Paper Group ANR 237
SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder. Exploitation of Semantic Keywords for Malicious Event Classification. Generation and Pruning of Pronunciation Variants to Improve ASR Accuracy. On the Resistance of Nearest Neighbor to Random Noisy Labels. Reverse Engineering and Symbolic Knowledge Extraction …
SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder
| Title | SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder |
| Authors | Noura Al Moubayed, Toby Breckon, Peter Matthews, A. Stephen McGough |
| Abstract | In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages. Our approach requires minimum features engineering and a small set of la- belled data samples. Features are extracted using topic modelling based on latent Dirichlet allocation, and then a comprehensive data model is created using a Stacked Denoising Autoencoder (SDA). Topic modelling summarises the data providing ease of use and high interpretability by visualising the topics using word clouds. Given that the SMS messages can be regarded as either spam (unwanted) or ham (wanted), the SDA is able to model the messages and accurately discriminate between the two classes without the need for a pre-labelled training set. The results are compared against the state-of-the-art spam detection algorithms with our proposed approach achieving over 97% accuracy which compares favourably to the best reported algorithms presented in the literature. |
| Tasks | Denoising |
| Published | 2016-06-17 |
| URL | http://arxiv.org/abs/1606.05554v1 |
| http://arxiv.org/pdf/1606.05554v1.pdf | |
| PWC | https://paperswithcode.com/paper/sms-spam-filtering-using-probabilistic-topic |
| Repo | |
| Framework | |
Exploitation of Semantic Keywords for Malicious Event Classification
| Title | Exploitation of Semantic Keywords for Malicious Event Classification |
| Authors | Hyungtae Lee, Sungmin Eum, Joel Levis, Heesung Kwon, James Michaelis, Michael Kolodny |
| Abstract | Learning an event classifier is challenging when the scenes are semantically different but visually similar. However, as humans, we typically handle such tasks painlessly by adding our background semantic knowledge. Motivated by this observation, we aim to provide an empirical study about how additional information such as semantic keywords can boost up the discrimination of such events. To demonstrate the validity of this study, we first construct a novel Malicious Crowd Dataset containing crowd images with two events, benign and malicious, which look visually similar. Note that the primary focus of this paper is not to provide the state-of-the-art performance on this dataset but to show the beneficial aspects of using semantically-driven keyword information. By leveraging crowd-sourcing platforms, such as Amazon Mechanical Turk, we collect semantic keywords associated with images and then subsequently identify a subset of keywords (e.g. police, fire, etc.) unique to specific events. We first show that by using recently introduced attention models, a naive CNN-based event classifier actually learns to primarily focus on local attributes associated with the discriminant semantic keywords identified by the Turks. We further show that incorporating the keyword-driven information into early- and late-fusion approaches can significantly enhance malicious event classification. |
| Tasks | |
| Published | 2016-10-21 |
| URL | http://arxiv.org/abs/1610.06903v2 |
| http://arxiv.org/pdf/1610.06903v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploitation-of-semantic-keywords-for |
| Repo | |
| Framework | |
Generation and Pruning of Pronunciation Variants to Improve ASR Accuracy
| Title | Generation and Pruning of Pronunciation Variants to Improve ASR Accuracy |
| Authors | Zhenhao Ge, Aravind Ganapathiraju, Ananth N. Iyer, Scott A. Randal, Felix I. Wyss |
| Abstract | Speech recognition, especially name recognition, is widely used in phone services such as company directory dialers, stock quote providers or location finders. It is usually challenging due to pronunciation variations. This paper proposes an efficient and robust data-driven technique which automatically learns acceptable word pronunciations and updates the pronunciation dictionary to build a better lexicon without affecting recognition of other words similar to the target word. It generalizes well on datasets with various sizes, and reduces the error rate on a database with 13000+ human names by 42%, compared to a baseline with regular dictionaries already covering canonical pronunciations of 97%+ words in names, plus a well-trained spelling-to-pronunciation (STP) engine. |
