PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1403.1902

Quality-based Multimodal Classification Using Tree-Structured Sparsity

Recent studies have demonstrated advantages of information fusion based on sparsity models for multimodal classification. Among several sparsity models, tree-structured sparsity provides a flexible framework for extraction of cross-correlated information from different sources and for enforcing group sparsity at multiple granularities. However, the existing algorithm only solves an approximated version of the cost functional and the resulting solution is not necessarily sparse at group levels. This paper reformulates the tree-structured sparse model for multimodal classification task. An accelerated proximal algorithm is proposed to solve the optimization problem, which is an efficient tool for feature-level fusion among either homogeneous or heterogeneous sources of information. In addition, a (fuzzy-set-theoretic) possibilistic scheme is proposed to weight the available modalities, based on their respective reliability, in a joint optimization problem for finding the sparsity codes. This approach provides a general framework for quality-based fusion that offers added robustness to several sparsity-based multimodal classification algorithms. To demonstrate their efficacy, the proposed methods are evaluated on three different applications - multiview face recognition, multimodal face recognition, and target classification.

arXiv:1403.1735

Ant Colony based Feature Selection Heuristics for Retinal Vessel Segmentation

Features selection is an essential step for successful data classification, since it reduces the data dimensionality by removing redundant features. Consequently, that minimizes the classification complexity and time in addition to maximizing its accuracy. In this article, a comparative study considering six features selection heuristics is conducted in order to select the best relevant features subset. The tested features vector consists of fourteen features that are computed for each pixel in the field of view of retinal images in the DRIVE database. The comparison is assessed in terms of sensitivity, specificity, and accuracy measurements of the recommended features subset resulted by each heuristic when applied with the ant colony system. Experimental results indicated that the features subset recommended by the relief heuristic outperformed the subsets recommended by the other experienced heuristics.

arXiv:1403.1687

Rigid-Motion Scattering for Texture Classification

A rigid-motion scattering computes adaptive invariants along translations and rotations, with a deep convolutional network. Convolutions are calculated on the rigid-motion group, with wavelets defined on the translation and rotation variables. It preserves joint rotation and translation information, while providing global invariants at any desired scale. Texture classification is studied, through the characterization of stationary processes from a single realization. State-of-the-art results are obtained on multiple texture data bases, with important rotation and scaling variabilities.

arXiv:1403.1451

Real-Time Classification of Twitter Trends

Social media users give rise to social trends as they share about common interests, which can be triggered by different reasons. In this work, we explore the types of triggers that spark trends on Twitter, introducing a typology with following four types: 'news', 'ongoing events', 'memes', and 'commemoratives'. While previous research has analyzed trending topics in a long term, we look at the earliest tweets that produce a trend, with the aim of categorizing trends early on. This would allow to provide a filtered subset of trends to end users. We analyze and experiment with a set of straightforward language-independent features based on the social spread of trends to categorize them into the introduced typology. Our method provides an efficient way to accurately categorize trending topics without need of external data, enabling news organizations to discover breaking news in real-time, or to quickly identify viral memes that might enrich marketing decisions, among others. The analysis of social features also reveals patterns associated with each type of trend, such as tweets about ongoing events being shorter as many were likely sent from mobile devices, or memes having more retweets originating from a few trend-setters.

arXiv:1403.1362

Illumination,Expression and Occlusion Invariant Pose-Adaptive Face Recognition System for Real-Time Applications

Face recognition in real-time scenarios is mainly affected by illumination, expression and pose variations and also by occlusion. This paper presents the framework for pose adaptive component-based face recognition system. The framework proposed deals with all the above mentioned issues. The steps involved in the presented framework are (i) facial landmark localisation, (ii) facial component extraction, (iii) pre-processing of facial image (iv) facial pose estimation (v) feature extraction using Local Binary Pattern Histograms of each component followed by (vi) fusion of pose adaptive classification of components. By employing pose adaptive classification, the recognition process is carried out on some part of database, based on estimated pose, instead of applying the recognition process on the whole database. Pre-processing techniques employed to overcome the problems due to illumination variation are also discussed in this paper. Component-based techniques provide better recognition rates when face images are occluded compared to the holistic methods. Our method is simple, feasible and provides better results when compared to other holistic methods.

arXiv:1403.1353

Collaborative Representation for Classification, Sparse or Non-sparse?

