July 29, 2019

2790 words 14 mins read

Paper Group ANR 151

Signal reconstruction via operator guiding. Bayesian Additive Adaptive Basis Tensor Product Models for Modeling High Dimensional Surfaces: An application to high-throughput toxicity testing. Unsupervised Domain Adaptation with Similarity Learning. External Evaluation of Event Extraction Classifiers for Automatic Pathway Curation: An extended study …

Signal reconstruction via operator guiding


Title	Signal reconstruction via operator guiding
Authors	Andrew Knyazev, Alexander Malyshev
Abstract	Signal reconstruction from a sample using an orthogonal projector onto a guiding subspace is theoretically well justified, but may be difficult to practically implement. We propose more general guiding operators, which increase signal components in the guiding subspace relative to those in a complementary subspace, e.g., iterative low-pass edge-preserving filters for super-resolution of images. Two examples of super-resolution illustrate our technology: a no-flash RGB photo guided using a high resolution flash RGB photo, and a depth image guided using a high resolution RGB photo.
Tasks	Super-Resolution
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03493v1
PDF	http://arxiv.org/pdf/1705.03493v1.pdf
PWC	https://paperswithcode.com/paper/signal-reconstruction-via-operator-guiding
Repo
Framework

Bayesian Additive Adaptive Basis Tensor Product Models for Modeling High Dimensional Surfaces: An application to high-throughput toxicity testing


Title	Bayesian Additive Adaptive Basis Tensor Product Models for Modeling High Dimensional Surfaces: An application to high-throughput toxicity testing
Authors	Matthew W. Wheeler
Abstract	Many modern data sets are sampled with error from complex high-dimensional surfaces. Methods such as tensor product splines or Gaussian processes are effective/well suited for characterizing a surface in two or three dimensions but may suffer from difficulties when representing higher dimensional surfaces. Motivated by high throughput toxicity testing where observed dose-response curves are cross sections of a surface defined by a chemical’s structural properties, a model is developed to characterize this surface to predict untested chemicals’ dose-responses. This manuscript proposes a novel approach that models the multidimensional surface as a sum of learned basis functions formed as the tensor product of lower dimensional functions, which are themselves representable by a basis expansion learned from the data. The model is described, a Gibbs sampling algorithm proposed, and is investigated in a simulation study as well as data taken from the US EPA’s ToxCast high throughput toxicity testing platform.
Tasks	Gaussian Processes
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04775v2
PDF	http://arxiv.org/pdf/1702.04775v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-additive-adaptive-basis-tensor
Repo
Framework

Unsupervised Domain Adaptation with Similarity Learning


Title	Unsupervised Domain Adaptation with Similarity Learning
Authors	Pedro O. Pinheiro
Abstract	The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain) and (ii) make the features from both domains to be as indistinguishable as possible, so that a classifier trained on the source can also be applied on the target domain. In general, the classifiers in step (i) consist of fully-connected layers applied directly on the indistinguishable features learned in (ii). In this paper, we propose a different way to do the classification, using similarity learning. The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category. The domain-invariant features and the categorical prototype representations are learned jointly and in an end-to-end fashion. At inference time, images from the target domain are compared to the prototypes and the label associated with the one that best matches the image is outputed. The approach is simple, scalable and effective. We show that our model achieves state-of-the-art performance in different unsupervised domain adaptation scenarios.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08995v2
PDF	http://arxiv.org/pdf/1711.08995v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-with-1
Repo
Framework

External Evaluation of Event Extraction Classifiers for Automatic Pathway Curation: An extended study of the mTOR pathway


Title	External Evaluation of Event Extraction Classifiers for Automatic Pathway Curation: An extended study of the mTOR pathway
Authors	Wojciech Kusa, Michael Spranger
Abstract	This paper evaluates the impact of various event extraction systems on automatic pathway curation using the popular mTOR pathway. We quantify the impact of training data sets as well as different machine learning classifiers and show that some improve the quality of automatically extracted pathways.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02063v1
PDF	http://arxiv.org/pdf/1707.02063v1.pdf
PWC	https://paperswithcode.com/paper/external-evaluation-of-event-extraction
Repo
Framework