| Tasks | Speech Recognition |
| Published | 2016-06-28 |
| URL | http://arxiv.org/abs/1606.08821v1 |
| http://arxiv.org/pdf/1606.08821v1.pdf | |
| PWC | https://paperswithcode.com/paper/generation-and-pruning-of-pronunciation |
| Repo | |
| Framework | |
On the Resistance of Nearest Neighbor to Random Noisy Labels
| Title | On the Resistance of Nearest Neighbor to Random Noisy Labels |
| Authors | Wei Gao, Bin-Bin Yang, Zhi-Hua Zhou |
| Abstract | Nearest neighbor has always been one of the most appealing non-parametric approaches in machine learning, pattern recognition, computer vision, etc. Previous empirical studies partly shows that nearest neighbor is resistant to noise, yet there is a lack of deep analysis. This work presents the finite-sample and distribution-dependent bounds on the consistency of nearest neighbor in the random noise setting. The theoretical results show that, for asymmetric noises, k-nearest neighbor is robust enough to classify most data correctly, except for a handful of examples, whose labels are totally misled by random noises. For symmetric noises, however, k-nearest neighbor achieves the same consistent rate as that of noise-free setting, which verifies the resistance of k-nearest neighbor to random noisy labels. Motivated by the theoretical analysis, we propose the Robust k-Nearest Neighbor (RkNN) approach to deal with noisy labels. The basic idea is to make unilateral corrections to examples, whose labels are totally misled by random noises, and classify the others directly by utilizing the robustness of k-nearest neighbor. We verify the effectiveness of the proposed algorithm both theoretically and empirically. |
| Tasks | |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07526v5 |
| http://arxiv.org/pdf/1607.07526v5.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-resistance-of-nearest-neighbor-to |
| Repo | |
| Framework | |
Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks
| Title | Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks |
| Authors | Carlos Leandro |
| Abstract | This work describes a methodology to combine logic-based systems and connectionist systems. Our approach uses finite truth valued {\L}ukasiewicz logic, where we take advantage of fact what in this type of logics every connective can be define by a neuron in an artificial network having by activation function the identity truncated to zero and one. This allowed the injection of first-order formulas in a network architecture, and also simplified symbolic rule extraction. Our method trains a neural network using Levenderg-Marquardt algorithm, where we restrict the knowledge dissemination in the network structure. We show how this reduces neural networks plasticity without damage drastically the learning performance. Making the descriptive power of produced neural networks similar to the descriptive power of {\L}ukasiewicz logic language, simplifying the translation between symbolic and connectionist structures. This method is used in the reverse engineering problem of finding the formula used on generation of a truth table for a multi-valued {\L}ukasiewicz logic. For real data sets the method is particularly useful for attribute selection, on binary classification problems defined using nominal attribute. After attribute selection and possible data set completion in the resulting connectionist model: neurons are directly representable using a disjunctive or conjunctive formulas, in the {\L}ukasiewicz logic, or neurons are interpretations which can be approximated by symbolic rules. This fact is exemplified, extracting symbolic knowledge from connectionist models generated for the data set Mushroom from UCI Machine Learning Repository. |
| Tasks | |
| Published | 2016-04-11 |
| URL | http://arxiv.org/abs/1604.02774v1 |
| http://arxiv.org/pdf/1604.02774v1.pdf | |
| PWC | https://paperswithcode.com/paper/reverse-engineering-and-symbolic-knowledge |
| Repo | |
| Framework | |
Convolution in Convolution for Network in Network
| Title | Convolution in Convolution for Network in Network |
| Authors | Yanwei Pang, Manli Sun, Xiaoheng Jiang, Xuelong Li |
| Abstract | Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow MultiLayer Perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and $ 1\times 1 $ convolutions in spatial domain, NiN has stronger ability of feature representation and hence results in better recognition rate. However, MLP itself consists of fully connected layers which give rise to a large number of parameters. In this paper, we propose to replace dense shallow MLP with sparse shallow MLP. One or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel-spatial domain. The proposed method is implemented by applying unshared convolution across the channel dimension and applying shared convolution across the spatial dimension in some computational layers. The proposed method is called CiC. Experimental results on the CIFAR10 dataset, augmented CIFAR10 dataset, and CIFAR100 dataset demonstrate the effectiveness of the proposed CiC method. |