Sparse representation based classification (SRC) has been proved to be a simple, effective and robust solution to face recognition. As it gets popular, doubts on the necessity of enforcing sparsity starts coming up, and primary experimental results showed that simply changing the $l_1$-norm based regularization to the computationally much more efficient $l_2$-norm based non-sparse version would lead to a similar or even better performance. However, that's not always the case. Given a new classification task, it's still unclear which regularization strategy (i.e., making the coefficients sparse or non-sparse) is a better choice without trying both for comparison. In this paper, we present as far as we know the first study on solving this issue, based on plenty of diverse classification experiments. We propose a scoring function for pre-selecting the regularization strategy using only the dataset size, the feature dimensionality and a discrimination score derived from a given feature representation. Moreover, we show that when dictionary learning is taking into account, non-sparse representation has a more significant superiority to sparse representation. This work is expected to enrich our understanding of sparse/non-sparse collaborative representation for classification and motivate further research activities.

arXiv:1403.0829

Multiview Hessian regularized logistic regression for action recognition

With the rapid development of social media sharing, people often need to manage the growing volume of multimedia data such as large scale video classification and annotation, especially to organize those videos containing human activities. Recently, manifold regularized semi-supervised learning (SSL), which explores the intrinsic data probability distribution and then improves the generalization ability with only a small number of labeled data, has emerged as a promising paradigm for semiautomatic video classification. In addition, human action videos often have multi-modal content and different representations. To tackle the above problems, in this paper we propose multiview Hessian regularized logistic regression (mHLR) for human action recognition. Compared with existing work, the advantages of mHLR lie in three folds: (1) mHLR combines multiple Hessian regularization, each of which obtained from a particular representation of instance, to leverage the exploring of local geometry; (2) mHLR naturally handle multi-view instances with multiple representations; (3) mHLR employs a smooth loss function and then can be effectively optimized. We carefully conduct extensive experiments on the unstructured social activity attribute (USAA) dataset and the experimental results demonstrate the effectiveness of the proposed multiview Hessian regularized logistic regression for human action recognition.

arXiv:1403.0700

Random Projections on Manifolds of Symmetric Positive Definite Matrices for Image Classification

Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance. Taking into account manifold geometry is typically done via (1) embedding the manifolds in tangent spaces, or (2) embedding into Reproducing Kernel Hilbert Spaces (RKHS). While embedding into tangent spaces allows the use of existing Euclidean-based learning algorithms, manifold shape is only approximated which can cause loss of discriminatory information. The RKHS approach retains more of the manifold structure, but may require non-trivial effort to kernelise Euclidean-based learning algorithms. In contrast to the above approaches, in this paper we offer a novel solution that allows SPD matrices to be used with unmodified Euclidean-based learning algorithms, with the true manifold shape well-preserved. Specifically, we propose to project SPD matrices using a set of random projection hyperplanes over RKHS into a random projection space, which leads to representing each matrix as a vector of projection coefficients. Experiments on face recognition, person re-identification and texture classification show that the proposed approach outperforms several recent methods, such as Tensor Sparse Coding, Histogram Plus Epitome, Riemannian Locality Preserving Projection and Relational Divergence Classification.

arXiv:1403.0699

Multi-Shot Person Re-Identification via Relational Stein Divergence

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.

