Paper Group ANR 420
A Simple Text Analytics Model To Assist Literary Criticism: comparative approach and example on James Joyce against Shakespeare and the Bible. Learning Deep Networks from Noisy Labels with Dropout Regularization. Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting. Particle Optimization in Stochastic Gradient MCMC. L …
A Simple Text Analytics Model To Assist Literary Criticism: comparative approach and example on James Joyce against Shakespeare and the Bible
| Title | A Simple Text Analytics Model To Assist Literary Criticism: comparative approach and example on James Joyce against Shakespeare and the Bible |
| Authors | Renato Fabbri, Luis Henrique Garcia |
| Abstract | Literary analysis, criticism or studies is a largely valued field with dedicated journals and researchers which remains mostly within the humanities scope. Text analytics is the computer-aided process of deriving information from texts. In this article we describe a simple and generic model for performing literary analysis using text analytics. The method relies on statistical measures of: 1) token and sentence sizes and 2) Wordnet synset features. These measures are then used in Principal Component Analysis where the texts to be analyzed are observed against Shakespeare and the Bible, regarded as reference literature. The model is validated by analyzing selected works from James Joyce (1882-1941), one of the most important writers of the 20th century. We discuss the consistency of this approach, the reasons why we did not use other techniques (e.g. part-of-speech tagging) and the ways by which the analysis model might be adapted and enhanced. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-10-24 |
| URL | http://arxiv.org/abs/1710.09233v1 |
| http://arxiv.org/pdf/1710.09233v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-text-analytics-model-to-assist |
| Repo | |
| Framework | |
Learning Deep Networks from Noisy Labels with Dropout Regularization
| Title | Learning Deep Networks from Noisy Labels with Dropout Regularization |
| Authors | Ishan Jindal, Matthew Nokleby, Xuewen Chen |
| Abstract | Large datasets often have unreliable labels-such as those obtained from Amazon’s Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment a standard deep network with a softmax layer that models the label noise statistics. Then, we train the deep network and noise model jointly via end-to-end stochastic gradient descent on the (perhaps mislabeled) dataset. The augmented model is overdetermined, so in order to encourage the learning of a non-trivial noise model, we apply dropout regularization to the weights of the noise model during training. Numerical experiments on noisy versions of the CIFAR-10 and MNIST datasets show that the proposed dropout technique outperforms state-of-the-art methods. |
| Tasks | |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03419v1 |
| http://arxiv.org/pdf/1705.03419v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-networks-from-noisy-labels-with |
| Repo | |
| Framework | |
Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting
| Title | Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting |
| Authors | Tim Dahmen, Patrick Trampert, Pascal Peter, Pinak Bheed, Joachim Weickert, Philipp Slusallek |
| Abstract | Exemplar-based inpainting is the process of reconstructing missing parts of an image by searching the remaining data for patches that fit seamlessly. The image is completed to a plausible-looking solution by repeatedly inserting the patch that is the best match according to some cost function. We present an acceleration structure that uses a multi-index scheme to accelerate this search procedure drastically, particularly in the case of very large datasets. The index scheme uses ideas such as dimensionality reduction and k-nearest neighbor search on space-filling curves that are well known in the field of multimedia databases. Our method has a theoretic runtime of O(log2 n) per iteration and reaches a speedup factor of up to 660 over the original method. The approach has the advantage of being agnostic to most modelbased parts of exemplar-based inpainting such as the order in which patches are processed and the cost function used to determine patch similarity. Thus, the acceleration structure can be used in conjunction with most exemplar-based inpainting algorithms. |
| Tasks | Dimensionality Reduction |
| Published | 2017-12-18 |
| URL | https://arxiv.org/abs/1712.06326v2 |
| https://arxiv.org/pdf/1712.06326v2.pdf | |
| PWC | https://paperswithcode.com/paper/space-filling-curve-indices-as-acceleration |
| Repo | |
| Framework | |
Particle Optimization in Stochastic Gradient MCMC
| Title | Particle Optimization in Stochastic Gradient MCMC |
| Authors | Changyou Chen, Ruiyi Zhang |
| Abstract | Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasingly popular in Bayesian learning due to its ability to deal with large data. A standard SG-MCMC algorithm simulates samples from a discretized-time Markov chain to approximate a target distribution. However, the samples are typically highly correlated due to the sequential generation process, an undesired property in SG-MCMC. In contrary, Stein variational gradient descent (SVGD) directly optimizes a set of particles, and it is able to approximate a target distribution with much fewer samples. In this paper, we propose a novel method to directly optimize particles (or samples) in SG-MCMC from scratch. Specifically, we propose efficient methods to solve the corresponding Fokker-Planck equation on the space of probability distributions, whose solution (i.e., a distribution) is approximated by particles. Through our framework, we are able to show connections of SG-MCMC to SVGD, as well as the seemly unrelated generative-adversarial-net framework. Under certain relaxations, particle optimization in SG-MCMC can be interpreted as an extension of standard SVGD with momentum. |