| Tasks | |
| Published | 2016-03-22 |
| URL | http://arxiv.org/abs/1603.06759v1 |
| http://arxiv.org/pdf/1603.06759v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolution-in-convolution-for-network-in |
| Repo | |
| Framework | |
An Introduction to MM Algorithms for Machine Learning and Statistical
| Title | An Introduction to MM Algorithms for Machine Learning and Statistical |
| Authors | Hien D. Nguyen |
| Abstract | MM (majorization–minimization) algorithms are an increasingly popular tool for solving optimization problems in machine learning and statistical estimation. This article introduces the MM algorithm framework in general and via three popular example applications: Gaussian mixture regressions, multinomial logistic regressions, and support vector machines. Specific algorithms for the three examples are derived and numerical demonstrations are presented. Theoretical and practical aspects of MM algorithm design are discussed. |
| Tasks | |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.03969v1 |
| http://arxiv.org/pdf/1611.03969v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-introduction-to-mm-algorithms-for-machine |
| Repo | |
| Framework | |
A Variational Model for Joint Motion Estimation and Image Reconstruction
| Title | A Variational Model for Joint Motion Estimation and Image Reconstruction |
| Authors | Martin Burger, Hendrik Dirks, Carola-Bibiane Schönlieb |
| Abstract | The aim of this paper is to derive and analyze a variational model for the joint estimation of motion and reconstruction of image sequences, which is based on a time-continuous Eulerian motion model. The model can be set up in terms of the continuity equation or the brightness constancy equation. The analysis in this paper focuses on the latter for robust motion estimation on sequences of two-dimensional images. We rigorously prove the existence of a minimizer in a suitable function space setting. Moreover, we discuss the numerical solution of the model based on primal-dual algorithms and investigate several examples. Finally, the benefits of our model compared to existing techniques, such as sequential image reconstruction and motion estimation, are shown. |
| Tasks | Image Reconstruction, Motion Estimation |
| Published | 2016-07-12 |
| URL | http://arxiv.org/abs/1607.03255v1 |
| http://arxiv.org/pdf/1607.03255v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-model-for-joint-motion |
| Repo | |
| Framework | |
Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure
| Title | Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure |
| Authors | Sattar Vakili, Qing Zhao |
| Abstract | The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel results under the measure of mean-variance, a commonly adopted risk measure in economics and mathematical finance. We show that the model-specific regret and the model-independent regret in terms of the mean-variance of the reward process are lower bounded by $\Omega(\log T)$ and $\Omega(T^{2/3})$, respectively. We then show that variations of the UCB policy and the DSEE policy developed for the classic risk-neutral MAB achieve these lower bounds. |
| Tasks | |
| Published | 2016-04-18 |
| URL | http://arxiv.org/abs/1604.05257v3 |
| http://arxiv.org/pdf/1604.05257v3.pdf | |
| PWC | https://paperswithcode.com/paper/risk-averse-multi-armed-bandit-problems-under |
| Repo | |
| Framework | |
Improved Deep Learning of Object Category using Pose Information
| Title | Improved Deep Learning of Object Category using Pose Information |
| Authors | Jiaping Zhao, Laurent Itti |
