May 5, 2019

3126 words 15 mins read

Paper Group ANR 495

Spectrally Grouped Total Variation Reconstruction for Scatter Imaging Using ADMM. Compressive phase-only filtering at extreme compression rates. Coupling Distributed and Symbolic Execution for Natural Language Queries. Learnt quasi-transitive similarity for retrieval from large collections of faces. End-to-End Image Super-Resolution via Deep and Sh …

Spectrally Grouped Total Variation Reconstruction for Scatter Imaging Using ADMM


Title	Spectrally Grouped Total Variation Reconstruction for Scatter Imaging Using ADMM
Authors	Ikenna Odinaka, Yan Kaganovsky, Joel A. Greenberg, Mehadi Hassan, David G. Politte, Joseph A. O’Sullivan, Lawrence Carin, David J. Brady
Abstract	We consider X-ray coherent scatter imaging, where the goal is to reconstruct momentum transfer profiles (spectral distributions) at each spatial location from multiplexed measurements of scatter. Each material is characterized by a unique momentum transfer profile (MTP) which can be used to discriminate between different materials. We propose an iterative image reconstruction algorithm based on a Poisson noise model that can account for photon-limited measurements as well as various second order statistics of the data. To improve image quality, previous approaches use edge-preserving regularizers to promote piecewise constancy of the image in the spatial domain while treating each spectral bin separately. Instead, we propose spectrally grouped regularization that promotes piecewise constant images along the spatial directions but also ensures that the MTPs of neighboring spatial bins are similar, if they contain the same material. We demonstrate that this group regularization results in improvement of both spectral and spatial image quality. We pursue an optimization transfer approach where convex decompositions are used to lift the problem such that all hyper-voxels can be updated in parallel and in closed-form. The group penalty introduces a challenge since it is not directly amendable to these decompositions. We use the alternating directions method of multipliers (ADMM) to replace the original problem with an equivalent sequence of sub-problems that are amendable to convex decompositions, leading to a highly parallel algorithm. We demonstrate the performance on real data.
Tasks	Image Reconstruction
Published	2016-01-29
URL	http://arxiv.org/abs/1601.08201v1
PDF	http://arxiv.org/pdf/1601.08201v1.pdf
PWC	https://paperswithcode.com/paper/spectrally-grouped-total-variation
Repo
Framework

Compressive phase-only filtering at extreme compression rates


Title	Compressive phase-only filtering at extreme compression rates
Authors	David Pastor-Calle, Anna Pastuszczak, Michal Mikolajczyk, Rafal Kotynski
Abstract	We introduce an efficient method for the reconstruction of the correlation between a compressively measured image and a phase-only filter. The proposed method is based on two properties of phase-only filtering: such filtering is a unitary circulant transform, and the correlation plane it produces is usually sparse. Thanks to these properties, phase-only filters are perfectly compatible with the framework of compressive sensing. Moreover, the lasso-based recovery algorithm is very fast when phase-only filtering is used as the compression matrix. The proposed method can be seen as a generalisation of the correlation-based pattern recognition technique, which is hereby applied directly to non-adaptively acquired compressed data. At the time of measurement, any prior knowledge of the target object for which the data will be scanned is not required. We show that images measured at extremely high compression rates may still contain sufficient information for target classification and localization, even if the compression rate is high enough, that visual recognition of the target in the reconstructed image is no longer possible. The method has been applied by us to highly undersampled measurements obtained from a single-pixel camera, with sampling based on randomly chosen Walsh-Hadamard patterns.
Tasks	Compressive Sensing
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07751v5
PDF	http://arxiv.org/pdf/1604.07751v5.pdf
PWC	https://paperswithcode.com/paper/compressive-phase-only-filtering-at-extreme
Repo
Framework

Coupling Distributed and Symbolic Execution for Natural Language Queries


Title	Coupling Distributed and Symbolic Execution for Natural Language Queries
Authors	Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin
Abstract	Building neural networks to query a knowledge base (a table) with natural language is an emerging research topic in deep learning. An executor for table querying typically requires multiple steps of execution because queries may have complicated structures. In previous studies, researchers have developed either fully distributed executors or symbolic executors for table querying. A distributed executor can be trained in an end-to-end fashion, but is weak in terms of execution efficiency and explicit interpretability. A symbolic executor is efficient in execution, but is very difficult to train especially at initial stages. In this paper, we propose to couple distributed and symbolic execution for natural language queries, where the symbolic executor is pretrained with the distributed executor’s intermediate execution results in a step-by-step fashion. Experiments show that our approach significantly outperforms both distributed and symbolic executors, exhibiting high accuracy, high learning efficiency, high execution efficiency, and high interpretability.
Tasks
Published	2016-12-08
URL	http://arxiv.org/abs/1612.02741v4
PDF	http://arxiv.org/pdf/1612.02741v4.pdf
PWC	https://paperswithcode.com/paper/coupling-distributed-and-symbolic-execution
Repo
Framework