Geracao Automatica de Paineis de Controle para Analise de Mobilidade Urbana Utilizando Redes Complexas


Title	Geracao Automatica de Paineis de Controle para Analise de Mobilidade Urbana Utilizando Redes Complexas
Authors	Victor Dantas, Henrique Santos, Carlos Caminha, Vasco Furtado
Abstract	In this paper we describe an automatic generator to support the data scientist to construct, in a user-friendly way, dashboards from data represented as networks. The generator called SBINet (Semantic for Business Intelligence from Networks) has a semantic layer that, through ontologies, describes the data that represents a network as well as the possible metrics to be calculated in the network. Thus, with SBINet, the stages of the dashboard constructing process that uses complex network metrics are facilitated and can be done by users who do not necessarily know about complex networks.
Tasks
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01399v1
PDF	http://arxiv.org/pdf/1704.01399v1.pdf
PWC	https://paperswithcode.com/paper/geracao-automatica-de-paineis-de-controle
Repo
Framework

Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis


Title	Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
Authors	Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu
Abstract	Tight collaboration between experts of machine learning and manycore system design is necessary to create a data-driven manycore design framework that integrates both learning and expert knowledge. Such a framework will be necessary to address the rising complexity of designing large-scale manycore systems and machine learning techniques.
Tasks
Published	2017-11-30
URL	http://arxiv.org/abs/1712.00076v1
PDF	http://arxiv.org/pdf/1712.00076v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-and-manycore-systems-design
Repo
Framework

Tableaux for Policy Synthesis for MDPs with PCTL* Constraints


Title	Tableaux for Policy Synthesis for MDPs with PCTL* Constraints
Authors	Peter Baumgartner, Sylvie Thiébaux, Felipe Trevizan
Abstract	Markov decision processes (MDPs) are the standard formalism for modelling sequential decision making in stochastic environments. Policy synthesis addresses the problem of how to control or limit the decisions an agent makes so that a given specification is met. In this paper we consider PCTL, the probabilistic counterpart of CTL, as the specification language. Because in general the policy synthesis problem for PCTL* is undecidable, we restrict to policies whose execution history memory is finitely bounded a priori. Surprisingly, no algorithm for policy synthesis for this natural and expressive framework has been developed so far. We close this gap and describe a tableau-based algorithm that, given an MDP and a PCTL* specification, derives in a non-deterministic way a system of (possibly nonlinear) equalities and inequalities. The solutions of this system, if any, describe the desired (stochastic) policies. Our main result in this paper is the correctness of our method, i.e., soundness, completeness and termination.
Tasks	Decision Making
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10102v3
PDF	http://arxiv.org/pdf/1706.10102v3.pdf
PWC	https://paperswithcode.com/paper/tableaux-for-policy-synthesis-for-mdps-with
Repo
Framework

Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work


Title	Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work
Authors	Nizar Massouh, Francesca Babiloni, Tatiana Tommasi, Jay Young, Nick Hawes, Barbara Caputo
Abstract	Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in time, and as such it is prone to aging, as well as dataset bias issues. Moving beyond fixed training datasets will lead to more robust visual systems, especially when deployed on robots in new environments which must train on the objects they encounter there. To make this possible, it is important to break free from the need for manual annotators. Recent work has begun to investigate how to use the massive amount of images available on the Web in place of manual image annotations. We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy. By combining these two results, we obtain a method for learning powerful deep object models automatically from the Web. We confirm the effectiveness of our approach through object categorization experiments using our Web-derived version of ImageNet on a popular robot vision benchmark database, and on a lifelong object discovery task on a mobile robot.
Tasks	Object Classification
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08513v1
PDF	http://arxiv.org/pdf/1702.08513v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-visual-object-models-from-noisy
Repo
Framework

Toward a full-scale neural machine translation in production: the Booking.com use case