| Abstract | Despite significant recent progress, the best available computer vision algorithms still lag far behind human capabilities, even for recognizing individual discrete objects under various poses, illuminations, and backgrounds. Here we present a new approach to using object pose information to improve deep network learning. While existing large-scale datasets, e.g. ImageNet, do not have pose information, we leverage the newly published turntable dataset, iLab-20M, which has ~22M images of 704 object instances shot under different lightings, camera viewpoints and turntable rotations, to do more controlled object recognition experiments. We introduce a new convolutional neural network architecture, what/where CNN (2W-CNN), built on a linear-chain feedforward CNN (e.g., AlexNet), augmented by hierarchical layers regularized by object poses. Pose information is only used as feedback signal during training, in addition to category information; during test, the feedforward network only predicts category. To validate the approach, we train both 2W-CNN and AlexNet using a fraction of the dataset, and 2W-CNN achieves 6% performance improvement in category prediction. We show mathematically that 2W-CNN has inherent advantages over AlexNet under the stochastic gradient descent (SGD) optimization procedure. Further more, we fine-tune object recognition on ImageNet by using the pretrained 2W-CNN and AlexNet features on iLab-20M, results show that significant improvements have been achieved, compared with training AlexNet from scratch. Moreover, fine-tuning 2W-CNN features performs even better than fine-tuning the pretrained AlexNet features. These results show pretrained features on iLab- 20M generalizes well to natural image datasets, and 2WCNN learns even better features for object recognition than AlexNet. |
| Tasks | Object Recognition |
| Published | 2016-07-20 |
| URL | http://arxiv.org/abs/1607.05836v3 |
| http://arxiv.org/pdf/1607.05836v3.pdf | |
| PWC | https://paperswithcode.com/paper/improved-deep-learning-of-object-category |
| Repo | |
| Framework | |
Real-time 3D scene description using Spheres, Cones and Cylinders
| Title | Real-time 3D scene description using Spheres, Cones and Cylinders |
| Authors | Kristiyan Georgiev, Motaz Al-Hami, Rolf Lakaemper |
| Abstract | The paper describes a novel real-time algorithm for finding 3D geometric primitives (cylinders, cones and spheres) from 3D range data. In its core, it performs a fast model fitting with a model update in constant time (O(1)) for each new data point added to the model. We use a three stage approach.The first step inspects 1.5D sub spaces, to find ellipses. The next stage uses these ellipses as input by examining their neighborhood structure to form sets of candidates for the 3D geometric primitives. Finally, candidate ellipses are fitted to the geometric primitives. The complexity for point processing is O(n); additional time of lower order is needed for working on significantly smaller amount of mid-level objects. This allows the approach to process 30 frames per second on Kinect depth data, which suggests this approach as a pre-processing step for 3D real-time higher level tasks in robotics, like tracking or feature based mapping. |
| Tasks | |
| Published | 2016-03-12 |
| URL | http://arxiv.org/abs/1603.03856v1 |
| http://arxiv.org/pdf/1603.03856v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-3d-scene-description-using-spheres |
| Repo | |
| Framework | |
Generalized Interval-valued OWA Operators with Interval Weights Derived from Interval-valued Overlap Functions
| Title | Generalized Interval-valued OWA Operators with Interval Weights Derived from Interval-valued Overlap Functions |
| Authors | Benjamin Bedregal, Humberto Bustince, Eduardo Palmeira, Graçaliz Pereira Dimuro, Javier Fernandez |
| Abstract | In this work we extend to the interval-valued setting the notion of an overlap functions and we discuss a method which makes use of interval-valued overlap functions for constructing OWA operators with interval-valued weights. . Some properties of interval-valued overlap functions and the derived interval-valued OWA operators are analysed. We specially focus on the homogeneity and migrativity properties. |
| Tasks | |
| Published | 2016-10-20 |
| URL | http://arxiv.org/abs/1610.06473v1 |
| http://arxiv.org/pdf/1610.06473v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-interval-valued-owa-operators |
| Repo | |
| Framework | |
Deep Convolutional Neural Network Features and the Original Image
| Title | Deep Convolutional Neural Network Features and the Original Image |
| Authors | Connor J. Parde, Carlos Castillo, Matthew Q. Hill, Y. Ivette Colon, Swami Sankaranarayanan, Jun-Cheng Chen, Alice J. O’Toole |
