Paper Group ANR 1041
Advances of Scene Text Datasets. Learning to Recognize Discontiguous Entities. RedSync : Reducing Synchronization Traffic for Distributed Deep Learning. Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector. Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score …
Advances of Scene Text Datasets
| Title | Advances of Scene Text Datasets |
| Authors | Masakazu Iwamura |
| Abstract | This article introduces publicly available datasets in scene text detection and recognition. The information is as of 2017. |
| Tasks | Scene Text Detection |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05219v1 |
| http://arxiv.org/pdf/1812.05219v1.pdf | |
| PWC | https://paperswithcode.com/paper/advances-of-scene-text-datasets |
| Repo | |
| Framework | |
Learning to Recognize Discontiguous Entities
| Title | Learning to Recognize Discontiguous Entities |
| Authors | Aldrian Obaja Muis, Wei Lu |
| Abstract | This paper focuses on the study of recognizing discontiguous entities. Motivated by a previous work, we propose to use a novel hypergraph representation to jointly encode discontiguous entities of unbounded length, which can overlap with one another. To compare with existing approaches, we first formally introduce the notion of model ambiguity, which defines the difficulty level of interpreting the outputs of a model, and then formally analyze the theoretical advantages of our model over previous existing approaches based on linear-chain CRFs. Our empirical results also show that our model is able to achieve significantly better results when evaluated on standard data with many discontiguous entities. |
| Tasks | |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08579v1 |
| http://arxiv.org/pdf/1810.08579v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-recognize-discontiguous-entities |
| Repo | |
| Framework | |
RedSync : Reducing Synchronization Traffic for Distributed Deep Learning
| Title | RedSync : Reducing Synchronization Traffic for Distributed Deep Learning |
| Authors | Jiarui Fang, Haohuan Fu, Guangwen Yang, Cho-Jui Hsieh |
| Abstract | Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes. Since synchronizing a large number of gradients of the local model can be a bottleneck for large-scale distributed training, compressing communication data has gained widespread attention recently. Among several recent proposed compression algorithms, Residual Gradient Compression (RGC) is one of the most successful approaches—it can significantly compress the transmitting message size (0.1% of the gradient size) of each node and still achieve correct accuracy and the same convergence speed. However, the literature on compressing deep networks focuses almost exclusively on achieving good theoretical compression rate, while the efficiency of RGC in real distributed implementation has been less investigated. In this paper, we develop an RGC-based system that is able to reduce the end-to-end training time on real-world multi-GPU systems. Our proposed design called RedSync, which introduces a set of optimizations to reduce communication bandwidth requirement while introducing limited overhead. We evaluate the performance of RedSync on two different multiple GPU platforms, including 128 GPUs of a supercomputer and an 8-GPU server. Our test cases include image classification tasks on Cifar10 and ImageNet, and language modeling tasks on Penn Treebank and Wiki2 datasets. For DNNs featured with high communication to computation ratio, which have long been considered with poor scalability, RedSync brings significant performance improvements. |
| Tasks | Image Classification, Language Modelling |
| Published | 2018-08-13 |
| URL | https://arxiv.org/abs/1808.04357v3 |
| https://arxiv.org/pdf/1808.04357v3.pdf | |
| PWC | https://paperswithcode.com/paper/redsync-reducing-synchronization-traffic-for |
| Repo | |
| Framework | |
Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
| Title | Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector |
| Authors | Chen Du, Chunheng Wang, Yanna Wang, Cunzhao Shi, Baihua Xiao |
| Abstract | Different layers of deep convolutional neural networks(CNNs) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. If directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information. In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low-level features are selectively linked to high-level features with a feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on multiple challenging computer vision tasks, including image classification, scene text detection, and image-to-image translation. |
| Tasks | Image Classification, Image-to-Image Translation, Scene Text Detection |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06295v3 |
| http://arxiv.org/pdf/1811.06295v3.pdf | |
| PWC | https://paperswithcode.com/paper/selective-feature-connection-mechanism |
| Repo | |
| Framework | |
Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score
| Title | Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score |
| Authors | Yang Ning, Sida Peng, Kosuke Imai |
