May 7, 2019

2761 words 13 mins read

Paper Group ANR 69

Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval. Parsing Images of Overlapping Organisms with Deep Singling-Out Networks. Dynamic matrix factorization with social influence. Fast Algorithms for Robust PCA via Gradient Descent. LAYERS: Yet another Neural Network toolkit. End-to-end LSTM-based …

Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval


Title	Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
Authors	Weixun Zhou, Shawn Newsam, Congmin Li, Zhenfeng Shao
Abstract	Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the content complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNN) for high-resolution remote sensing image retrieval (HRRSIR). To this end, two effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, the deep features are extracted from the fully-connected and convolutional layers of the pre-trained CNN models, respectively; in the second scheme, we propose a novel CNN architecture based on conventional convolution layers and a three-layer perceptron. The novel CNN model is then trained on a large remote sensing dataset to learn low dimensional features. The two schemes are evaluated on several public and challenging datasets, and the results indicate that the proposed schemes and in particular the novel CNN are able to achieve state-of-the-art performance.
Tasks	Image Retrieval
Published	2016-10-10
URL	http://arxiv.org/abs/1610.03023v2
PDF	http://arxiv.org/pdf/1610.03023v2.pdf
PWC	https://paperswithcode.com/paper/learning-low-dimensional-convolutional-neural
Repo
Framework

Parsing Images of Overlapping Organisms with Deep Singling-Out Networks


Title	Parsing Images of Overlapping Organisms with Deep Singling-Out Networks
Authors	Victor Yurchenko, Victor Lempitsky
Abstract	This work is motivated by the mostly unsolved task of parsing biological images with multiple overlapping articulated model organisms (such as worms or larvae). We present a general approach that separates the two main challenges associated with such data, individual object shape estimation and object groups disentangling. At the core of the approach is a deep feed-forward singling-out network (SON) that is trained to map each local patch to a vectorial descriptor that is sensitive to the characteristics (e.g. shape) of a central object, while being invariant to the variability of all other surrounding elements. Given a SON, a local image patch can be matched to a gallery of isolated elements using their SON-descriptors, thus producing a hypothesis about the shape of the central element in that patch. The image-level optimization based on integer programming can then pick a subset of the hypotheses to explain (parse) the whole image and disentangle groups of organisms. While sharing many similarities with existing “analysis-by-synthesis” approaches, our method avoids the need for stochastic search in the high-dimensional configuration space and numerous rendering operations at test-time. We show that our approach can parse microscopy images of three popular model organisms (the C.Elegans roundworms, the Drosophila larvae, and the E.Coli bacteria) even under significant crowding and overlaps between organisms. We speculate that the overall approach is applicable to a wider class of image parsing problems concerned with crowded articulated objects, for which rendering training images is possible.
Tasks
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06017v1
PDF	http://arxiv.org/pdf/1612.06017v1.pdf
PWC	https://paperswithcode.com/paper/parsing-images-of-overlapping-organisms-with
Repo
Framework


Title	Dynamic matrix factorization with social influence
Authors	Aleksandr Y. Aravkin, Kush R. Varshney, Liu Yang
Abstract	Matrix factorization is a key component of collaborative filtering-based recommendation systems because it allows us to complete sparse user-by-item ratings matrices under a low-rank assumption that encodes the belief that similar users give similar ratings and that similar items garner similar ratings. This paradigm has had immeasurable practical success, but it is not the complete story for understanding and inferring the preferences of people. First, peoples’ preferences and their observable manifestations as ratings evolve over time along general patterns of trajectories. Second, an individual person’s preferences evolve over time through influence of their social connections. In this paper, we develop a unified process model for both types of dynamics within a state space approach, together with an efficient optimization scheme for estimation within that model. The model combines elements from recent developments in dynamic matrix factorization, opinion dynamics and social learning, and trust-based recommendation. The estimation builds upon recent advances in numerical nonlinear optimization. Empirical results on a large-scale data set from the Epinions website demonstrate consistent reduction in root mean squared error by consideration of the two types of dynamics.
Tasks	Recommendation Systems
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06194v1
PDF	http://arxiv.org/pdf/1604.06194v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-matrix-factorization-with-social
Repo
Framework