Learnt quasi-transitive similarity for retrieval from large collections of faces


Title	Learnt quasi-transitive similarity for retrieval from large collections of faces
Authors	Ognjen Arandjelovic
Abstract	We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as a means of computing the similarity between two sets, (ii) introduce transitivity meta-features based on the similarity of salient modes of appearance variation between sets, (iii) show how quasi-transitivity can be learnt from such features without any labelling or manual intervention, and (iv) demonstrate the effectiveness of the proposed methodology through experiments on the notoriously challenging YouTube database and two successful baselines from the literature.
Tasks
Published	2016-03-02
URL	http://arxiv.org/abs/1603.00560v2
PDF	http://arxiv.org/pdf/1603.00560v2.pdf
PWC	https://paperswithcode.com/paper/learnt-quasi-transitive-similarity-for
Repo
Framework

End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks


Title	End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks
Authors	Yifan Wang, Lijun Wang, Hongyu Wang, Peihua Li
Abstract	One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image super-resolution (SR) fail to maintain this advantage. They utilize CNNs in two decoupled steps, i.e., first upsampling the low resolution (LR) image to the high resolution (HR) size with hand-designed techniques (e.g., bicubic interpolation), and then applying CNNs on the upsampled LR image to reconstruct HR results. In this paper, we seek an alternative and propose a new image SR method, which jointly learns the feature extraction, upsampling and HR reconstruction modules, yielding a completely end-to-end trainable deep CNN. As opposed to existing approaches, the proposed method conducts upsampling in the latent feature space with filters that are optimized for the task of image SR. In addition, the HR reconstruction is performed in a multi-scale manner to simultaneously incorporate both short- and long-range contextual information, ensuring more accurate restoration of HR images. To facilitate network training, a new training approach is designed, which jointly trains the proposed deep network with a relatively shallow network, leading to faster convergence and more superior performance. The proposed method is extensively evaluated on widely adopted data sets and improves the performance of state-of-the-art methods with a considerable margin. Moreover, in-depth ablation studies are conducted to verify the contribution of different network designs to image SR, providing additional insights for future research.
Tasks	Image Super-Resolution, Super-Resolution
Published	2016-07-26
URL	http://arxiv.org/abs/1607.07680v1
PDF	http://arxiv.org/pdf/1607.07680v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-image-super-resolution-via-deep
Repo
Framework

Correlation Clustering with Low-Rank Matrices


Title	Correlation Clustering with Low-Rank Matrices
Authors	Nate Veldt, Anthony Wirth, David F. Gleich
Abstract	Correlation clustering is a technique for aggregating data based on qualitative information about which pairs of objects are labeled ‘similar’ or ‘dissimilar.’ Because the optimization problem is NP-hard, much of the previous literature focuses on finding approximation algorithms. In this paper we explore how to solve the correlation clustering objective exactly when the data to be clustered can be represented by a low-rank matrix. We prove in particular that correlation clustering can be solved in polynomial time when the underlying matrix is positive semidefinite with small constant rank, but that the task remains NP-hard in the presence of even one negative eigenvalue. Based on our theoretical results, we develop an algorithm for efficiently “solving” low-rank positive semidefinite correlation clustering by employing a procedure for zonotope vertex enumeration. We demonstrate the effectiveness and speed of our algorithm by using it to solve several clustering problems on both synthetic and real-world data.
Tasks
Published	2016-11-21
URL	http://arxiv.org/abs/1611.07305v2
PDF	http://arxiv.org/pdf/1611.07305v2.pdf
PWC	https://paperswithcode.com/paper/correlation-clustering-with-low-rank-matrices
Repo
Framework

Online Optimization with Costly and Noisy Measurements using Random Fourier Expansions


Title	Online Optimization with Costly and Noisy Measurements using Random Fourier Expansions
Authors	Laurens Bliek, Hans R. G. W. Verstraete, Michel Verhaegen, Sander Wahls
Abstract	This paper analyzes DONE, an online optimization algorithm that iteratively minimizes an unknown function based on costly and noisy measurements. The algorithm maintains a surrogate of the unknown function in the form of a random Fourier expansion (RFE). The surrogate is updated whenever a new measurement is available, and then used to determine the next measurement point. The algorithm is comparable to Bayesian optimization algorithms, but its computational complexity per iteration does not depend on the number of measurements. We derive several theoretical results that provide insight on how the hyper-parameters of the algorithm should be chosen. The algorithm is compared to a Bayesian optimization algorithm for a benchmark problem and three applications, namely, optical coherence tomography, optical beam-forming network tuning, and robot arm control. It is found that the DONE algorithm is significantly faster than Bayesian optimization in the discussed problems, while achieving a similar or better performance.
Tasks
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09620v3
PDF	http://arxiv.org/pdf/1603.09620v3.pdf
PWC	https://paperswithcode.com/paper/online-optimization-with-costly-and-noisy
Repo
Framework

