, Che-Chia Chang, Chia-Ming Tsai, Tian-Sheuan Chang, Tuo-Hung Hou
Abstract	Asymmetric nonlinear weight update is considered as one of the major obstacles for realizing hardware neural networks based on analog resistive synapses because it significantly compromises the online training capability. This paper provides new solutions to this critical issue through co-optimization with the hardware-applicable deep-learning algorithms. New insights on engineering activation functions and a threshold weight update scheme effectively suppress the undesirable training noise induced by inaccurate weight update. We successfully trained a two-layer perceptron network online and improved the classification accuracy of MNIST handwritten digit dataset to 87.8/94.8% by using 6-bit/8-bit analog synapses, respectively, with extremely high asymmetric nonlinearity.
Tasks
Published	2017-12-16
URL	http://arxiv.org/abs/1712.05895v1
PDF	http://arxiv.org/pdf/1712.05895v1.pdf
PWC	https://paperswithcode.com/paper/mitigating-asymmetric-nonlinear-weight-update
Repo
Framework

Inference of Spatio-Temporal Functions over Graphs via Multi-Kernel Kriged Kalman Filtering


Title	Inference of Spatio-Temporal Functions over Graphs via Multi-Kernel Kriged Kalman Filtering
Authors	Vassilis N. Ioannidis, Daniel Romero, Georgios B. Giannakis
Abstract	Inference of space-time varying signals on graphs emerges naturally in a plethora of network science related applications. A frequently encountered challenge pertains to reconstructing such dynamic processes, given their values over a subset of vertices and time instants. The present paper develops a graph-aware kernel-based kriged Kalman filter that accounts for the spatio-temporal variations, and offers efficient online reconstruction, even for dynamically evolving network topologies. The kernel-based learning framework bypasses the need for statistical information by capitalizing on the smoothness that graph signals exhibit with respect to the underlying graph. To address the challenge of selecting the appropriate kernel, the proposed filter is combined with a multi-kernel selection module. Such a data-driven method selects a kernel attuned to the signal dynamics on-the-fly within the linear span of a pre-selected dictionary. The novel multi-kernel learning algorithm exploits the eigenstructure of Laplacian kernel matrices to reduce computational complexity. Numerical tests with synthetic and real data demonstrate the superior reconstruction performance of the novel approach relative to state-of-the-art alternatives.
Tasks
Published	2017-11-25
URL	http://arxiv.org/abs/1711.09306v1
PDF	http://arxiv.org/pdf/1711.09306v1.pdf
PWC	https://paperswithcode.com/paper/inference-of-spatio-temporal-functions-over
Repo
Framework

Generalizing the Role of Determinization in Probabilistic Planning


Title	Generalizing the Role of Determinization in Probabilistic Planning
Authors	Luis Pineda, Shlomo Zilberstein
Abstract	The stochastic shortest path problem (SSP) is a highly expressive model for probabilistic planning. The computational hardness of SSPs has sparked interest in determinization-based planners that can quickly solve large problems. However, existing methods employ a simplistic approach to determinization. In particular, they ignore the possibility of tailoring the determinization to the specific characteristics of the target domain. In this work we examine this question, by showing that learning a good determinization for a planning domain can be done efficiently and can improve performance. Moreover, we show how to directly incorporate probabilistic reasoning into the planning problem when a good determinization is not sufficient by itself. Based on these insights, we introduce a planner, FF-LAO*, that outperforms state-of-the-art probabilistic planners on several well-known competition benchmarks.
Tasks
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07381v2
PDF	http://arxiv.org/pdf/1705.07381v2.pdf
PWC	https://paperswithcode.com/paper/generalizing-the-role-of-determinization-in
Repo
Framework

Modeling preference time in middle distance triathlons


Title	Modeling preference time in middle distance triathlons
Authors	Iztok Fister, Andres Iglesias, Suash Deb, Dušan Fister, Iztok Fister Jr
Abstract	Modeling preference time in triathlons means predicting the intermediate times of particular sports disciplines by a given overall finish time in a specific triathlon course for the athlete with the known personal best result. This is a hard task for athletes and sport trainers due to a lot of different factors that need to be taken into account, e.g., athlete’s abilities, health, mental preparations and even their current sports form. So far, this process was calculated manually without any specific software tools or using the artificial intelligence. This paper presents the new solution for modeling preference time in middle distance triathlons based on particle swarm optimization algorithm and archive of existing sports results. Initial results are presented, which suggest the usefulness of proposed approach, while remarks for future improvements and use are also emphasized.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00718v1
PDF	http://arxiv.org/pdf/1707.00718v1.pdf
PWC	https://paperswithcode.com/paper/modeling-preference-time-in-middle-distance
Repo
Framework

A data set for evaluating the performance of multi-class multi-object video tracking