Fast Algorithms for Robust PCA via Gradient Descent


Title	Fast Algorithms for Robust PCA via Gradient Descent
Authors	Xinyang Yi, Dohyung Park, Yudong Chen, Constantine Caramanis
Abstract	We consider the problem of Robust PCA in the fully and partially observed settings. Without corruptions, this is the well-known matrix completion problem. From a statistical standpoint this problem has been recently well-studied, and conditions on when recovery is possible (how many observations do we need, how many corruptions can we tolerate) via polynomial-time algorithms is by now understood. This paper presents and analyzes a non-convex optimization approach that greatly reduces the computational complexity of the above problems, compared to the best available algorithms. In particular, in the fully observed case, with $r$ denoting rank and $d$ dimension, we reduce the complexity from $\mathcal{O}(r^2d^2\log(1/\varepsilon))$ to $\mathcal{O}(rd^2\log(1/\varepsilon))$ – a big savings when the rank is big. For the partially observed case, we show the complexity of our algorithm is no more than $\mathcal{O}(r^4d \log d \log(1/\varepsilon))$. Not only is this the best-known run-time for a provable algorithm under partial observation, but in the setting where $r$ is small compared to $d$, it also allows for near-linear-in-$d$ run-time that can be exploited in the fully-observed case as well, by simply running our algorithm on a subset of the observations.
Tasks	Matrix Completion
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07784v2
PDF	http://arxiv.org/pdf/1605.07784v2.pdf
PWC	https://paperswithcode.com/paper/fast-algorithms-for-robust-pca-via-gradient
Repo
Framework

LAYERS: Yet another Neural Network toolkit


Title	LAYERS: Yet another Neural Network toolkit
Authors	Roberto Paredes, José-Miguel Benedí
Abstract	Layers is an open source neural network toolkit aim at providing an easy way to implement modern neural networks. The main user target are students and to this end layers provides an easy scriptting language that can be early adopted. The user has to focus only on design details as network totpology and parameter tunning.
Tasks
Published	2016-10-05
URL	http://arxiv.org/abs/1610.01430v2
PDF	http://arxiv.org/pdf/1610.01430v2.pdf
PWC	https://paperswithcode.com/paper/layers-yet-another-neural-network-toolkit
Repo
Framework

End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning


Title	End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
Authors	Jason D. Williams, Geoffrey Zweig
Abstract	This paper presents a model for end-to-end learning of task-oriented dialog systems. The main component of the model is a recurrent neural network (an LSTM), which maps from raw dialog history directly to a distribution over system actions. The LSTM automatically infers a representation of dialog history, which relieves the system developer of much of the manual feature engineering of dialog state. In addition, the developer can provide software that expresses business rules and provides access to programmatic APIs, enabling the LSTM to take actions in the real world on behalf of the user. The LSTM can be optimized using supervised learning (SL), where a domain expert provides example dialogs which the LSTM should imitate; or using reinforcement learning (RL), where the system improves by interacting directly with end users. Experiments show that SL and RL are complementary: SL alone can derive a reasonable initial policy from a small number of training dialogs; and starting RL optimization with a policy trained with SL substantially accelerates the learning rate of RL.
Tasks	Feature Engineering
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01269v1
PDF	http://arxiv.org/pdf/1606.01269v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-lstm-based-dialog-control
Repo
Framework

Revisiting Active Perception


Title	Revisiting Active Perception
Authors	Ruzena Bajcsy, Yiannis Aloimonos, John K. Tsotsos
Abstract	Despite the recent successes in robotics, artificial intelligence and computer vision, a complete artificial agent necessarily must include active perception. A multitude of ideas and methods for how to accomplish this have already appeared in the past, their broader utility perhaps impeded by insufficient computational power or costly hardware. The history of these ideas, perhaps selective due to our perspectives, is presented with the goal of organizing the past literature and highlighting the seminal contributions. We argue that those contributions are as relevant today as they were decades ago and, with the state of modern computational tools, are poised to find new life in the robotic perception systems of the next decade.
Tasks
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02729v2
PDF	http://arxiv.org/pdf/1603.02729v2.pdf
PWC	https://paperswithcode.com/paper/revisiting-active-perception
Repo
Framework

Synthetic Language Generation and Model Validation in BEAST2


Title	Synthetic Language Generation and Model Validation in BEAST2
Authors	Stuart Bradley
Abstract	Generating synthetic languages aids in the testing and validation of future computational linguistic models and methods. This thesis extends the BEAST2 phylogenetic framework to add linguistic sequence generation under multiple models. The new plugin is then used to test the effects of the phenomena of word borrowing on the inference process under two widely used phylolinguistic models.
Tasks	Text Generation
Published	2016-07-27
URL	http://arxiv.org/abs/1607.07931v1
PDF	http://arxiv.org/pdf/1607.07931v1.pdf
PWC	https://paperswithcode.com/paper/synthetic-language-generation-and-model
Repo
Framework