Title	Toward a full-scale neural machine translation in production: the Booking.com use case
Authors	Pavel Levin, Nishikant Dhanuka, Talaat Khalil, Fedor Kovalev, Maxim Khalilov
Abstract	While some remarkable progress has been made in neural machine translation (NMT) research, there have not been many reports on its development and evaluation in practice. This paper tries to fill this gap by presenting some of our findings from building an in-house travel domain NMT system in a large scale E-commerce setting. The three major topics that we cover are optimization and training (including different optimization strategies and corpus sizes), handling real-world content and evaluating results.
Tasks	Machine Translation
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05820v2
PDF	http://arxiv.org/pdf/1709.05820v2.pdf
PWC	https://paperswithcode.com/paper/toward-a-full-scale-neural-machine
Repo
Framework

Distributed Learning for Cooperative Inference


Title	Distributed Learning for Cooperative Inference
Authors	Angelia Nedić, Alex Olshevsky, César A. Uribe
Abstract	We study the problem of cooperative inference where a group of agents interact over a network and seek to estimate a joint parameter that best explains a set of observations. Agents do not know the network topology or the observations of other agents. We explore a variational interpretation of the Bayesian posterior density, and its relation to the stochastic mirror descent algorithm, to propose a new distributed learning algorithm. We show that, under appropriate assumptions, the beliefs generated by the proposed algorithm concentrate around the true parameter exponentially fast. We provide explicit non-asymptotic bounds for the convergence rate. Moreover, we develop explicit and computationally efficient algorithms for observation models belonging to exponential families.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02718v1
PDF	http://arxiv.org/pdf/1704.02718v1.pdf
PWC	https://paperswithcode.com/paper/distributed-learning-for-cooperative
Repo
Framework

Learning Non-Metric Visual Similarity for Image Retrieval


Title	Learning Non-Metric Visual Similarity for Image Retrieval
Authors	Noa Garcia, George Vogiatzis
Abstract	Measuring visual similarity between two or more instances within a data distribution is a fundamental task in image retrieval. Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system. In this work, we explore neural networks models for learning a non-metric similarity function for instance search. We argue that non-metric similarity functions based on neural networks can build a better model of human visual perception than standard metric distances. As our proposed similarity function is differentiable, we explore a real end-to-end trainable approach for image retrieval, i.e. we learn the weights from the input image pixels to the final similarity score. Experimental evaluation shows that non-metric similarity networks are able to learn visual similarities between images and improve performance on top of state-of-the-art image representations, boosting results in standard image retrieval datasets with respect standard metric distances.
Tasks	Content-Based Image Retrieval, Image Retrieval, Instance Search
Published	2017-09-05
URL	http://arxiv.org/abs/1709.01353v2
PDF	http://arxiv.org/pdf/1709.01353v2.pdf
PWC	https://paperswithcode.com/paper/learning-non-metric-visual-similarity-for
Repo
Framework

Deep manifold-to-manifold transforming network for action recognition


Title	Deep manifold-to-manifold transforming network for action recognition
Authors	Tong Zhang, Wenming Zheng, Zhen Cui, Chaolong Li
Abstract	Symmetric positive definite (SPD) matrices (e.g., covariances, graph Laplacians, etc.) are widely used to model the relationship of spatial or temporal domain. Nevertheless, SPD matrices are theoretically embedded on Riemannian manifolds. In this paper, we propose an end-to-end deep manifold-to-manifold transforming network (DMT-Net) which can make SPD matrices flow from one Riemannian manifold to another more discriminative one. To learn discriminative SPD features characterizing both spatial and temporal dependencies, we specifically develop three novel layers on manifolds: (i) the local SPD convolutional layer, (ii) the non-linear SPD activation layer, and (iii) the Riemannian-preserved recursive layer. The SPD property is preserved through all layers without any requirement of singular value decomposition (SVD), which is often used in the existing methods with expensive computation cost. Furthermore, a diagonalizing SPD layer is designed to efficiently calculate the final metric for the classification task. To evaluate our proposed method, we conduct extensive experiments on the task of action recognition, where input signals are popularly modeled as SPD matrices. The experimental results demonstrate that our DMT-Net is much more competitive over state-of-the-art.
Tasks	Temporal Action Localization
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10732v3
PDF	http://arxiv.org/pdf/1705.10732v3.pdf
PWC	https://paperswithcode.com/paper/deep-manifold-to-manifold-transforming
Repo
Framework

