May 7, 2019

2987 words 15 mins read

Paper Group ANR 125

Blind Deconvolution of PET Images using Anatomical Priors. Field-Programmable Crossbar Array (FPCA) for Reconfigurable Computing. Robust nonparametric nearest neighbor random process clustering. Similarity Learning for Time Series Classification. PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning. Multiple Instanc …


Title	Blind Deconvolution of PET Images using Anatomical Priors
Authors	Stéphanie Guérit, Adriana González, Anne Bol, John A. Lee, Laurent Jacques
Abstract	Images from positron emission tomography (PET) provide metabolic information about the human body. They present, however, a spatial resolution that is limited by physical and instrumental factors often modeled by a blurring function. Since this function is typically unknown, blind deconvolution (BD) techniques are needed in order to produce a useful restored PET image. In this work, we propose a general BD technique that restores a low resolution blurry image using information from data acquired with a high resolution modality (e.g., CT-based delineation of regions with uniform activity in PET images). The proposed BD method is validated on synthetic and actual phantoms.
Tasks
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01896v1
PDF	http://arxiv.org/pdf/1608.01896v1.pdf
PWC	https://paperswithcode.com/paper/blind-deconvolution-of-pet-images-using
Repo
Framework

Field-Programmable Crossbar Array (FPCA) for Reconfigurable Computing


Title	Field-Programmable Crossbar Array (FPCA) for Reconfigurable Computing
Authors	Mohammed A. Zidan, YeonJoo Jeong, Jong Hong Shin, Chao Du, Zhengya Zhang, Wei D. Lu
Abstract	For decades, advances in electronics were directly driven by the scaling of CMOS transistors according to Moore’s law. However, both the CMOS scaling and the classical computer architecture are approaching fundamental and practical limits, and new computing architectures based on emerging devices, such as resistive random-access memory (RRAM) devices, are expected to sustain the exponential growth of computing capability. Here we propose a novel memory-centric, reconfigurable, general purpose computing platform that is capable of handling the explosive amount of data in a fast and energy-efficient manner. The proposed computing architecture is based on a uniform, physical, resistive, memory-centric fabric that can be optimally reconfigured and utilized to perform different computing and data storage tasks in a massively parallel approach. The system can be tailored to achieve maximal energy efficiency based on the data flow by dynamically allocating the basic computing fabric for storage, arithmetic, and analog computing including neuromorphic computing tasks.
Tasks
Published	2016-12-09
URL	http://arxiv.org/abs/1612.02913v4
PDF	http://arxiv.org/pdf/1612.02913v4.pdf
PWC	https://paperswithcode.com/paper/field-programmable-crossbar-array-fpca-for
Repo
Framework

Robust nonparametric nearest neighbor random process clustering


Title	Robust nonparametric nearest neighbor random process clustering
Authors	Michael Tschannen, Helmut Bölcskei
Abstract	We consider the problem of clustering noisy finite-length observations of stationary ergodic random processes according to their generative models without prior knowledge of the model statistics and the number of generative models. Two algorithms, both using the $L^1$-distance between estimated power spectral densities (PSDs) as a measure of dissimilarity, are analyzed. The first one, termed nearest neighbor process clustering (NNPC), relies on partitioning the nearest neighbor graph of the observations via spectral clustering. The second algorithm, simply referred to as $k$-means (KM), consists of a single $k$-means iteration with farthest point initialization and was considered before in the literature, albeit with a different dissimilarity measure. We prove that both algorithms succeed with high probability in the presence of noise and missing entries, and even when the generative process PSDs overlap significantly, all provided that the observation length is sufficiently large. Our results quantify the tradeoff between the overlap of the generative process PSDs, the observation length, the fraction of missing entries, and the noise variance. Finally, we provide extensive numerical results for synthetic and real data and find that NNPC outperforms state-of-the-art algorithms in human motion sequence clustering.
Tasks
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01103v3
PDF	http://arxiv.org/pdf/1612.01103v3.pdf
PWC	https://paperswithcode.com/paper/robust-nonparametric-nearest-neighbor-random
Repo
Framework

Similarity Learning for Time Series Classification


Title	Similarity Learning for Time Series Classification
Authors	Maria-Irina Nicolae, Éric Gaussier, Amaury Habrard, Marc Sebban
Abstract	Multivariate time series naturally exist in many fields, like energy, bioinformatics, signal processing, and finance. Most of these applications need to be able to compare these structured data. In this context, dynamic time warping (DTW) is probably the most common comparison measure. However, not much research effort has been put into improving it by learning. In this paper, we propose a novel method for learning similarities based on DTW, in order to improve time series classification. Making use of the uniform stability framework, we provide the first theoretical guarantees in the form of a generalization bound for linear classification. The experimental study shows that the proposed approach is efficient, while yielding sparse classifiers.
Tasks	Time Series, Time Series Classification
Published	2016-10-15
URL	http://arxiv.org/abs/1610.04783v1
PDF	http://arxiv.org/pdf/1610.04783v1.pdf
PWC	https://paperswithcode.com/paper/similarity-learning-for-time-series
Repo
Framework

PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning


Title	PIGMIL: Positive Instance Detection via Graph Updating for Multiple Instance Learning
Authors	Dongkuan Xu, Jia Wu, Wei Zhang, Yingjie Tian
Abstract	Positive instance detection, especially for these in positive bags (true positive instances, TPIs), plays a key role for multiple instance learning (MIL) arising from a specific classification problem only provided with bag (a set of instances) label information. However, most previous MIL methods on this issue ignore the global similarity among positive instances and that negative instances are non-i.i.d., usually resulting in the detection of TPI not precise and sensitive to outliers. To the end, we propose a positive instance detection via graph updating for multiple instance learning, called PIGMIL, to detect TPI accurately. PIGMIL selects instances from working sets (WSs) of some working bags (WBs) as positive candidate pool (PCP). The global similarity among positive instances and the robust discrimination of instances of PCP from negative instances are measured to construct the consistent similarity and discrimination graph (CSDG). As a result, the primary goal (i.e. TPI detection) is transformed into PCP updating, which is approximated efficiently by updating CSDG with a random walk ranking algorithm and an instance updating strategy. At last bags are transformed into feature representation vector based on the identified TPIs to train a classifier. Extensive experiments demonstrate the high precision of PIGMIL’s detection of TPIs and its excellent performance compared to classic baseline MIL methods.
Tasks	Multiple Instance Learning
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03550v1
PDF	http://arxiv.org/pdf/1612.03550v1.pdf
PWC	https://paperswithcode.com/paper/pigmil-positive-instance-detection-via-graph
Repo
Framework

Multiple Instance Learning: A Survey of Problem Characteristics and Applications


Title	Multiple Instance Learning: A Survey of Problem Characteristics and Applications
Authors	Marc-André Carbonneau, Veronika Cheplygina, Eric Granger, Ghyslain Gagnon
Abstract	Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits various problems and allows to leverage weakly labeled data. Consequently, it has been used in diverse application fields such as computer vision and document classification. However, learning from bags raises important challenges that are unique to MIL. This paper provides a comprehensive survey of the characteristics which define and differentiate the types of MIL problems. Until now, these problem characteristics have not been formally identified and described. As a result, the variations in performance of MIL algorithms from one data set to another are difficult to explain. In this paper, MIL problem characteristics are grouped into four broad categories: the composition of the bags, the types of data distribution, the ambiguity of instance labels, and the task to be performed. Methods specialized to address each category are reviewed. Then, the extent to which these characteristics manifest themselves in key MIL application areas are described. Finally, experiments are conducted to compare the performance of 16 state-of-the-art MIL methods on selected problem characteristics. This paper provides insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.
Tasks	Document Classification, Multiple Instance Learning
Published	2016-12-11
URL	http://arxiv.org/abs/1612.03365v1
PDF	http://arxiv.org/pdf/1612.03365v1.pdf
PWC	https://paperswithcode.com/paper/multiple-instance-learning-a-survey-of
Repo
Framework

Learning Time Series Detection Models from Temporally Imprecise Labels


Title	Learning Time Series Detection Models from Temporally Imprecise Labels
Authors	Roy J. Adams, Benjamin M. Marlin
Abstract	In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels. In this problem, the data consist of a set of input time series, and supervision is provided by a sequence of noisy time stamps corresponding to the occurrence of positive class events. Such temporally imprecise labels commonly occur in areas like mobile health research where human annotators are tasked with labeling the occurrence of very short duration events. We propose a general learning framework for this problem that can accommodate different base classifiers and noise models. We present results on real mobile health data showing that the proposed framework significantly outperforms a number of alternatives including assuming that the label time stamps are noise-free, transforming the problem into the multiple instance learning framework, and learning on labels that were manually re-aligned.
Tasks	Multiple Instance Learning, Time Series
Published	2016-11-07
URL	http://arxiv.org/abs/1611.02258v2
PDF	http://arxiv.org/pdf/1611.02258v2.pdf
PWC	https://paperswithcode.com/paper/learning-time-series-detection-models-from
Repo
Framework