| Tasks | |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.10927v1 |
| http://arxiv.org/pdf/1711.10927v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-optimization-in-stochastic-gradient |
| Repo | |
| Framework | |
Learning to Identify Ambiguous and Misleading News Headlines
| Title | Learning to Identify Ambiguous and Misleading News Headlines |
| Authors | Wei Wei, Xiaojun Wan |
| Abstract | Accuracy is one of the basic principles of journalism. However, it is increasingly hard to manage due to the diversity of news media. Some editors of online news tend to use catchy headlines which trick readers into clicking. These headlines are either ambiguous or misleading, degrading the reading experience of the audience. Thus, identifying inaccurate news headlines is a task worth studying. Previous work names these headlines “clickbaits” and mainly focus on the features extracted from the headlines, which limits the performance since the consistency between headlines and news bodies is underappreciated. In this paper, we clearly redefine the problem and identify ambiguous and misleading headlines separately. We utilize class sequential rules to exploit structure information when detecting ambiguous headlines. For the identification of misleading headlines, we extract features based on the congruence between headlines and bodies. To make use of the large unlabeled data set, we apply a co-training method and gain an increase in performance. The experiment results show the effectiveness of our methods. Then we use our classifiers to detect inaccurate headlines crawled from different sources and conduct a data analysis. |
| Tasks | |
| Published | 2017-05-17 |
| URL | http://arxiv.org/abs/1705.06031v2 |
| http://arxiv.org/pdf/1705.06031v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-identify-ambiguous-and-misleading |
| Repo | |
| Framework | |
Constrained Bayesian Networks: Theory, Optimization, and Applications
| Title | Constrained Bayesian Networks: Theory, Optimization, and Applications |
| Authors | Paul Beaumont, Michael Huth |
| Abstract | We develop the theory and practice of an approach to modelling and probabilistic inference in causal networks that is suitable when application-specific or analysis-specific constraints should inform such inference or when little or no data for the learning of causal network structure or probability values at nodes are available. Constrained Bayesian Networks generalize a Bayesian Network such that probabilities can be symbolic, arithmetic expressions and where the meaning of the network is constrained by finitely many formulas from the theory of the reals. A formal semantics for constrained Bayesian Networks over first-order logic of the reals is given, which enables non-linear and non-convex optimisation algorithms that rely on decision procedures for this logic, and supports the composition of several constrained Bayesian Networks. A non-trivial case study in arms control, where few or no data are available to assess the effectiveness of an arms inspection process, evaluates our approach. An open-access prototype implementation of these foundations and their algorithms uses the SMT solver Z3 as decision procedure, leverages an open-source package for Bayesian inference to symbolic computation, and is evaluated experimentally. |
| Tasks | Bayesian Inference |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05326v1 |
| http://arxiv.org/pdf/1705.05326v1.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-bayesian-networks-theory |
| Repo | |
| Framework | |
Dynamic Zoom-in Network for Fast Object Detection in Large Images
| Title | Dynamic Zoom-in Network for Fast Object Detection in Large Images |
| Authors | Mingfei Gao, Ruichi Yu, Ang Li, Vlad I. Morariu, Larry S. Davis |
| Abstract | We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine manner, first on a down-sampled version of the image and then on a sequence of higher resolution regions identified as likely to improve the detection accuracy. Built upon reinforcement learning, our approach consists of a model (R-net) that uses coarse detection results to predict the potential accuracy gain for analyzing a region at a higher resolution and another model (Q-net) that sequentially selects regions to zoom in. Experiments on the Caltech Pedestrians dataset show that our approach reduces the number of processed pixels by over 50% without a drop in detection accuracy. The merits of our approach become more significant on a high resolution test set collected from YFCC100M dataset, where our approach maintains high detection performance while reducing the number of processed pixels by about 70% and the detection time by over 50%. |
| Tasks | Object Detection, Real-Time Object Detection |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05187v2 |
| http://arxiv.org/pdf/1711.05187v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-zoom-in-network-for-fast-object |
| Repo | |
| Framework | |
Cognitive networks: brains, internet, and civilizations