| Abstract | In this paper, we propose a robust method to estimate the average treatment effects in observational studies when the number of potential confounders is possibly much greater than the sample size. We first use a class of penalized M-estimators for the propensity score and outcome models. We then calibrate the initial estimate of the propensity score by balancing a carefully selected subset of covariates that are predictive of the outcome. Finally, the estimated propensity score is used to construct the inverse probability weighting estimator. We prove that the proposed estimator, which has the sample boundedness property, is root-n consistent, asymptotically normal, and semiparametrically efficient when the propensity score model is correctly specified and the outcome model is linear in covariates. More importantly, we show that our estimator remains root-n consistent and asymptotically normal so long as either the propensity score model or the outcome model is correctly specified. We provide valid confidence intervals in both cases and further extend these results to the case where the outcome model is a generalized linear model. In simulation studies, we find that the proposed methodology often estimates the average treatment effect more accurately than the existing methods. We also present an empirical application, in which we estimate the average causal effect of college attendance on adulthood political participation. Open-source software is available for implementing the proposed methodology. |
| Tasks | |
| Published | 2018-12-20 |
| URL | http://arxiv.org/abs/1812.08683v1 |
| http://arxiv.org/pdf/1812.08683v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-estimation-of-causal-effects-via-high |
| Repo | |
| Framework | |
Bayesian Classifier for Route Prediction with Markov Chains
| Title | Bayesian Classifier for Route Prediction with Markov Chains |
| Authors | Jonathan P. Epperlein, Julien Monteil, Mingming Liu, Yingqi Gu, Sergiy Zhuk, Robert Shorten |
| Abstract | We present here a general framework and a specific algorithm for predicting the destination, route, or more generally a pattern, of an ongoing journey, building on the recent work of [Y. Lassoued, J. Monteil, Y. Gu, G. Russo, R. Shorten, and M. Mevissen, “Hidden Markov model for route and destination prediction,” in IEEE International Conference on Intelligent Transportation Systems, 2017]. In the presented framework, known journey patterns are modelled as stochastic processes, emitting the road segments visited during the journey, and the ongoing journey is predicted by updating the posterior probability of each journey pattern given the road segments visited so far. In this contribution, we use Markov chains as models for the journey patterns, and consider the prediction as final, once one of the posterior probabilities crosses a predefined threshold. Despite the simplicity of both, examples run on a synthetic dataset demonstrate high accuracy of the made predictions. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1808.10705v1 |
| http://arxiv.org/pdf/1808.10705v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-classifier-for-route-prediction-with |
| Repo | |
| Framework | |
Maturation Trajectories of Cortical Resting-State Networks Depend on the Mediating Frequency Band
| Title | Maturation Trajectories of Cortical Resting-State Networks Depend on the Mediating Frequency Band |
| Authors | Sheraz Khan, Javeria Hashmi, Fahimeh Mamashli, Konstantinos Michmizos, Manfred Kitzbichler, Hari Bharadwaj, Yousra Bekhti, Santosh Ganesan, Keri A Garel, Susan Whitfield-Gabrieli, Randy Gollub, Jian Kong, Lucia M Vaina, Kunjan Rana, Steven Stufflebeam, Matti Hamalainen, Tal Kenet |
| Abstract | The functional significance of resting state networks and their abnormal manifestations in psychiatric disorders are firmly established, as is the importance of the cortical rhythms in mediating these networks. Resting state networks are known to undergo substantial reorganization from childhood to adulthood, but whether distinct cortical rhythms, which are generated by separable neural mechanisms and are often manifested abnormally in psychiatric conditions, mediate maturation differentially, remains unknown. Using magnetoencephalography (MEG) to map frequency band specific maturation of resting state networks from age 7 to 29 in 162 participants (31 independent), we found significant changes with age in networks mediated by the beta (13-30Hz) and gamma (31-80Hz) bands. More specifically, gamma band mediated networks followed an expected asymptotic trajectory, but beta band mediated networks followed a linear trajectory. Network integration increased with age in gamma band mediated networks, while local segregation increased with age in beta band mediated networks. Spatially, the hubs that changed in importance with age in the beta band mediated networks had relatively little overlap with those that showed the greatest changes in the gamma band mediated networks. These findings are relevant for our understanding of the neural mechanisms of cortical maturation, in both typical and atypical development. |
| Tasks | |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1803.04364v1 |
| http://arxiv.org/pdf/1803.04364v1.pdf | |
| PWC | https://paperswithcode.com/paper/maturation-trajectories-of-cortical-resting |
| Repo | |
| Framework | |
Global linear convergence of Newton’s method without strong-convexity or Lipschitz gradients
| Title | Global linear convergence of Newton’s method without strong-convexity or Lipschitz gradients |
| Authors | Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi |
| Abstract | We show that Newton’s method converges globally at a linear rate for objective functions whose Hessians are stable. This class of problems includes many functions which are not strongly convex, such as logistic regression. Our linear convergence result is (i) affine-invariant, and holds even if an (ii) approximate Hessian is used, and if the subproblems are (iii) only solved approximately. Thus we theoretically demonstrate the superiority of Newton’s method over first-order methods, which would only achieve a sublinear $O(1/t^2)$ rate under similar conditions. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00413v1 |
| http://arxiv.org/pdf/1806.00413v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-linear-convergence-of-newtons-method |
| Repo | |
| Framework | |
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages
| Title | WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages |
| Authors | Abhik Jana, Pranjal Kanojiya, Pawan Goyal, Animesh Mukherjee |
| Abstract | The exponential increase in the usage of Wikipedia as a key source of scientific knowledge among the researchers is making it absolutely necessary to metamorphose this knowledge repository into an integral and self-contained source of information for direct utilization. Unfortunately, the references which support the content of each Wikipedia entity page, are far from complete. Why are the reference section ill-formed for most Wikipedia pages? Is this section edited as frequently as the other sections of a page? Can there be appropriate surrogates that can automatically enhance the reference section? In this paper, we propose a novel two step approach – WikiRef – that (i) leverages the wikilinks present in a scientific Wikipedia target page and, thereby, (ii) recommends highly relevant references to be included in that target page appropriately and automatically borrowed from the reference section of the wikilinks. In the first step, we build a classifier to ascertain whether a wikilink is a potential source of reference or not. In the following step, we recommend references to the target page from the reference section of the wikilinks that are classified as potential sources of references in the first step. We perform an extensive evaluation of our approach on datasets from two different domains – Computer Science and Physics. For Computer Science we achieve a notably good performance with a precision@1 of 0.44 for reference recommendation as opposed to 0.38 obtained from the most competitive baseline. For the Physics dataset, we obtain a similar performance boost of 10% with respect to the most competitive baseline. |
| Tasks | |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.04092v2 |
| http://arxiv.org/pdf/1806.04092v2.pdf | |
| PWC | https://paperswithcode.com/paper/wikiref-wikilinks-as-a-route-to-recommending |
| Repo | |
| Framework | |
Spatial Fusion GAN for Image Synthesis
| Title | Spatial Fusion GAN for Image Synthesis |
| Authors | Fangneng Zhan, Hongyuan Zhu, Shijian Lu |
| Abstract | Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry space but few in both. This paper presents an innovative Spatial Fusion GAN (SF-GAN) that combines a geometry synthesizer and an appearance synthesizer to achieve synthesis realism in both geometry and appearance spaces. The geometry synthesizer learns contextual geometries of background images and transforms and places foreground objects into the background images unanimously. The appearance synthesizer adjusts the color, brightness and styles of the foreground objects and embeds them into background images harmoniously, where a guided filter is introduced for detail preserving. The two synthesizers are inter-connected as mutual references which can be trained end-to-end without supervision. The SF-GAN has been evaluated in two tasks: (1) realistic scene text image synthesis for training better recognition models; (2) glass and hat wearing for realistic matching glasses and hats with real portraits. Qualitative and quantitative comparisons with the state-of-the-art demonstrate the superiority of the proposed SF-GAN. |
| Tasks | Image Generation |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.05840v3 |
| http://arxiv.org/pdf/1812.05840v3.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-fusion-gan-for-image-synthesis |
| Repo | |
| Framework | |
Neural network feedback controller for inertial platform
| Title | Neural network feedback controller for inertial platform |
| Authors | Yan Anisimov, Alexandr Lysov, Dmitry Katsai |
| Abstract | The paper describes an algorithm for the synthesis of neural networks to control gyro stabilizer. The neural network performs the role of observer for state vector. The role of an observer in a feedback of gyro stabilizer is illustrated. Paper detail a problem specific features stage of classics algorithm: choosing of network architecture, learning of neural network and verification of result feedback control. In the article presented optimal configuration of the neural network like a memory depth, the number of layers and neuron in these layers and activation functions in layers. Using the information of dynamic system for improving learning of neural network is provided. A scheme creation of an optimal training sample is provided. |
| Tasks | |