Fast Adaptation in Generative Models with Generative Matching Networks


Title	Fast Adaptation in Generative Models with Generative Matching Networks
Authors	Sergey Bartunov, Dmitry P. Vetrov
Abstract	Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called Generative Matching Network which is inspired by the recently proposed matching networks for one-shot learning in discriminative tasks. By conditioning on the additional input dataset, our model can instantly learn new concepts that were not available in the training data but conform to a similar generative process. The proposed framework does not explicitly restrict diversity of the conditioning data and also does not require an extensive inference procedure for training or adaptation. Our experiments on the Omniglot dataset demonstrate that Generative Matching Networks significantly improve predictive performance on the fly as more additional data is available and outperform existing state of the art conditional generative models.
Tasks	Omniglot, One-Shot Learning
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02192v2
PDF	http://arxiv.org/pdf/1612.02192v2.pdf
PWC	https://paperswithcode.com/paper/fast-adaptation-in-generative-models-with
Repo
Framework

Multiple Instance Fuzzy Inference Neural Networks


Title	Multiple Instance Fuzzy Inference Neural Networks
Authors	Amine Ben Khalifa, Hichem Frigui
Abstract	Fuzzy logic is a powerful tool to model knowledge uncertainty, measurements imprecision, and vagueness. However, there is another type of vagueness that arises when data have multiple forms of expression that fuzzy logic does not address quite well. This is the case for multiple instance learning problems (MIL). In MIL, an object is represented by a collection of instances, called a bag. A bag is labeled negative if all of its instances are negative, and positive if at least one of its instances is positive. Positive bags encode ambiguity since the instances themselves are not labeled. In this paper, we introduce fuzzy inference systems and neural networks designed to handle bags of instances as input and capable of learning from ambiguously labeled data. First, we introduce the Multiple Instance Sugeno style fuzzy inference (MI-Sugeno) that extends the standard Sugeno style inference to handle reasoning with multiple instances. Second, we use MI-Sugeno to define and develop Multiple Instance Adaptive Neuro Fuzzy Inference System (MI-ANFIS). We expand the architecture of the standard ANFIS to allow reasoning with bags and derive a learning algorithm using backpropagation to identify the premise and consequent parameters of the network. The proposed inference system is tested and validated using synthetic and benchmark datasets suitable for MIL problems. We also apply the proposed MI-ANFIS to fuse the output of multiple discrimination algorithms for the purpose of landmine detection using Ground Penetrating Radar.
Tasks	Multiple Instance Learning
Published	2016-10-17
URL	http://arxiv.org/abs/1610.04973v1
PDF	http://arxiv.org/pdf/1610.04973v1.pdf
PWC	https://paperswithcode.com/paper/multiple-instance-fuzzy-inference-neural
Repo
Framework

Empirical Evaluation of RNN Architectures on Sentence Classification Task


Title	Empirical Evaluation of RNN Architectures on Sentence Classification Task
Authors	Lei Shen, Junlin Zhang
Abstract	Recurrent Neural Networks have achieved state-of-the-art results for many problems in NLP and two most popular RNN architectures are Tail Model and Pooling Model. In this paper, a hybrid architecture is proposed and we present the first empirical study using LSTMs to compare performance of the three RNN structures on sentence classification task. Experimental results show that the Max Pooling Model or Hybrid Max Pooling Model achieves the best performance on most datasets, while Tail Model does not outperform other models.
Tasks	Sentence Classification
Published	2016-09-29
URL	http://arxiv.org/abs/1609.09171v2
PDF	http://arxiv.org/pdf/1609.09171v2.pdf
PWC	https://paperswithcode.com/paper/empirical-evaluation-of-rnn-architectures-on
Repo
Framework

Distributed Iterative Learning Control for a Team of Quadrotors


Title	Distributed Iterative Learning Control for a Team of Quadrotors
Authors	Andreas Hock, Angela P. Schoellig
Abstract	The goal of this work is to enable a team of quadrotors to learn how to accurately track a desired trajectory while holding a given formation. We solve this problem in a distributed manner, where each vehicle has only access to the information of its neighbors. The desired trajectory is only available to one (or few) vehicles. We present a distributed iterative learning control (ILC) approach where each vehicle learns from the experience of its own and its neighbors’ previous task repetitions, and adapts its feedforward input to improve performance. Existing algorithms are extended in theory to make them more applicable to real-world experiments. In particular, we prove stability for any causal learning function with gains chosen according to a simple scalar condition. Previous proofs were restricted to a specific learning function that only depends on the tracking error derivative (D-type ILC). Our extension provides more degrees of freedom in the ILC design and, as a result, better performance can be achieved. We also show that stability is not affected by a linear dynamic coupling between neighbors. This allows us to use an additional consensus feedback controller to compensate for non-repetitive disturbances. Experiments with two quadrotors attest the effectiveness of the proposed distributed multi-agent ILC approach. This is the first work to show distributed ILC in experiment.
Tasks
Published	2016-03-18
URL	http://arxiv.org/abs/1603.05933v2
PDF	http://arxiv.org/pdf/1603.05933v2.pdf
PWC	https://paperswithcode.com/paper/distributed-iterative-learning-control-for-a
Repo
Framework

