May 6, 2019

3293 words 16 mins read

Paper Group ANR 296

Robust Non-linear Regression: A Greedy Approach Employing Kernels with Application to Image Denoising. Fundamental Matrices from Moving Objects Using Line Motion Barcodes. Resource Sharing for Multi-Tenant NoSQL Data Store in Cloud. Language Detection For Short Text Messages In Social Media. Unsupervised Semantic Action Discovery from Video Collect …

Robust Non-linear Regression: A Greedy Approach Employing Kernels with Application to Image Denoising


Title	Robust Non-linear Regression: A Greedy Approach Employing Kernels with Application to Image Denoising
Authors	George Papageorgiou, Pantelis Bouboulis, Sergios Theodoridis
Abstract	We consider the task of robust non-linear regression in the presence of both inlier noise and outliers. Assuming that the unknown non-linear function belongs to a Reproducing Kernel Hilbert Space (RKHS), our goal is to estimate the set of the associated unknown parameters. Due to the presence of outliers, common techniques such as the Kernel Ridge Regression (KRR) or the Support Vector Regression (SVR) turn out to be inadequate. Instead, we employ sparse modeling arguments to explicitly model and estimate the outliers, adopting a greedy approach. The proposed robust scheme, i.e., Kernel Greedy Algorithm for Robust Denoising (KGARD), is inspired by the classical Orthogonal Matching Pursuit (OMP) algorithm. Specifically, the proposed method alternates between a KRR task and an OMP-like selection step. Theoretical results concerning the identification of the outliers are provided. Moreover, KGARD is compared against other cutting edge methods, where its performance is evaluated via a set of experiments with various types of noise. Finally, the proposed robust estimation framework is applied to the task of image denoising, and its enhanced performance in the presence of outliers is demonstrated.
Tasks	Denoising, Image Denoising
Published	2016-01-04
URL	http://arxiv.org/abs/1601.00595v2
PDF	http://arxiv.org/pdf/1601.00595v2.pdf
PWC	https://paperswithcode.com/paper/robust-non-linear-regression-a-greedy
Repo
Framework

Fundamental Matrices from Moving Objects Using Line Motion Barcodes


Title	Fundamental Matrices from Moving Objects Using Line Motion Barcodes
Authors	Yoni Kasten, Gil Ben-Artzi, Shmuel Peleg, Michael Werman
Abstract	Computing the epipolar geometry between cameras with very different viewpoints is often very difficult. The appearance of objects can vary greatly, and it is difficult to find corresponding feature points. Prior methods searched for corresponding epipolar lines using points on the convex hull of the silhouette of a single moving object. These methods fail when the scene includes multiple moving objects. This paper extends previous work to scenes having multiple moving objects by using the “Motion Barcodes”, a temporal signature of lines. Corresponding epipolar lines have similar motion barcodes, and candidate pairs of corresponding epipoar lines are found by the similarity of their motion barcodes. As in previous methods we assume that cameras are relatively stationary and that moving objects have already been extracted using background subtraction.
Tasks
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07660v1
PDF	http://arxiv.org/pdf/1607.07660v1.pdf
PWC	https://paperswithcode.com/paper/fundamental-matrices-from-moving-objects
Repo
Framework


Title	Resource Sharing for Multi-Tenant NoSQL Data Store in Cloud
Authors	Jiaan Zeng
Abstract	Multi-tenancy hosting of users in cloud NoSQL data stores is favored by cloud providers because it enables resource sharing at low operating cost. Multi-tenancy takes several forms depending on whether the back-end file system is a local file system (LFS) or a parallel file system (PFS), and on whether tenants are independent or share data across tenants. In this thesis I focus on and propose solutions to two cases: independent data-local file system, and shared data-parallel file system. In the independent data-local file system case, resource contention occurs under certain conditions in Cassandra and HBase, two state-of-the-art NoSQL stores, causing performance degradation for one tenant by another. We investigate the interference and propose two approaches. The first provides a scheduling scheme that can approximate resource consumption, adapt to workload dynamics and work in a distributed fashion. The second introduces a workload-aware resource reservation approach to prevent interference. The approach relies on a performance model obtained offline and plans the reservation according to different workload resource demands. Results show the approaches together can prevent interference and adapt to dynamic workloads under multi-tenancy. In the shared data-parallel file system case, it has been shown that running a distributed NoSQL store over PFS for shared data across tenants is not cost effective. Overheads are introduced due to the unawareness of the NoSQL store of PFS. This dissertation targets the key-value store (KVS), a specific form of NoSQL stores, and proposes a lightweight KVS over a parallel file system to improve efficiency. The solution is built on an embedded KVS for high performance but uses novel data structures to support concurrent writes. Results show the proposed system outperforms Cassandra and Voldemort in several different workloads.
Tasks
Published	2016-01-05
URL	http://arxiv.org/abs/1601.00738v1
PDF	http://arxiv.org/pdf/1601.00738v1.pdf
PWC	https://paperswithcode.com/paper/resource-sharing-for-multi-tenant-nosql-data
Repo
Framework