| Published | 2018-03-07 |
| URL | http://arxiv.org/abs/1803.02738v2 |
| http://arxiv.org/pdf/1803.02738v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-feedback-controller-for |
| Repo | |
| Framework | |
Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization
| Title | Katyusha X: Practical Momentum Method for Stochastic Sum-of-Nonconvex Optimization |
| Authors | Zeyuan Allen-Zhu |
| Abstract | The problem of minimizing sum-of-nonconvex functions (i.e., convex functions that are average of non-convex ones) is becoming increasingly important in machine learning, and is the core machinery for PCA, SVD, regularized Newton’s method, accelerated non-convex optimization, and more. We show how to provably obtain an accelerated stochastic algorithm for minimizing sum-of-nonconvex functions, by $\textit{adding one additional line}$ to the well-known SVRG method. This line corresponds to momentum, and shows how to directly apply momentum to the finite-sum stochastic minimization of sum-of-nonconvex functions. As a side result, our method enjoys linear parallel speed-up using mini-batch. |
| Tasks | |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.03866v1 |
| http://arxiv.org/pdf/1802.03866v1.pdf | |
| PWC | https://paperswithcode.com/paper/katyusha-x-practical-momentum-method-for |
| Repo | |
| Framework | |
Active Metric Learning for Supervised Classification
| Title | Active Metric Learning for Supervised Classification |
| Authors | Krishnan Kumaran, Dimitri Papageorgiou, Yutong Chang, Minhan Li, Martin Takáč |
| Abstract | Clustering and classification critically rely on distance metrics that provide meaningful comparisons between data points. We present mixed-integer optimization approaches to find optimal distance metrics that generalize the Mahalanobis metric extensively studied in the literature. Additionally, we generalize and improve upon leading methods by removing reliance on pre-designated “target neighbors,” “triplets,” and “similarity pairs.” Another salient feature of our method is its ability to enable active learning by recommending precise regions to sample after an optimal metric is computed to improve classification performance. This targeted acquisition can significantly reduce computational burden by ensuring training data completeness, representativeness, and economy. We demonstrate classification and computational performance of the algorithms through several simple and intuitive examples, followed by results on real image and medical datasets. |
| Tasks | Active Learning, Metric Learning |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10647v1 |
| http://arxiv.org/pdf/1803.10647v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-metric-learning-for-supervised |
| Repo | |
| Framework | |
Evolutionary framework for two-stage stochastic resource allocation problems
| Title | Evolutionary framework for two-stage stochastic resource allocation problems |
| Authors | Pedro H. D. B. Hokama, Mário C. San Felice, Evandro C. Bracht, Fábio L. Usberti |
| Abstract | Resource allocation problems are a family of problems in which resources must be selected to satisfy given demands. This paper focuses on the two-stage stochastic generalization of resource allocation problems where future demands are expressed in a finite number of possible scenarios. The goal is to select cost effective resources to be acquired in the present time (first stage), and to implement a complete solution for each scenario (second stage), while minimizing the total expected cost of the choices in both stages. We propose an evolutionary framework for solving general two-stage stochastic resource allocation problems. In each iteration of our framework, a local search algorithm selects resources to be acquired in the first stage. A genetic metaheuristic then completes the solutions for each scenario and relevant information is passed onto the next iteration, thereby supporting the acquisition of promising resources in the following first stage. Experimentation on numerous instances of the two-stage stochastic Steiner tree problem suggests that our evolutionary framework is powerful enough to address large instances of a wide variety of two-stage stochastic resource allocation problems. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1903.01885v1 |
| http://arxiv.org/pdf/1903.01885v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-framework-for-two-stage |
| Repo | |
| Framework | |
Exact multiplicative updates for convolutional $β$-NMF in 2D
| Title | Exact multiplicative updates for convolutional $β$-NMF in 2D |
| Authors | Pedro J. Villasana T., Stanislaw Gorlow |
| Abstract | In this paper, we extend the $\beta$-CNMF to two dimensions and derive exact multiplicative updates for its factors. The new updates generalize and correct the nonnegative matrix factor deconvolution previously proposed by Schmidt and M{\o}rup. We show by simulation that the updates lead to a monotonically decreasing $\beta$-divergence in terms of the mean and the standard deviation and that the corresponding convergence curves are consistent across the most common values for $\beta$. |
| Tasks | |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01661v1 |
| http://arxiv.org/pdf/1811.01661v1.pdf | |
| PWC | https://paperswithcode.com/paper/exact-multiplicative-updates-for |
| Repo | |
| Framework | |