Fast color transfer from multiple images


Title	Fast color transfer from multiple images
Authors	Asad Khan, Luo Jiang, Wei Li, Ligang Liu
Abstract	Color transfer between images uses the statistics information of image effectively. We present a novel approach of local color transfer between images based on the simple statistics and locally linear embedding. A sketching interface is proposed for quickly and easily specifying the color correspondences between target and source image. The user can specify the correspondences of local region using scribes, which more accurately transfers the target color to the source image while smoothly preserving the boundaries, and exhibits more natural output results. Our algorithm is not restricted to one-to-one image color transfer and can make use of more than one target images to transfer the color in different regions in the source image. Moreover, our algorithm does not require to choose the same color style and image size between source and target images. We propose the sub-sampling to reduce the computational load. Comparing with other approaches, our algorithm is much better in color blending in the input data. Our approach preserves the other color details in the source image. Various experimental results show that our approach specifies the correspondences of local color region in source and target images. And it expresses the intention of users and generates more actual and natural results of visual effect.
Tasks
Published	2016-12-28
URL	http://arxiv.org/abs/1612.08927v1
PDF	http://arxiv.org/pdf/1612.08927v1.pdf
PWC	https://paperswithcode.com/paper/fast-color-transfer-from-multiple-images
Repo
Framework

Semi-supervised K-means++


Title	Semi-supervised K-means++
Authors	Jordan Yoder, Carey E. Priebe
Abstract	Traditionally, practitioners initialize the {\tt k-means} algorithm with centers chosen uniformly at random. Randomized initialization with uneven weights ({\tt k-means++}) has recently been used to improve the performance over this strategy in cost and run-time. We consider the k-means problem with semi-supervised information, where some of the data are pre-labeled, and we seek to label the rest according to the minimum cost solution. By extending the {\tt k-means++} algorithm and analysis to account for the labels, we derive an improved theoretical bound on expected cost and observe improved performance in simulated and real data examples. This analysis provides theoretical justification for a roughly linear semi-supervised clustering algorithm.
Tasks
Published	2016-02-01
URL	http://arxiv.org/abs/1602.00360v1
PDF	http://arxiv.org/pdf/1602.00360v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-k-means
Repo
Framework

A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation


Title	A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation
Authors	Jayadev Acharya, Hirakendu Das, Alon Orlitsky, Ananda Theertha Suresh
Abstract	The advent of data science has spurred interest in estimating properties of distributions over large alphabets. Fundamental symmetric properties such as support size, support coverage, entropy, and proximity to uniformity, received most attention, with each property estimated using a different technique and often intricate analysis tools. We prove that for all these properties, a single, simple, plug-in estimator—profile maximum likelihood (PML)—performs as well as the best specialized techniques. This raises the possibility that PML may optimally estimate many other symmetric properties.
Tasks
Published	2016-11-09
URL	http://arxiv.org/abs/1611.02960v2
PDF	http://arxiv.org/pdf/1611.02960v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-maximum-likelihood-approach-for
Repo
Framework

Oriented bounding boxes using multiresolution contours for fast interference detection of arbitrary geometry objects


Title	Oriented bounding boxes using multiresolution contours for fast interference detection of arbitrary geometry objects
Authors	L. A. Rivera, Vania V. Estrela, P. C. P. Carvalho
Abstract	Interference detection of arbitrary geometric objects is not a trivial task due to the heavy computational load imposed by implementation issues. The hierarchically structured bounding boxes help us to quickly isolate the contour of segments in interference. In this paper, a new approach is introduced to treat the interference detection problem involving the representation of arbitrary shaped objects. Our proposed method relies upon searching for the best possible way to represent contours by means of hierarchically structured rectangular oriented bounding boxes. This technique handles 2D objects boundaries defined by closed B-spline curves with roughness details. Each oriented box is adapted and fitted to the segments of the contour using second order statistical indicators from some elements of the segments of the object contour in a multiresolution framework. Our method is efficient and robust when it comes to 2D animations in real time. It can deal with smooth curves and polygonal approximations as well results are present to illustrate the performance of the new method.
Tasks
Published	2016-11-11
URL	http://arxiv.org/abs/1611.03666v1
PDF	http://arxiv.org/pdf/1611.03666v1.pdf
PWC	https://paperswithcode.com/paper/oriented-bounding-boxes-using-multiresolution
Repo
Framework