| Title | Cognitive networks: brains, internet, and civilizations |
| Authors | Dmitrii Yu. Manin, Yuri I. Manin |
| Abstract | In this short essay, we discuss some basic features of cognitive activity at several different space-time scales: from neural networks in the brain to civilizations. One motivation for such comparative study is its heuristic value. Attempts to better understand the functioning of “wetware” involved in cognitive activities of central nervous system by comparing it with a computing device have a long tradition. We suggest that comparison with Internet might be more adequate. We briefly touch upon such subjects as encoding, compression, and Saussurean trichotomy langue/langage/parole in various environments. |
| Tasks | |
| Published | 2017-09-10 |
| URL | http://arxiv.org/abs/1709.03114v1 |
| http://arxiv.org/pdf/1709.03114v1.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-networks-brains-internet-and |
| Repo | |
| Framework | |
Detection of bimanual gestures everywhere: why it matters, what we need and what is missing
| Title | Detection of bimanual gestures everywhere: why it matters, what we need and what is missing |
| Authors | Divya Shah, Ernesto Denicia, Tiago Pimentel, Barbara Bruno, Fulvio Mastrogiovanni |
| Abstract | Bimanual gestures are of the utmost importance for the study of motor coordination in humans and in everyday activities. A reliable detection of bimanual gestures in unconstrained environments is fundamental for their clinical study and to assess common activities of daily living. This paper investigates techniques for a reliable, unconstrained detection and classification of bimanual gestures. It assumes the availability of inertial data originating from the two hands/arms, builds upon a previously developed technique for gesture modelling based on Gaussian Mixture Modelling (GMM) and Gaussian Mixture Regression (GMR), and compares different modelling and classification techniques, which are based on a number of assumptions inspired by literature about how bimanual gestures are represented and modelled in the brain. Experiments show results related to 5 everyday bimanual activities, which have been selected on the basis of three main parameters: (not) constraining the two hands by a physical tool, (not) requiring a specific sequence of single-hand gestures, being recursive (or not). In the best performing combination of modeling approach and classification technique, five out of five activities are recognized up to an accuracy of 97%, a precision of 82% and a level of recall of 100%. |
| Tasks | |
| Published | 2017-07-09 |
| URL | http://arxiv.org/abs/1707.02605v1 |
| http://arxiv.org/pdf/1707.02605v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-bimanual-gestures-everywhere-why |
| Repo | |
| Framework | |
Clothing Retrieval with Visual Attention Model
| Title | Clothing Retrieval with Visual Attention Model |
| Authors | Zhonghao Wang, Yujun Gu, Ya Zhang, Jun Zhou, Xiao Gu |
| Abstract | Clothing retrieval is a challenging problem in computer vision. With the advance of Convolutional Neural Networks (CNNs), the accuracy of clothing retrieval has been significantly improved. FashionNet[1], a recent study, proposes to employ a set of artificial features in the form of landmarks for clothing retrieval, which are shown to be helpful for retrieval. However, the landmark detection module is trained with strong supervision which requires considerable efforts to obtain. In this paper, we propose a self-learning Visual Attention Model (VAM) to extract attention maps from clothing images. The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map. Extensive experiments on several widely used benchmark clothing retrieval data sets have demonstrated the promise of the proposed method. We also show that compared to the trivial Product connection, the Impdrop connection makes the network structure more robust when training sets of limited size are used. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11446v1 |
| http://arxiv.org/pdf/1710.11446v1.pdf | |
| PWC | https://paperswithcode.com/paper/clothing-retrieval-with-visual-attention |
| Repo | |
| Framework | |
Improved Training for Self-Training by Confidence Assessments
| Title | Improved Training for Self-Training by Confidence Assessments |
| Authors | Gal Hyams, Daniel Greenfeld, Dor Bank |
| Abstract | It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training on a limited labeled data set. The suggested approach can be used as an online learning method on the unlabeled test set. In the general classification task, whenever we predict a label with high enough confidence, we treat it as a true label and train the data accordingly. For the semantic segmentation task, a classic example for an expensive data labeling process, we do so pixel-wise. Our suggested approaches were applied on the MNIST data-set as a proof of concept for a vision classification task and on the ADE20K data-set in order to tackle the semi-supervised semantic segmentation problem. |
| Tasks | Semantic Segmentation, Semi-Supervised Semantic Segmentation |
| Published | 2017-09-30 |
| URL | http://arxiv.org/abs/1710.00209v2 |
| http://arxiv.org/pdf/1710.00209v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-training-for-self-training-by |
| Repo | |
| Framework | |
FOIL it! Find One mismatch between Image and Language caption
| Title | FOIL it! Find One mismatch between Image and Language caption |