| Abstract | Face recognition algorithms based on deep convolutional neural networks (DCNNs) have made progress on the task of recognizing faces in unconstrained viewing conditions. These networks operate with compact feature-based face representations derived from learning a very large number of face images. While the learned features produced by DCNNs can be highly robust to changes in viewpoint, illumination, and appearance, little is known about the nature of the face code that emerges at the top level of such networks. We analyzed the DCNN features produced by two face recognition algorithms. In the first set of experiments we used the top-level features from the DCNNs as input into linear classifiers aimed at predicting metadata about the images. The results show that the DCNN features contain surprisingly accurate information about the yaw and pitch of a face, and about whether the face came from a still image or a video frame. In the second set of experiments, we measured the extent to which individual DCNN features operated in a view-dependent or view-invariant manner. We found that view-dependent coding was a characteristic of the identities rather than the DCNN features - with some identities coded consistently in a view-dependent way and others in a view-independent way. In our third analysis, we visualized the DCNN feature space for over 24,000 images of 500 identities. Images in the center of the space were uniformly of low quality (e.g., extreme views, face occlusion, low resolution). Image quality increased monotonically as a function of distance from the origin. This result suggests that image quality information is available in the DCNN features, such that consistently average feature values reflect coding failures that reliably indicate poor or unusable images. Combined, the results offer insight into the coding mechanisms that support robust representation of faces in DCNNs. |
| Tasks | Face Recognition |
| Published | 2016-11-06 |
| URL | http://arxiv.org/abs/1611.01751v1 |
| http://arxiv.org/pdf/1611.01751v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-network-features |
| Repo | |
| Framework | |
Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search
| Title | Self-paced Learning for Weakly Supervised Evidence Discovery in Multimedia Event Search |
| Authors | Mengyi Liu, Lu Jiang, Shiguang Shan, Alexander G. Hauptmann |
| Abstract | Multimedia event detection has been receiving increasing attention in recent years. Besides recognizing an event, the discovery of evidences (which is refered to as “recounting”) is also crucial for user to better understand the searching result. Due to the difficulty of evidence annotation, only limited supervision of event labels are available for training a recounting model. To deal with the problem, we propose a weakly supervised evidence discovery method based on self-paced learning framework, which follows a learning process from easy “evidences” to gradually more complex ones, and simultaneously exploit more and more positive evidence samples from numerous weakly annotated video segments. Moreover, to evaluate our method quantitatively, we also propose two metrics, \textit{PctOverlap} and \textit{F1-score}, for measuring the performance of evidence localization specifically. The experiments are conducted on a subset of TRECVID MED dataset and demonstrate the promising results obtained by our method. |
| Tasks | |
| Published | 2016-08-12 |
| URL | http://arxiv.org/abs/1608.03748v3 |
| http://arxiv.org/pdf/1608.03748v3.pdf | |
| PWC | https://paperswithcode.com/paper/self-paced-learning-for-weakly-supervised |
| Repo | |
| Framework | |
Leveraging over intact priors for boosting control and dexterity of prosthetic hands by amputees
| Title | Leveraging over intact priors for boosting control and dexterity of prosthetic hands by amputees |
| Authors | Valentina Gregori, Barbara Caputo |
| Abstract | Non-invasive myoelectric prostheses require a long training time to obtain satisfactory control dexterity. These training times could possibly be reduced by leveraging over training efforts by previous subjects. So-called domain adaptation algorithms formalize this strategy and have indeed been shown to significantly reduce the amount of required training data for intact subjects for myoelectric movements classification. It is not clear, however, whether these results extend also to amputees and, if so, whether prior information from amputees and intact subjects is equally useful. To overcome this problem, we evaluated several domain adaptation algorithms on data coming from both amputees and intact subjects. Our findings indicate that: (1) the use of previous experience from other subjects allows us to reduce the training time by about an order of magnitude; (2) this improvement holds regardless of whether an amputee exploits previous information from other amputees or from intact subjects. |
| Tasks | Domain Adaptation |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.07536v1 |
| http://arxiv.org/pdf/1608.07536v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-over-intact-priors-for-boosting |
| Repo | |
| Framework | |
