October 20, 2019

3212 words 16 mins read

Paper Group ANR 82

Probabilistic Blocking with An Application to the Syrian Conflict. Domain transfer convolutional attribute embedding. On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects. Discriminative Feature Learning with Foreground Attention for Person Re-Identification. OWLAx: A Protege Plugin to Support Ontology Axiomatization …

Probabilistic Blocking with An Application to the Syrian Conflict


Title	Probabilistic Blocking with An Application to the Syrian Conflict
Authors	Rebecca C. Steorts, Anshumali Shrivastava
Abstract	Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce $k$-means locality sensitive hashing (KLSH), which is based upon the information retrieval literature and clusters similar records into blocks using a vector-space representation and projections. Second, we introduce a subquadratic variant of LSH to the literature, known as Densified One Permutation Hashing (DOPH). Third, we propose a weighted variant of DOPH. We illustrate each method on an application to a subset of the ongoing Syrian conflict, giving a discussion of each method.
Tasks	Entity Resolution, Information Retrieval
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05497v1
PDF	http://arxiv.org/pdf/1810.05497v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-blocking-with-an-application-to
Repo
Framework

Domain transfer convolutional attribute embedding


Title	Domain transfer convolutional attribute embedding
Authors	Fang Su, Jing-Yan Wang
Abstract	In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross different domains. This strongly motives us to learn effective domain transfer attribute representations. To this end, we proposed to embed the attributes of the data to a common space by using the powerful convolutional neural network (CNN) model. The convolutional representations of the data points are mapped to the corresponding attributes so that they can be effective embedding of the attributes. We also represent the data of different domains by a domain-independent CNN, ant a domain-specific CNN, and combine their outputs with the attribute embedding to build the classification model. An joint learning framework is constructed to minimize the classification errors, the attribute mapping error, the mismatching of the domain-independent representations cross different domains, and to encourage the the neighborhood smoothness of representations in the target domain. The minimization problem is solved by an iterative algorithm based on gradient descent. Experiments over benchmark data sets of person re-identification, bankruptcy prediction, and spam email detection, show the effectiveness of the proposed method.
Tasks	Person Re-Identification, Transfer Learning
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09733v2
PDF	http://arxiv.org/pdf/1803.09733v2.pdf
PWC	https://paperswithcode.com/paper/domain-transfer-convolutional-attribute
Repo
Framework

On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects


Title	On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects
Authors	Steve Morad, Ravi Teja Nallapu, Himangshu Kalita, Byon Kwon, Vishnu Reddy, Roberto Furfaro, Erik Asphaug, Jekan Thangavelautham
Abstract	The wide availability of Commercial Off-The-Shelf (COTS) electronics that can withstand Low Earth Orbit conditions has opened avenue for wide deployment of CubeSats and small-satellites. CubeSats thanks to their low developmental and launch costs offer new opportunities for rapidly demonstrating on-orbit surveillance capabilities. In our earlier work, we proposed development of SWIMSat (Space based Wide-angle Imaging of Meteors) a 3U CubeSat demonstrator that is designed to observe illuminated objects entering the Earth’s atmosphere. The spacecraft would operate autonomously using a smart camera with vision algorithms to detect, track and report of objects. Several CubeSats can track an object in a coordinated fashion to pinpoint an object’s trajectory. An extension of this smart camera capability is to track unilluminated objects utilizing capabilities we have been developing to track and navigate to Near Earth Objects (NEOs). This extension enables detecting and tracking objects that can’t readily be detected by humans. The system maintains a dense star map of the night sky and performs round the clock observations. Standard optical flow algorithms are used to obtain trajectories of all moving objects in the camera field of view. Through a process of elimination, certain stars maybe occluded by a transiting unilluminated object which is then used to first detect and obtain a trajectory of the object. Using multiple cameras observing the event from different points of view, it may be possible then to triangulate the position of the object in space and obtain its orbital trajectory. In this work, the performance of our space object detection algorithm coupled with a spacecraft guidance, navigation, and control system is demonstrated.
Tasks	Object Detection, Optical Flow Estimation
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02042v1
PDF	http://arxiv.org/pdf/1809.02042v1.pdf
PWC	https://paperswithcode.com/paper/on-orbit-smart-camera-system-to-observe
Repo
Framework