Predicting Exploitation of Disclosed Software Vulnerabilities Using Open-source Data


Title	Predicting Exploitation of Disclosed Software Vulnerabilities Using Open-source Data
Authors	Benjamin L. Bullough, Anna K. Yanchenko, Christopher L. Smith, Joseph R. Zipkin
Abstract	Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities are known and users quickly install those patches as soon as they are available. However, most vulnerabilities are never actually exploited. Since writing, testing, and installing software patches can involve considerable resources, it would be desirable to prioritize the remediation of vulnerabilities that are likely to be exploited. Several published research studies have reported moderate success in applying machine learning techniques to the task of predicting whether a vulnerability will be exploited. These approaches typically use features derived from vulnerability databases (such as the summary text describing the vulnerability) or social media posts that mention the vulnerability by name. However, these prior studies share multiple methodological shortcomings that inflate predictive power of these approaches. We replicate key portions of the prior work, compare their approaches, and show how selection of training and test data critically affect the estimated performance of predictive models. The results of this study point to important methodological considerations that should be taken into account so that results reflect real-world utility.
Tasks
Published	2017-07-25
URL	http://arxiv.org/abs/1707.08015v1
PDF	http://arxiv.org/pdf/1707.08015v1.pdf
PWC	https://paperswithcode.com/paper/predicting-exploitation-of-disclosed-software
Repo
Framework

Saliency-guided video classification via adaptively weighted learning


Title	Saliency-guided video classification via adaptively weighted learning
Authors	Yunzhen Zhao, Yuxin Peng
Abstract	Video classification is productive in many practical applications, and the recent deep learning has greatly improved its accuracy. However, existing works often model video frames indiscriminately, but from the view of motion, video frames can be decomposed into salient and non-salient areas naturally. Salient and non-salient areas should be modeled with different networks, for the former present both appearance and motion information, and the latter present static background information. To address this problem, in this paper, video saliency is predicted by optical flow without supervision firstly. Then two streams of 3D CNN are trained individually for raw frames and optical flow on salient areas, and another 2D CNN is trained for raw frames on non-salient areas. For the reason that these three streams play different roles for each class, the weights of each stream are adaptively learned for each class. Experimental results show that saliency-guided modeling and adaptively weighted learning can reinforce each other, and we achieve the state-of-the-art results.
Tasks	Optical Flow Estimation, Video Classification
Published	2017-03-23
URL	http://arxiv.org/abs/1703.08025v2
PDF	http://arxiv.org/pdf/1703.08025v2.pdf
PWC	https://paperswithcode.com/paper/saliency-guided-video-classification-via
Repo
Framework

Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data


Title	Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data
Authors	Abhijit Guha Roy, Sailesh Conjeti, Debdoot Sheet, Amin Katouzian, Nassir Navab, Christian Wachinger
Abstract	Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with existing tools and to use them for pre-training. For the subsequent fine-tuning of the network with manually labeled data, we introduce error corrective boosting (ECB), which emphasizes parameter updates on classes with lower accuracy. Furthermore, we introduce SkipDeconv-Net (SD-Net), a new F-CNN architecture for brain segmentation that combines skip connections with the unpooling strategy for upsampling. The SD-Net addresses challenges of severe class imbalance and errors along boundaries. With application to whole-brain MRI T1 scan segmentation, we generate auxiliary labels on a large dataset with FreeSurfer and fine-tune on two datasets with manual annotations. Our results show that the inclusion of auxiliary labels and ECB yields significant improvements. SD-Net segments a 3D scan in 7 secs in comparison to 30 hours for the closest multi-atlas segmentation method, while reaching similar performance. It also outperforms the latest state-of-the-art F-CNN models.
Tasks	Brain Segmentation, Semantic Segmentation
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00938v2
PDF	http://arxiv.org/pdf/1705.00938v2.pdf
PWC	https://paperswithcode.com/paper/error-corrective-boosting-for-learning-fully
Repo
Framework