A Neural Network for Coordination Boundary Prediction


Title	A Neural Network for Coordination Boundary Prediction
Authors	Jessica Ficler, Yoav Goldberg
Abstract	We propose a neural-network based model for coordination boundary prediction. The network is designed to incorporate two signals: the similarity between conjuncts and the observation that replacing the whole coordination phrase with a conjunct tends to produce a coherent sentences. The modeling makes use of several LSTM networks. The model is trained solely on conjunction annotations in a Treebank, without using external resources. We show improvements on predicting coordination boundaries on the PTB compared to two state-of-the-art parsers; as well as improvement over previous coordination boundary prediction systems on the Genia corpus.
Tasks
Published	2016-10-13
URL	http://arxiv.org/abs/1610.03946v1
PDF	http://arxiv.org/pdf/1610.03946v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-for-coordination-boundary
Repo
Framework

Predicting the evolution of stationary graph signals


Title	Predicting the evolution of stationary graph signals
Authors	Andreas Loukas, Nathanael Perraudin
Abstract	An emerging way of tackling the dimensionality issues arising in the modeling of a multivariate process is to assume that the inherent data structure can be captured by a graph. Nevertheless, though state-of-the-art graph-based methods have been successful for many learning tasks, they do not consider time-evolving signals and thus are not suitable for prediction. Based on the recently introduced joint stationarity framework for time-vertex processes, this letter considers multivariate models that exploit the graph topology so as to facilitate the prediction. The resulting method yields similar accuracy to the joint (time-graph) mean-squared error estimator but at lower complexity, and outperforms purely time-based methods.
Tasks
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03313v1
PDF	http://arxiv.org/pdf/1607.03313v1.pdf
PWC	https://paperswithcode.com/paper/predicting-the-evolution-of-stationary-graph
Repo
Framework

Active Canny: Edge Detection and Recovery with Open Active Contour Models


Title	Active Canny: Edge Detection and Recovery with Open Active Contour Models
Authors	Muhammet Bastan, S. Saqib Bukhari, Thomas M. Breuel
Abstract	We introduce an edge detection and recovery framework based on open active contour models (snakelets). This is motivated by the noisy or broken edges output by standard edge detection algorithms, like Canny. The idea is to utilize the local continuity and smoothness cues provided by strong edges and grow them to recover the missing edges. This way, the strong edges are used to recover weak or missing edges by considering the local edge structures, instead of blindly linking them if gradient magnitudes are above some threshold. We initialize short snakelets on the gradient magnitudes or binary edges automatically and then deform and grow them under the influence of gradient vector flow. The output snakelets are able to recover most of the breaks or weak edges, and they provide a smooth edge representation of the image; they can also be used for higher level analysis, like contour segmentation.
Tasks	Edge Detection
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03415v1
PDF	http://arxiv.org/pdf/1609.03415v1.pdf
PWC	https://paperswithcode.com/paper/active-canny-edge-detection-and-recovery-with
Repo
Framework

Are Facial Attributes Adversarially Robust?


Title	Are Facial Attributes Adversarially Robust?
Authors	Andras Rozsa, Manuel Günther, Ethan M. Rudd, Terrance E. Boult
Abstract	Facial attributes are emerging soft biometrics that have the potential to reject non-matches, for example, based on mismatching gender. To be usable in stand-alone systems, facial attributes must be extracted from images automatically and reliably. In this paper, we propose a simple yet effective solution for automatic facial attribute extraction by training a deep convolutional neural network (DCNN) for each facial attribute separately, without using any pre-training or dataset augmentation, and we obtain new state-of-the-art facial attribute classification results on the CelebA benchmark. To test the stability of the networks, we generated adversarial images – formed by adding imperceptible non-random perturbations to original inputs which result in classification errors – via a novel fast flipping attribute (FFA) technique. We show that FFA generates more adversarial examples than other related algorithms, and that DCNNs for certain attributes are generally robust to adversarial inputs, while DCNNs for other attributes are not. This result is surprising because no DCNNs tested to date have exhibited robustness to adversarial images without explicit augmentation in the training procedure to account for adversarial examples. Finally, we introduce the concept of natural adversarial samples, i.e., images that are misclassified but can be easily turned into correctly classified images by applying small perturbations. We demonstrate that natural adversarial samples commonly occur, even within the training set, and show that many of these images remain misclassified even with additional training epochs. This phenomenon is surprising because correcting the misclassification, particularly when guided by training data, should require only a small adjustment to the DCNN parameters.
Tasks	Facial Attribute Classification
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05411v3
PDF	http://arxiv.org/pdf/1605.05411v3.pdf
PWC	https://paperswithcode.com/paper/are-facial-attributes-adversarially-robust
Repo
Framework