Discriminative Feature Learning with Foreground Attention for Person Re-Identification


Title	Discriminative Feature Learning with Foreground Attention for Person Re-Identification
Authors	Sanping Zhou, Jinjun Wang, Deyu Meng, Yudong Liang, Yihong Gong, Nanning Zheng
Abstract	The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively emphasize the foreground persons becomes very critical to solve the person Re-ID problem. In this paper, we propose a simple yet effective foreground attentive neural network (FANN) to learn a discriminative feature representation for person Re-ID, which can adaptively enhance the positive side of foreground and weaken the negative side of background. Specifically, a novel foreground attentive subnetwork is designed to drive the network’s attention, in which a decoder network is used to reconstruct the binary mask by using a novel local regression loss function, and an encoder network is regularized by the decoder network to focus its attention on the foreground persons. The resulting feature maps of encoder network are further fed into the body part subnetwork and feature fusion subnetwork to learn discriminative features. Besides, a novel symmetric triplet loss function is introduced to supervise feature learning, in which the intra-class distance is minimized and the inter-class distance is maximized in each triplet unit, simultaneously. Training our FANN in a multi-task learning framework, a discriminative feature representation can be learned to find out the matched reference to each probe among various candidates in the gallery. Extensive experimental results on several public benchmark datasets are evaluated, which have shown clear improvements of our method over the state-of-the-art approaches.
Tasks	Multi-Task Learning, Person Re-Identification
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01455v2
PDF	http://arxiv.org/pdf/1807.01455v2.pdf
PWC	https://paperswithcode.com/paper/discriminative-feature-learning-with
Repo
Framework

OWLAx: A Protege Plugin to Support Ontology Axiomatization through Diagramming


Title	OWLAx: A Protege Plugin to Support Ontology Axiomatization through Diagramming
Authors	Md. Kamruzzaman Sarker, Adila A. Krisnadhi, Pascal Hitzler
Abstract	Once the conceptual overview, in terms of a somewhat informal class diagram, has been designed in the course of engineering an ontology, the process of adding many of the appropriate logical axioms is mostly a routine task. We provide a Protege plugin which supports this task, together with a visual user interface, based on established methods for ontology design pattern modeling.
Tasks
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10105v1
PDF	http://arxiv.org/pdf/1808.10105v1.pdf
PWC	https://paperswithcode.com/paper/owlax-a-protege-plugin-to-support-ontology
Repo
Framework

Instance-based Deep Transfer Learning


Title	Instance-based Deep Transfer Learning
Authors	Tianyang Wang, Jun Huan, Michelle Zhu
Abstract	Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is probably the most frequently used method. However, very little research work has been devoted to enhancing deep transfer learning by focusing on the influence of data. In this paper, we propose an instance-based approach to improve deep transfer learning in a target domain. Specifically, we choose a pre-trained model from a source domain and apply this model to estimate the influence of training samples in a target domain. Then we optimize the training data of the target domain by removing the training samples that will lower the performance of the pre-trained model. We later either fine-tune the pre-trained model with the optimized training data in the target domain, or build a new model which is initialized partially based on the pre-trained model, and fine-tune it with the optimized training data in the target domain. Using this approach, transfer learning can help deep learning models to capture more useful features. Extensive experiments demonstrate the effectiveness of our approach on boosting the quality of deep learning models for some common computer vision tasks, such as image classification.
Tasks	Image Classification, Transfer Learning
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02776v2
PDF	http://arxiv.org/pdf/1809.02776v2.pdf
PWC	https://paperswithcode.com/paper/instance-based-deep-transfer-learning
Repo
Framework

PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models


Title	PANDA: AdaPtive Noisy Data Augmentation for Regularization of Undirected Graphical Models
Authors	Yinan Li, Xiao Liu, Fang Liu
Abstract	We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data until convergence to achieve regularization on model parameters. The augmented noises can be designed to achieve various regularization effects on graph estimation, such as the bridge (including lasso and ridge), elastic net, adaptive lasso, and SCAD penalization; it also realizes the group lasso and fused ridge. We examine the tail bound of the noise-augmented loss function and establish that the noise-augmented loss function and its minimizer converge almost surely to the expected penalized loss function and its minimizer, respectively. We derive the asymptotic distributions for the regularized parameters through PANDA in generalized linear models, based on which, inferences for the parameters can be obtained simultaneously with variable selection. We show the non-inferior performance of PANDA in constructing graphs of different types in simulation studies and apply PANDA to an autism spectrum disorder data to construct a mixed-node graph. We also show that the inferences based on the asymptotic distribution of regularized parameter estimates via PANDA achieve nominal or near-nominal coverage and are far more efficient, compared to some existing post-selection procedures. Computationally, PANDA can be easily programmed in software that implements (GLMs) without resorting to complicated optimization techniques.
Tasks	Data Augmentation
Published	2018-10-11
URL	https://arxiv.org/abs/1810.04851v2
PDF	https://arxiv.org/pdf/1810.04851v2.pdf
PWC	https://paperswithcode.com/paper/panda-adaptive-noisy-data-augmentation-for
Repo
Framework

signSGD with Majority Vote is Communication Efficient And Fault Tolerant


Title	signSGD with Majority Vote is Communication Efficient And Fault Tolerant
Authors	Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar
Abstract	Training neural networks on large datasets can be accelerated by distributing the workload over a network of machines. As datasets grow ever larger, networks of hundreds or thousands of machines become economically viable. The time cost of communicating gradients limits the effectiveness of using such large machine counts, as may the increased chance of network faults. We explore a particularly simple algorithm for robust, communication-efficient learning—signSGD. Workers transmit only the sign of their gradient vector to a server, and the overall update is decided by a majority vote. This algorithm uses $32\times$ less communication per iteration than full-precision, distributed SGD. Under natural conditions verified by experiment, we prove that signSGD converges in the large and mini-batch settings, establishing convergence for a parameter regime of Adam as a byproduct. Aggregating sign gradients by majority vote means that no individual worker has too much power. We prove that unlike SGD, majority vote is robust when up to 50% of workers behave adversarially. The class of adversaries we consider includes as special cases those that invert or randomise their gradient estimate. On the practical side, we built our distributed training system in Pytorch. Benchmarking against the state of the art collective communications library (NCCL), our framework—with the parameter server housed entirely on one machine—led to a 25% reduction in time for training resnet50 on Imagenet when using 15 AWS p3.2xlarge machines.
Tasks
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05291v3
PDF	http://arxiv.org/pdf/1810.05291v3.pdf
PWC	https://paperswithcode.com/paper/signsgd-with-majority-vote-is-communication
Repo
Framework

Faster Rates for Convex-Concave Games


Title	Faster Rates for Convex-Concave Games
Authors	Jacob Abernethy, Kevin A. Lai, Kfir Y. Levy, Jun-Kun Wang
Abstract	We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games. While standard regret bounds would lead to convergence rates on the order of $O(T^{-1/2})$, recent work \citep{RS13,SALS15} has established $O(1/T)$ rates by taking advantage of a particular class of optimistic prediction algorithms. In this work we go further, showing that for a particular class of games one achieves a $O(1/T^2)$ rate, and we show how this applies to the Frank-Wolfe method and recovers a similar bound \citep{D15}. We also show that such no-regret techniques can even achieve a linear rate, $O(\exp(-T))$, for equilibrium computation under additional curvature assumptions.
Tasks
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06792v1
PDF	http://arxiv.org/pdf/1805.06792v1.pdf
PWC	https://paperswithcode.com/paper/faster-rates-for-convex-concave-games
Repo
Framework