Title	Language Detection For Short Text Messages In Social Media
Authors	Ivana Balazevic, Mikio Braun, Klaus-Robert Müller
Abstract	With the constant growth of the World Wide Web and the number of documents in different languages accordingly, the need for reliable language detection tools has increased as well. Platforms such as Twitter with predominantly short texts are becoming important information resources, which additionally imposes the need for short texts language detection algorithms. In this paper, we show how incorporating personalized user-specific information into the language detection algorithm leads to an important improvement of detection results. To choose the best algorithm for language detection for short text messages, we investigate several machine learning approaches. These approaches include the use of the well-known classifiers such as SVM and logistic regression, a dictionary based approach, and a probabilistic model based on modified Kneser-Ney smoothing. Furthermore, the extension of the probabilistic model to include additional user-specific information such as evidence accumulation per user and user interface language is explored, with the goal of improving the classification performance. The proposed approaches are evaluated on randomly collected Twitter data containing Latin as well as non-Latin alphabet languages and the quality of the obtained results is compared, followed by the selection of the best performing algorithm. This algorithm is then evaluated against two already existing general language detection tools: Chromium Compact Language Detector 2 (CLD2) and langid, where our method significantly outperforms the results achieved by both of the mentioned methods. Additionally, a preview of benefits and possible applications of having a reliable language detection algorithm is given.
Tasks
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08515v1
PDF	http://arxiv.org/pdf/1608.08515v1.pdf
PWC	https://paperswithcode.com/paper/language-detection-for-short-text-messages-in
Repo
Framework

Unsupervised Semantic Action Discovery from Video Collections


Title	Unsupervised Semantic Action Discovery from Video Collections
Authors	Ozan Sener, Amir Roshan Zamir, Chenxia Wu, Silvio Savarese, Ashutosh Saxena
Abstract	Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic “storyline” of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate our method on a large number of complex YouTube videos and show that our method discovers semantically correct instructions for a variety of tasks.
Tasks
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03324v1
PDF	http://arxiv.org/pdf/1605.03324v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-semantic-action-discovery-from
Repo
Framework

Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models


Title	Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
Authors	Marcello Benedetti, John Realpe-Gómez, Rupak Biswas, Alejandro Perdomo-Ortiz
Abstract	Mainstream machine-learning techniques such as deep learning and probabilistic programming rely heavily on sampling from generally intractable probability distributions. There is increasing interest in the potential advantages of using quantum computing technologies as sampling engines to speed up these tasks or to make them more effective. However, some pressing challenges in state-of-the-art quantum annealers have to be overcome before we can assess their actual performance. The sparse connectivity, resulting from the local interaction between quantum bits in physical hardware implementations, is considered the most severe limitation to the quality of constructing powerful generative unsupervised machine-learning models. Here we use embedding techniques to add redundancy to data sets, allowing us to increase the modeling capacity of quantum annealers. We illustrate our findings by training hardware-embedded graphical models on a binarized data set of handwritten digits and two synthetic data sets in experiments with up to 940 quantum bits. Our model can be trained in quantum hardware without full knowledge of the effective parameters specifying the corresponding quantum Gibbs-like distribution; therefore, this approach avoids the need to infer the effective temperature at each iteration, speeding up learning; it also mitigates the effect of noise in the control parameters, making it robust to deviations from the reference Gibbs distribution. Our approach demonstrates the feasibility of using quantum annealers for implementing generative models, and it provides a suitable framework for benchmarking these quantum technologies on machine-learning-related tasks.
Tasks	Probabilistic Programming
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02542v4
PDF	http://arxiv.org/pdf/1609.02542v4.pdf
PWC	https://paperswithcode.com/paper/quantum-assisted-learning-of-hardware
Repo
Framework

On the usability of deep networks for object-based image analysis


Title	On the usability of deep networks for object-based image analysis
Authors	Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre
Abstract	As computer vision before, remote sensing has been radically changed by the introduction of Convolution Neural Networks. Land cover use, object detection and scene understanding in aerial images rely more and more on deep learning to achieve new state-of-the-art results. Recent architectures such as Fully Convolutional Networks (Long et al., 2015) can even produce pixel level annotations for semantic mapping. In this work, we show how to use such deep networks to detect, segment and classify different varieties of wheeled vehicles in aerial images from the ISPRS Potsdam dataset. This allows us to tackle object detection and classification on a complex dataset made up of visually similar classes, and to demonstrate the relevance of such a subclass modeling approach. Especially, we want to show that deep learning is also suitable for object-oriented analysis of Earth Observation data. First, we train a FCN variant on the ISPRS Potsdam dataset and show how the learnt semantic maps can be used to extract precise segmentation of vehicles, which allow us studying the repartition of vehicles in the city. Second, we train a CNN to perform vehicle classification on the VEDAI (Razakarivony and Jurie, 2016) dataset, and transfer its knowledge to classify candidate segmented vehicles on the Potsdam dataset.
Tasks	Object Detection, Scene Understanding
Published	2016-09-22
URL	http://arxiv.org/abs/1609.06845v1
PDF	http://arxiv.org/pdf/1609.06845v1.pdf
PWC	https://paperswithcode.com/paper/on-the-usability-of-deep-networks-for-object
Repo
Framework

Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level


Title	Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level
Authors	Rie Johnson, Tong Zhang
Abstract	This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016). Our findings are as follows. The shallow word-level CNNs achieve better error rates than the error rates reported in Conneau et al., though the results should be interpreted with some consideration due to the unique pre-processing of Conneau et al. The shallow word-level CNN uses more parameters and therefore requires more storage than the deep character-level CNN; however, the shallow word-level CNN computes much faster.
Tasks	Text Categorization
Published	2016-08-31
URL	http://arxiv.org/abs/1609.00718v1
PDF	http://arxiv.org/pdf/1609.00718v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-text
Repo
Framework

High Dimensional Multivariate Regression and Precision Matrix Estimation via Nonconvex Optimization


Title	High Dimensional Multivariate Regression and Precision Matrix Estimation via Nonconvex Optimization
Authors	Jinghui Chen, Quanquan Gu
Abstract	We propose a nonconvex estimator for joint multivariate regression and precision matrix estimation in the high dimensional regime, under sparsity constraints. A gradient descent algorithm with hard thresholding is developed to solve the nonconvex estimator, and it attains a linear rate of convergence to the true regression coefficients and precision matrix simultaneously, up to the statistical error. Compared with existing methods along this line of research, which have little theoretical guarantee, the proposed algorithm not only is computationally much more efficient with provable convergence guarantee, but also attains the optimal finite sample statistical rate up to a logarithmic factor. Thorough experiments on both synthetic and real datasets back up our theory.
Tasks
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00832v1
PDF	http://arxiv.org/pdf/1606.00832v1.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-multivariate-regression-and
Repo
Framework

Multi-objective design of quantum circuits using genetic programming


Title	Multi-objective design of quantum circuits using genetic programming
Authors	Moein Sarvaghad-Moghaddam
Abstract	Quantum computing is a new way of data processing based on the concept of quantum mechanics. Quantum circuit design is a process of converting a quantum gate to a series of basic gates and is divided into two general categories based on the decomposition and composition. In the second group, using evolutionary algorithms and especially genetic algorithms, multiplication of matrix gates was used to achieve the final characteristic of quantum circuit. Genetic programming is a subfield of evolutionary computing in which computer programs evolve to solve studied problems. In past research that has been done in the field of quantum circuits design, only one cost metrics (usually quantum cost) has been investigated. In this paper for the first time, a multi-objective approach has been provided to design quantum circuits using genetic programming that considers the depth and the cost of nearest neighbor metrics in addition to quantum cost metric. Another innovation of this article is the use of two-step fitness function and taking into account the equivalence of global phase in quantum gates. The results show that the proposed method is able to find a good answer in a short time.
Tasks
Published	2016-04-03
URL	http://arxiv.org/abs/1604.00642v3
PDF	http://arxiv.org/pdf/1604.00642v3.pdf
PWC	https://paperswithcode.com/paper/multi-objective-design-of-quantum-circuits
Repo
Framework

Less is more: zero-shot learning from online textual documents with noise suppression


Title	Less is more: zero-shot learning from online textual documents with noise suppression
Authors	Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton van den Hengel
Abstract	Classifying a visual concept merely from its associated online textual source, such as a Wikipedia article, is an attractive research topic in zero-shot learning because it alleviates the burden of manually collecting semantic attributes. Several recent works have pursued this approach by exploring various ways of connecting the visual and text domains. This paper revisits this idea by stepping further to consider one important factor: the textual representation is usually too noisy for the zero-shot learning application. This consideration motivates us to design a simple-but-effective zero-shot learning method capable of suppressing noise in the text. More specifically, we propose an $l_{2,1}$-norm based objective function which can simultaneously suppress the noisy signal in the text and learn a function to match the text document and visual features. We also develop an optimization algorithm to efficiently solve the resulting problem. By conducting experiments on two large datasets, we demonstrate that the proposed method significantly outperforms the competing methods which rely on online information sources but without explicit noise suppression. We further make an in-depth analysis of the proposed method and provide insight as to what kind of information in documents is useful for zero-shot learning.
Tasks	Zero-Shot Learning
Published	2016-04-05
URL	http://arxiv.org/abs/1604.01146v1
PDF	http://arxiv.org/pdf/1604.01146v1.pdf
PWC	https://paperswithcode.com/paper/less-is-more-zero-shot-learning-from-online
Repo
Framework