Robust Bayesian Compressed sensing


Title	Robust Bayesian Compressed sensing
Authors	Qian Wan, Huiping Duan, Jun Fang, Hongbin Li
Abstract	We consider the problem of robust compressed sensing whose objective is to recover a high-dimensional sparse signal from compressed measurements corrupted by outliers. A new sparse Bayesian learning method is developed for robust compressed sensing. The basic idea of the proposed method is to identify and remove the outliers from sparse signal recovery. To automatically identify the outliers, we employ a set of binary indicator hyperparameters to indicate which observations are outliers. These indicator hyperparameters are treated as random variables and assigned a beta process prior such that their values are confined to be binary. In addition, a Gaussian-inverse Gamma prior is imposed on the sparse signal to promote sparsity. Based on this hierarchical prior model, we develop a variational Bayesian method to estimate the indicator hyperparameters as well as the sparse signal. Simulation results show that the proposed method achieves a substantial performance improvement over existing robust compressed sensing techniques.
Tasks
Published	2016-10-10
URL	http://arxiv.org/abs/1610.02807v2
PDF	http://arxiv.org/pdf/1610.02807v2.pdf
PWC	https://paperswithcode.com/paper/robust-bayesian-compressed-sensing
Repo
Framework

Interaction pursuit in high-dimensional multi-response regression via distance correlation


Title	Interaction pursuit in high-dimensional multi-response regression via distance correlation
Authors	Yinfei Kong, Daoji Li, Yingying Fan, Jinchi Lv
Abstract	Feature interactions can contribute to a large proportion of variation in many prediction models. In the era of big data, the coexistence of high dimensionality in both responses and covariates poses unprecedented challenges in identifying important interactions. In this paper, we suggest a two-stage interaction identification method, called the interaction pursuit via distance correlation (IPDC), in the setting of high-dimensional multi-response interaction models that exploits feature screening applied to transformed variables with distance correlation followed by feature selection. Such a procedure is computationally efficient, generally applicable beyond the heredity assumption, and effective even when the number of responses diverges with the sample size. Under mild regularity conditions, we show that this method enjoys nice theoretical properties including the sure screening property, support union recovery, and oracle inequalities in prediction and estimation for both interactions and main effects. The advantages of our method are supported by several simulation studies and real data analysis.
Tasks	Feature Selection
Published	2016-05-11
URL	http://arxiv.org/abs/1605.03315v1
PDF	http://arxiv.org/pdf/1605.03315v1.pdf
PWC	https://paperswithcode.com/paper/interaction-pursuit-in-high-dimensional-multi
Repo
Framework

Neural Networks with Smooth Adaptive Activation Functions for Regression


Title	Neural Networks with Smooth Adaptive Activation Functions for Regression
Authors	Le Hou, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, Joel H. Saltz
Abstract	In Neural Networks (NN), Adaptive Activation Functions (AAF) have parameters that control the shapes of activation functions. These parameters are trained along with other parameters in the NN. AAFs have improved performance of Neural Networks (NN) in multiple classification tasks. In this paper, we propose and apply AAFs on feedforward NNs for regression tasks. We argue that applying AAFs in the regression (second-to-last) layer of a NN can significantly decrease the bias of the regression NN. However, using existing AAFs may lead to overfitting. To address this problem, we propose a Smooth Adaptive Activation Function (SAAF) with piecewise polynomial form which can approximate any continuous function to arbitrary degree of error. NNs with SAAFs can avoid overfitting by simply regularizing the parameters. In particular, an NN with SAAFs is Lipschitz continuous given a bounded magnitude of the NN parameters. We prove an upper-bound for model complexity in terms of fat-shattering dimension for any Lipschitz continuous regression model. Thus, regularizing the parameters in NNs with SAAFs avoids overfitting. We empirically evaluated NNs with SAAFs and achieved state-of-the-art results on multiple regression datasets.
Tasks
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06557v1
PDF	http://arxiv.org/pdf/1608.06557v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-with-smooth-adaptive
Repo
Framework

Longitudinal Analysis of Discussion Topics in an Online Breast Cancer Community using Convolutional Neural Networks