A Discriminative Latent-Variable Model for Bilingual Lexicon Induction


Title	A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
Authors	Sebastian Ruder, Ryan Cotterell, Yova Kementchedjhieva, Anders Søgaard
Abstract	We introduce a novel discriminative latent-variable model for the task of bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a state-of-the-art embedding-based approach. To train the model, we derive an efficient Viterbi EM algorithm. We provide empirical improvements on six language pairs under two metrics and show that the prior theoretically and empirically helps to mitigate the hubness problem. We also demonstrate how previous work may be viewed as a similarly fashioned latent-variable model, albeit with a different prior.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09334v2
PDF	http://arxiv.org/pdf/1808.09334v2.pdf
PWC	https://paperswithcode.com/paper/a-discriminative-latent-variable-model-for
Repo
Framework

FeatureLego: Volume Exploration Using Exhaustive Clustering of Super-Voxels


Title	FeatureLego: Volume Exploration Using Exhaustive Clustering of Super-Voxels
Authors	Shreeraj Jadhav, Saad Nadeem, Arie Kaufman
Abstract	We present a volume exploration framework, FeatureLego, that uses a novel voxel clustering approach for efficient selection of semantic features. We partition the input volume into a set of compact super-voxels that represent the finest selection granularity. We then perform an exhaustive clustering of these super-voxels using a graph-based clustering method. Unlike the prevalent brute-force parameter sampling approaches, we propose an efficient algorithm to perform this exhaustive clustering. By computing an exhaustive set of clusters, we aim to capture as many boundaries as possible and ensure that the user has sufficient options for efficiently selecting semantically relevant features. Furthermore, we merge all the computed clusters into a single tree of meta-clusters that can be used for hierarchical exploration. We implement an intuitive user-interface to interactively explore volumes using our clustering approach. Finally, we show the effectiveness of our framework on multiple real-world datasets of different modalities.
Tasks
Published	2018-10-11
URL	https://arxiv.org/abs/1810.05220v2
PDF	https://arxiv.org/pdf/1810.05220v2.pdf
PWC	https://paperswithcode.com/paper/featurelego-volume-exploration-using
Repo
Framework

Robot Imitation through Vision, Kinesthetic and Force Features with Online Adaptation to Changing Environments


Title	Robot Imitation through Vision, Kinesthetic and Force Features with Online Adaptation to Changing Environments
Authors	Raul Fernandez-Fernandez, Juan G. Victores, David Estevez, Carlos Balaguer
Abstract	Continuous Goal-Directed Actions (CGDA) is a robot imitation framework that encodes actions as the changes they produce on the environment. While it presents numerous advantages with respect to other robot imitation frameworks in terms of generalization and portability, final robot joint trajectories for the execution of actions are not necessarily encoded within the model. This is studied as an optimization problem, and the solution is computed through evolutionary algorithms in simulated environments. Evolutionary algorithms require a large number of evaluations, which had made the use of these algorithms in real world applications very challenging. This paper presents online evolutionary strategies, as a change of paradigm within CGDA execution. Online evolutionary strategies shift and merge motor execution into the planning loop. A concrete online evolutionary strategy, Online Evolved Trajectories (OET), is presented. OET drastically reduces computational times between motor executions, and enables working in real world dynamic environments and/or with human collaboration. Its performance has been measured against Full Trajectory Evolution (FTE) and Incrementally Evolved Trajectories (IET), obtaining the best overall results. Experimental evaluations are performed on the TEO full-sized humanoid robot with “paint” and “iron” actions that together involve vision, kinesthetic and force features.
Tasks
Published	2018-07-24
URL	https://arxiv.org/abs/1807.09177v3
PDF	https://arxiv.org/pdf/1807.09177v3.pdf
PWC	https://paperswithcode.com/paper/robot-imitation-through-vision-kinesthetic
Repo
Framework