A hybrid approach based segmentation technique for brain tumor in MRI Images


Title	A hybrid approach based segmentation technique for brain tumor in MRI Images
Authors	D. Anithadevi, K. Perumal
Abstract	Automatic image segmentation becomes very crucial for tumor detection in medical image processing.In general, manual and semi automatic segmentation techniques require more time and knowledge. However these drawbacks had overcome by automatic segmentation still there needs to develop more appropriate techniques for medical image segmentation. Therefore, we proposed hybrid approach based image segmentation using the combined features of region growing and threshold based segmentation techniques. It is followed by pre-processing stage to provide an accurate brain tumor extraction by the help of Magnetic Resonance Imaging (MRI). If the tumor has holes, the region growing segmentation algorithm cannot reveal but the proposed hybrid segmentation technique can be achieved and the result as well improved. Hence the result used to made assessment with the various performance measures as DICE, JACCARD similarity, accuracy, sensitivity and specificity. These similarity measures have been extensively used for evaluation with the ground truth of each processed image and its results are compared and analyzed.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02447v1
PDF	http://arxiv.org/pdf/1603.02447v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-approach-based-segmentation
Repo
Framework

Predictive Coarse-Graining


Title	Predictive Coarse-Graining
Authors	Markus Schöberl, Nicholas Zabaras, Phaedon-Stelios Koutsourelakis
Abstract	We propose a data-driven, coarse-graining formulation in the context of equilibrium statistical mechanics. In contrast to existing techniques which are based on a fine-to-coarse map, we adopt the opposite strategy by prescribing a probabilistic coarse-to-fine map. This corresponds to a directed probabilistic model where the coarse variables play the role of latent generators of the fine scale (all-atom) data. From an information-theoretic perspective, the framework proposed provides an improvement upon the relative entropy method and is capable of quantifying the uncertainty due to the information loss that unavoidably takes place during the CG process. Furthermore, it can be readily extended to a fully Bayesian model where various sources of uncertainties are reflected in the posterior of the model parameters. The latter can be used to produce not only point estimates of fine-scale reconstructions or macroscopic observables, but more importantly, predictive posterior distributions on these quantities. Predictive posterior distributions reflect the confidence of the model as a function of the amount of data and the level of coarse-graining. The issues of model complexity and model selection are seamlessly addressed by employing a hierarchical prior that favors the discovery of sparse solutions, revealing the most prominent features in the coarse-grained model. A flexible and parallelizable Monte Carlo - Expectation-Maximization (MC-EM) scheme is proposed for carrying out inference and learning tasks. A comparative assessment of the proposed methodology is presented for a lattice spin system and the SPC/E water model.
Tasks	Model Selection
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08301v2
PDF	http://arxiv.org/pdf/1605.08301v2.pdf
PWC	https://paperswithcode.com/paper/predictive-coarse-graining
Repo
Framework

Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation


Title	Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
Authors	Huiling Wang, Tapani Raiko, Lasse Lensu, Tinghuai Wang, Juha Karhunen
Abstract	Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the existing pretrained CNN image recognition model for video segmentation task can severely hurt performance. We propose a semi-supervised approach to adapting CNN image recognition model trained from labeled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of video data. By explicitly modeling and compensating for the domain shift from the source domain to the target domain, this proposed approach underpins a robust semantic object segmentation method against the changes in appearance, shape and occlusion in natural videos. We present extensive experiments on challenging datasets that demonstrate the superior performance of our approach compared with the state-of-the-art methods.
Tasks	Domain Adaptation, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02280v1
PDF	http://arxiv.org/pdf/1606.02280v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-domain-adaptation-for-weakly
Repo
Framework

How to Allocate Resources For Features Acquisition?


Title	How to Allocate Resources For Features Acquisition?
Authors	Oran Richman, Shie Mannor
Abstract	We study classification problems where features are corrupted by noise and where the magnitude of the noise in each feature is influenced by the resources allocated to its acquisition. This is the case, for example, when multiple sensors share a common resource (power, bandwidth, attention, etc.). We develop a method for computing the optimal resource allocation for a variety of scenarios and derive theoretical bounds concerning the benefit that may arise by non-uniform allocation. We further demonstrate the effectiveness of the developed method in simulations.
Tasks
Published	2016-07-10
URL	http://arxiv.org/abs/1607.02763v1
PDF	http://arxiv.org/pdf/1607.02763v1.pdf
PWC	https://paperswithcode.com/paper/how-to-allocate-resources-for-features
Repo
Framework