Title	Longitudinal Analysis of Discussion Topics in an Online Breast Cancer Community using Convolutional Neural Networks
Authors	Shaodian Zhang, Edouard Grave, Elizabeth Sklar, Noemie Elhadad
Abstract	Identifying topics of discussions in online health communities (OHC) is critical to various applications, but can be difficult because topics of OHC content are usually heterogeneous and domain-dependent. In this paper, we provide a multi-class schema, an annotated dataset, and supervised classifiers based on convolutional neural network (CNN) and other models for the task of classifying discussion topics. We apply the CNN classifier to the most popular breast cancer online community, and carry out a longitudinal analysis to show topic distributions and topic changes throughout members’ participation. Our experimental results suggest that CNN outperforms other classifiers in the task of topic classification, and that certain trajectories can be detected with respect to topic changes.
Tasks
Published	2016-03-28
URL	http://arxiv.org/abs/1603.08458v3
PDF	http://arxiv.org/pdf/1603.08458v3.pdf
PWC	https://paperswithcode.com/paper/longitudinal-analysis-of-discussion-topics-in
Repo
Framework

Why (and How) Avoid Orthogonal Procrustes in Regularized Multivariate Analysis


Title	Why (and How) Avoid Orthogonal Procrustes in Regularized Multivariate Analysis
Authors	Sergio Muñoz-Romero, Vanessa Gómez-Verdejo, Jerónimo Arenas-García
Abstract	Multivariate Analysis (MVA) comprises a family of well-known methods for feature extraction that exploit correlations among input variables of the data representation. One important property that is enjoyed by most such methods is uncorrelation among the extracted features. Recently, regularized versions of MVA methods have appeared in the literature, mainly with the goal to gain interpretability of the solution. In these cases, the solutions can no longer be obtained in a closed manner, and it is frequent to recur to the iteration of two steps, one of them being an orthogonal Procrustes problem. This letter shows that the Procrustes solution is not optimal from the perspective of the overall MVA method, and proposes an alternative approach based on the solution of an eigenvalue problem. Our method ensures the preservation of several properties of the original methods, most notably the uncorrelation of the extracted features, as demonstrated theoretically and through a collection of selected experiments.
Tasks
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02674v2
PDF	http://arxiv.org/pdf/1605.02674v2.pdf
PWC	https://paperswithcode.com/paper/why-and-how-avoid-orthogonal-procrustes-in
Repo
Framework

Inverting Variational Autoencoders for Improved Generative Accuracy


Title	Inverting Variational Autoencoders for Improved Generative Accuracy
Authors	Ian Gemp, Ishan Durugkar, Mario Parente, M. Darby Dyar, Sridhar Mahadevan
Abstract	Recent advances in semi-supervised learning with deep generative models have shown promise in generalizing from small labeled datasets ($\mathbf{x},\mathbf{y}$) to large unlabeled ones ($\mathbf{x}$). In the case where the codomain has known structure, a large unfeatured dataset ($\mathbf{y}$) is potentially available. We develop a parameter-efficient, deep semi-supervised generative model for the purpose of exploiting this untapped data source. Empirical results show improved performance in disentangling latent variable semantics as well as improved discriminative prediction on Martian spectroscopic and handwritten digit domains.
Tasks
Published	2016-08-21
URL	http://arxiv.org/abs/1608.05983v2
PDF	http://arxiv.org/pdf/1608.05983v2.pdf
PWC	https://paperswithcode.com/paper/inverting-variational-autoencoders-for
Repo
Framework

Bots as Virtual Confederates: Design and Ethics


Title	Bots as Virtual Confederates: Design and Ethics
Authors	Peter M Krafft, Michael Macy, Alex Pentland
Abstract	The use of bots as virtual confederates in online field experiments holds extreme promise as a new methodological tool in computational social science. However, this potential tool comes with inherent ethical challenges. Informed consent can be difficult to obtain in many cases, and the use of confederates necessarily implies the use of deception. In this work we outline a design space for bots as virtual confederates, and we propose a set of guidelines for meeting the status quo for ethical experimentation. We draw upon examples from prior work in the CSCW community and the broader social science literature for illustration. While a handful of prior researchers have used bots in online experimentation, our work is meant to inspire future work in this area and raise awareness of the associated ethical issues.
Tasks
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00447v1
PDF	http://arxiv.org/pdf/1611.00447v1.pdf
PWC	https://paperswithcode.com/paper/bots-as-virtual-confederates-design-and
Repo
Framework