The Visual QA Devil in the Details: The Impact of Early Fusion and Batch Norm on CLEVR


Title	The Visual QA Devil in the Details: The Impact of Early Fusion and Batch Norm on CLEVR
Authors	Mateusz Malinowski, Carl Doersch
Abstract	Visual QA is a pivotal challenge for higher-level reasoning, requiring understanding language, vision, and relationships between many objects in a scene. Although datasets like CLEVR are designed to be unsolvable without such complex relational reasoning, some surprisingly simple feed-forward, “holistic” models have recently shown strong performance on this dataset. These models lack any kind of explicit iterative, symbolic reasoning procedure, which are hypothesized to be necessary for counting objects, narrowing down the set of relevant objects based on several attributes, etc. The reason for this strong performance is poorly understood. Hence, our work analyzes such models, and finds that minor architectural elements are crucial to performance. In particular, we find that \textit{early fusion} of language and vision provides large performance improvements. This contrasts with the late fusion approaches popular at the dawn of Visual QA. We propose a simple module we call Multimodal Core, which we hypothesize performs the fundamental operations for multimodal tasks. We believe that understanding why these elements are so important to complex question answering will aid the design of better-performing algorithms for Visual QA while minimizing hand-engineering effort.
Tasks	Question Answering, Relational Reasoning
Published	2018-09-11
URL	http://arxiv.org/abs/1809.04482v1
PDF	http://arxiv.org/pdf/1809.04482v1.pdf
PWC	https://paperswithcode.com/paper/the-visual-qa-devil-in-the-details-the-impact
Repo
Framework

Large Spectral Density Matrix Estimation by Thresholding


Title	Large Spectral Density Matrix Estimation by Thresholding
Authors	Yiming Sun, Yige Li, Amy Kuceyeski, Sumanta Basu
Abstract	Spectral density matrix estimation of multivariate time series is a classical problem in time series and signal processing. In modern neuroscience, spectral density based metrics are commonly used for analyzing functional connectivity among brain regions. In this paper, we develop a non-asymptotic theory for regularized estimation of high-dimensional spectral density matrices of Gaussian and linear processes using thresholded versions of averaged periodograms. Our theoretical analysis ensures that consistent estimation of spectral density matrix of a $p$-dimensional time series using $n$ samples is possible under high-dimensional regime $\log p / n \rightarrow 0$ as long as the true spectral density is approximately sparse. A key technical component of our analysis is a new concentration inequality of average periodogram around its expectation, which is of independent interest. Our estimation consistency results complement existing results for shrinkage based estimators of multivariate spectral density, which require no assumption on sparsity but only ensure consistent estimation in a regime $p^2/n \rightarrow 0$. In addition, our proposed thresholding based estimators perform consistent and automatic edge selection when learning coherence networks among the components of a multivariate time series. We demonstrate the advantage of our estimators using simulation studies and a real data application on functional connectivity analysis with fMRI data.
Tasks	Time Series
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00532v1
PDF	http://arxiv.org/pdf/1812.00532v1.pdf
PWC	https://paperswithcode.com/paper/large-spectral-density-matrix-estimation-by
Repo
Framework

Approximate Probabilistic Neural Networks with Gated Threshold Logic


Title	Approximate Probabilistic Neural Networks with Gated Threshold Logic
Authors	Olga Krestinskaya, Alex Pappachen James
Abstract	Probabilistic Neural Network (PNN) is a feed-forward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.
Tasks	Quantization
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00733v1
PDF	http://arxiv.org/pdf/1808.00733v1.pdf
PWC	https://paperswithcode.com/paper/approximate-probabilistic-neural-networks
Repo
Framework