SoK: Applying Machine Learning in Security - A Survey


Title	SoK: Applying Machine Learning in Security - A Survey
Authors	Heju Jiang, Jasvir Nagra, Parvez Ahammad
Abstract	The idea of applying machine learning(ML) to solve problems in security domains is almost 3 decades old. As information and communications grow more ubiquitous and more data become available, many security risks arise as well as appetite to manage and mitigate such risks. Consequently, research on applying and designing ML algorithms and systems for security has grown fast, ranging from intrusion detection systems(IDS) and malware classification to security policy management(SPM) and information leak checking. In this paper, we systematically study the methods, algorithms, and system designs in academic publications from 2008-2015 that applied ML in security domains. 98 percent of the surveyed papers appeared in the 6 highest-ranked academic security conferences and 1 conference known for pioneering ML applications in security. We examine the generalized system designs, underlying assumptions, measurements, and use cases in active research. Our examinations lead to 1) a taxonomy on ML paradigms and security domains for future exploration and exploitation, and 2) an agenda detailing open and upcoming challenges. Based on our survey, we also suggest a point of view that treats security as a game theory problem instead of a batch-trained ML problem.
Tasks	Intrusion Detection, Malware Classification
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03186v1
PDF	http://arxiv.org/pdf/1611.03186v1.pdf
PWC	https://paperswithcode.com/paper/sok-applying-machine-learning-in-security-a
Repo
Framework

Generalizable Features From Unsupervised Learning


Title	Generalizable Features From Unsupervised Learning
Authors	Mehdi Mirza, Aaron Courville, Yoshua Bengio
Abstract	Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is physical intuition(Lake et al., 2016). In this work, we explore the potential of unsupervised learning to find features that promote better generalization to settings outside the supervised training distribution. Our task is predicting the stability of towers of square blocks. We demonstrate that an unsupervised model, trained to predict future frames of a video sequence of stable and unstable block configurations, can yield features that support extrapolating stability prediction to blocks configurations outside the training set distribution
Tasks
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03809v1
PDF	http://arxiv.org/pdf/1612.03809v1.pdf
PWC	https://paperswithcode.com/paper/generalizable-features-from-unsupervised
Repo
Framework

Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks


Title	Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
Authors	Willem P. Sanberg, Gijs Dubbelman, Peter H. N. de With
Abstract	Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in a self-supervised manner and achieve similar results compared to training on manually annotated data, thereby reducing the need for large manually annotated training sets. To this end, our self-supervised training relies on a stereo-vision disparity system, to automatically generate (weak) training labels for the color-based FCN. Additionally, our self-supervised training facilitates online training of the FCN instead of offline. Consequently, given that the applied FCN is relatively small, the free-space analysis becomes highly adaptive to any traffic scene that the vehicle encounters. We have validated our algorithm using publicly available data and on a new challenging benchmark dataset that is released with this paper. Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.
Tasks
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02316v2
PDF	http://arxiv.org/pdf/1604.02316v2.pdf
PWC	https://paperswithcode.com/paper/free-space-detection-with-self-supervised-and
Repo
Framework

Large scale modeling of antimicrobial resistance with interpretable classifiers


Title	Large scale modeling of antimicrobial resistance with interpretable classifiers
Authors	Alexandre Drouin, Frédéric Raymond, Gaël Letarte St-Pierre, Mario Marchand, Jacques Corbeil, François Laviolette
Abstract	Antimicrobial resistance is an important public health concern that has implications in the practice of medicine worldwide. Accurately predicting resistance phenotypes from genome sequences shows great promise in promoting better use of antimicrobial agents, by determining which antibiotics are likely to be effective in specific clinical cases. In healthcare, this would allow for the design of treatment plans tailored for specific individuals, likely resulting in better clinical outcomes for patients with bacterial infections. In this work, we present the recent work of Drouin et al. (2016) on using Set Covering Machines to learn highly interpretable models of antibiotic resistance and complement it by providing a large scale application of their method to the entire PATRIC database. We report prediction results for 36 new datasets and present the Kover AMR platform, a new web-based tool allowing the visualization and interpretation of the generated models.
Tasks
Published	2016-12-03
URL	http://arxiv.org/abs/1612.01030v1
PDF	http://arxiv.org/pdf/1612.01030v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-modeling-of-antimicrobial
Repo
Framework