Title	A data set for evaluating the performance of multi-class multi-object video tracking
Authors	Avishek Chakraborty, Victor Stamatescu, Sebastien C. Wong, Grant Wigley, David Kearney
Abstract	One of the challenges in evaluating multi-object video detection, tracking and classification systems is having publically available data sets with which to compare different systems. However, the measures of performance for tracking and classification are different. Data sets that are suitable for evaluating tracking systems may not be appropriate for classification. Tracking video data sets typically only have ground truth track IDs, while classification video data sets only have ground truth class-label IDs. The former identifies the same object over multiple frames, while the latter identifies the type of object in individual frames. This paper describes an advancement of the ground truth meta-data for the DARPA Neovision2 Tower data set to allow both the evaluation of tracking and classification. The ground truth data sets presented in this paper contain unique object IDs across 5 different classes of object (Car, Bus, Truck, Person, Cyclist) for 24 videos of 871 image frames each. In addition to the object IDs and class labels, the ground truth data also contains the original bounding box coordinates together with new bounding boxes in instances where un-annotated objects were present. The unique IDs are maintained during occlusions between multiple objects or when objects re-enter the field of view. This will provide: a solid foundation for evaluating the performance of multi-object tracking of different types of objects, a straightforward comparison of tracking system performance using the standard Multi Object Tracking (MOT) framework, and classification performance using the Neovision2 metrics. These data have been hosted publically.
Tasks	Multi-Object Tracking, Object Tracking
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06378v1
PDF	http://arxiv.org/pdf/1704.06378v1.pdf
PWC	https://paperswithcode.com/paper/a-data-set-for-evaluating-the-performance-of
Repo
Framework

Second-Order Kernel Online Convex Optimization with Adaptive Sketching


Title	Second-Order Kernel Online Convex Optimization with Adaptive Sketching
Authors	Daniele Calandriello, Alessandro Lazaric, Michal Valko
Abstract	Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO methods such as functional gradient descent require only $\mathcal{O}(t)$ time and space per iteration, and, when the only information on the losses is their convexity, achieve a minimax optimal $\mathcal{O}(\sqrt{T})$ regret. Nonetheless, many common losses in kernel problems, such as squared loss, logistic loss, and squared hinge loss posses stronger curvature that can be exploited. In this case, second-order KOCO methods achieve $\mathcal{O}(\log(\text{Det}(\boldsymbol{K})))$ regret, which we show scales as $\mathcal{O}(d_{\text{eff}}\log T)$, where $d_{\text{eff}}$ is the effective dimension of the problem and is usually much smaller than $\mathcal{O}(\sqrt{T})$. The main drawback of second-order methods is their much higher $\mathcal{O}(t^2)$ space and time complexity. In this paper, we introduce kernel online Newton step (KONS), a new second-order KOCO method that also achieves $\mathcal{O}(d_{\text{eff}}\log T)$ regret. To address the computational complexity of second-order methods, we introduce a new matrix sketching algorithm for the kernel matrix $\boldsymbol{K}_t$, and show that for a chosen parameter $\gamma \leq 1$ our Sketched-KONS reduces the space and time complexity by a factor of $\gamma^2$ to $\mathcal{O}(t^2\gamma^2)$ space and time per iteration, while incurring only $1/\gamma$ times more regret.
Tasks
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04892v1
PDF	http://arxiv.org/pdf/1706.04892v1.pdf
PWC	https://paperswithcode.com/paper/second-order-kernel-online-convex
Repo
Framework

Deep Memory Networks for Attitude Identification


Title	Deep Memory Networks for Attitude Identification
Authors	Cheng Li, Xiaoxiao Guo, Qiaozhu Mei
Abstract	We consider the task of identifying attitudes towards a given set of entities from text. Conventionally, this task is decomposed into two separate subtasks: target detection that identifies whether each entity is mentioned in the text, either explicitly or implicitly, and polarity classification that classifies the exact sentiment towards an identified entity (the target) into positive, negative, or neutral. Instead, we show that attitude identification can be solved with an end-to-end machine learning architecture, in which the two subtasks are interleaved by a deep memory network. In this way, signals produced in target detection provide clues for polarity classification, and reversely, the predicted polarity provides feedback to the identification of targets. Moreover, the treatments for the set of targets also influence each other – the learned representations may share the same semantics for some targets but vary for others. The proposed deep memory network, the AttNet, outperforms methods that do not consider the interactions between the subtasks or those among the targets, including conventional machine learning methods and the state-of-the-art deep learning models.
Tasks
Published	2017-01-16
URL	http://arxiv.org/abs/1701.04189v1
PDF	http://arxiv.org/pdf/1701.04189v1.pdf
PWC	https://paperswithcode.com/paper/deep-memory-networks-for-attitude
Repo
Framework