| Authors | Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich, Aurelie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi |
| Abstract | In this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities. To this end, we propose an extension of the MSCOCO dataset, FOIL-COCO, which associates images with both correct and “foil” captions, that is, descriptions of the image that are highly similar to the original ones, but contain one single mistake (“foil word”). We show that current LaVi models fall into the traps of this data and perform badly on three tasks: a) caption classification (correct vs. foil); b) foil word detection; c) foil word correction. Humans, in contrast, have near-perfect performance on those tasks. We demonstrate that merely utilising language cues is not enough to model FOIL-COCO and that it challenges the state-of-the-art by requiring a fine-grained understanding of the relation between text and image. |
| Tasks | |
| Published | 2017-05-03 |
| URL | http://arxiv.org/abs/1705.01359v1 |
| http://arxiv.org/pdf/1705.01359v1.pdf | |
| PWC | https://paperswithcode.com/paper/foil-it-find-one-mismatch-between-image-and |
| Repo | |
| Framework | |
SGAN: An Alternative Training of Generative Adversarial Networks
| Title | SGAN: An Alternative Training of Generative Adversarial Networks |
| Authors | Tatjana Chavdarova, François Fleuret |
| Abstract | The Generative Adversarial Networks (GANs) have demonstrated impressive performance for data synthesis, and are now used in a wide range of computer vision tasks. In spite of this success, they gained a reputation for being difficult to train, what results in a time-consuming and human-involved development process to use them. We consider an alternative training process, named SGAN, in which several adversarial “local” pairs of networks are trained independently so that a “global” supervising pair of networks can be trained against them. The goal is to train the global pair with the corresponding ensemble opponent for improved performances in terms of mode coverage. This approach aims at increasing the chances that learning will not stop for the global pair, preventing both to be trapped in an unsatisfactory local minimum, or to face oscillations often observed in practice. To guarantee the latter, the global pair never affects the local ones. The rules of SGAN training are thus as follows: the global generator and discriminator are trained using the local discriminators and generators, respectively, whereas the local networks are trained with their fixed local opponent. Experimental results on both toy and real-world problems demonstrate that this approach outperforms standard training in terms of better mitigating mode collapse, stability while converging and that it surprisingly, increases the convergence speed as well. |
| Tasks | |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.02330v1 |
| http://arxiv.org/pdf/1712.02330v1.pdf | |
| PWC | https://paperswithcode.com/paper/sgan-an-alternative-training-of-generative |
| Repo | |
| Framework | |
High SNR Consistent Compressive Sensing
| Title | High SNR Consistent Compressive Sensing |
| Authors | Sreejith Kallummil, Sheetal Kalyani |
| Abstract | High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subset selection procedures (SSPs) is applicable to linear regression with full rank measurement matrices only. Hence, the performance of SSPs used in underdetermined linear models (a.k.a compressive sensing (CS) algorithms) at high SNR is largely unknown. This paper fills this gap by deriving necessary and sufficient conditions for the high SNR consistency of popular CS algorithms like $l_0$-minimization, basis pursuit de-noising or LASSO, orthogonal matching pursuit and Dantzig selector. Necessary conditions analytically establish the high SNR inconsistency of CS algorithms when used with the tuning parameters discussed in literature. Novel tuning parameters with SNR adaptations are developed using the sufficient conditions and the choice of SNR adaptations are discussed analytically using convergence rate analysis. CS algorithms with the proposed tuning parameters are numerically shown to be high SNR consistent and outperform existing tuning parameters in the moderate to high SNR regime. |
| Tasks | Compressive Sensing, Model Selection |
| Published | 2017-03-10 |
| URL | http://arxiv.org/abs/1703.03596v1 |
| http://arxiv.org/pdf/1703.03596v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-snr-consistent-compressive-sensing |
| Repo | |
| Framework | |
A Fast HOG Descriptor Using Lookup Table and Integral Image
| Title | A Fast HOG Descriptor Using Lookup Table and Integral Image |
| Authors | Chunde Huang, Jiaxiang Huang |
| Abstract | The histogram of oriented gradients (HOG) is a widely used feature descriptor in computer vision for the purpose of object detection. In the paper, a modified HOG descriptor is described, it uses a lookup table and the method of integral image to speed up the detection performance by a factor of 5~10. By exploiting the special hardware features of a given platform(e.g. a digital signal processor), further improvement can be made to the HOG descriptor in order to have real-time object detection and tracking. |
| Tasks | Object Detection, Real-Time Object Detection |
| Published | 2017-03-18 |
| URL | http://arxiv.org/abs/1703.06256v1 |
| http://arxiv.org/pdf/1703.06256v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fast-hog-descriptor-using-lookup-table-and |
| Repo | |
| Framework | |