arXiv:1403.0522

Expert System Based On Neural-Fuzzy Rules for Thyroid Diseases Diagnosis

The thyroid, an endocrine gland that secretes hormones in the blood, circulates its products to all tissues of the body, where they control vital functions in every cell. Normal levels of thyroid hormone help the brain, heart, intestines, muscles and reproductive system function normally. Thyroid hormones control the metabolism of the body. Abnormalities of thyroid function are usually related to production of too little thyroid hormone (hypothyroidism) or production of too much thyroid hormone (hyperthyroidism). Therefore, the correct diagnosis of these diseases is very important topic. In this study, Linguistic Hedges Neural-Fuzzy Classifier with Selected Features (LHNFCSF) is presented for diagnosis of thyroid diseases. The performance evaluation of this system is estimated by using classification accuracy and k-fold cross-validation. The results indicated that the classification accuracy without feature selection was 98.6047% and 97.6744% during training and testing phases, respectively with RMSE of 0.02335. After applying feature selection algorithm, LHNFCSF achieved 100% for all cluster sizes during training phase. However, in the testing phase LHNFCSF achieved 88.3721% using one cluster for each class, 90.6977% using two clusters, 91.8605% using three clusters and 97.6744% using four clusters for each class and 12 fuzzy rules. The obtained classification accuracy was very promising with regard to the other classification applications in literature for this problem.

arXiv:1403.0320

Matching Image Sets via Adaptive Multi Convex Hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

arXiv:1401.0509

Zero-Shot Learning for Semantic Utterance Classification

We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier $f: X \to Y$ for problems where none of the semantic categories $Y$ are present in the training set. The framework uncovers the link between categories and utterances using a semantic space. We show that this semantic space can be learned by deep neural networks trained on large amounts of search engine query log data. More precisely, we propose a novel method that can learn discriminative semantic features without supervision. It uses the zero-shot learning framework to guide the learning of the semantic features. We demonstrate the effectiveness of the zero-shot semantic learning algorithm on the SUC dataset collected by (Tur, 2012). Furthermore, we achieve state-of-the-art results by combining the semantic features with a supervised method.

arXiv:1312.4400공식 코드 · Papers with Code

Network In Network

We propose a novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract the data within the receptive field. We instantiate the micro neural network with a multilayer perceptron, which is a potent function approximator. The feature maps are obtained by sliding the micro networks over the input in a similar manner as CNN; they are then fed into the next layer. Deep NIN can be implemented by stacking mutiple of the above described structure. With enhanced local modeling via the micro network, we are able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers. We demonstrated the state-of-the-art classification performances with NIN on CIFAR-10 and CIFAR-100, and reasonable performances on SVHN and MNIST datasets.

arXiv:1403.4540

Similarity networks for classification: a case study in the Horse Colic problem

This paper develops a two-layer neural network in which the neuron model computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the mean of the partial input-weight similarities. The resulting neuron model is capable of dealing directly with variables of potentially different nature (continuous, fuzzy, ordinal, categorical). There is also provision for missing values. The network is trained using a two-stage procedure very similar to that used to train a radial basis function (RBF) neural network. The network is compared to two types of RBF networks in a non-trivial dataset: the Horse Colic problem, taken as a case study and analyzed in detail.

arXiv:1403.3780

Automatic Classification of Human Epithelial Type 2 Cell Indirect Immunofluorescence Images using Cell Pyramid Matching

This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol. The IIF protocol on HEp-2 cells has been the hallmark method to identify the presence of ANAs, due to its high sensitivity and the large range of antigens that can be detected. However, it suffers from numerous shortcomings, such as being subjective as well as time and labour intensive. Computer Aided Diagnostic (CAD) systems have been developed to address these problems, which automatically classify a HEp-2 cell image into one of its known patterns (eg. speckled, homogeneous). Most of the existing CAD systems use handpicked features to represent a HEp-2 cell image, which may only work in limited scenarios. We propose a novel automatic cell image classification method termed Cell Pyramid Matching (CPM), which is comprised of regional histograms of visual words coupled with the Multiple Kernel Learning framework. We present a study of several variations of generating histograms and show the efficacy of the system on two publicly available datasets: the ICPR HEp-2 cell classification contest dataset and the SNPHEp-2 dataset.

arXiv:1403.3628

Mixed-norm Regularization for Brain Decoding

This work investigates the use of mixed-norm regularization for sensor selection in Event-Related Potential (ERP) based Brain-Computer Interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multi-task learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multi-task learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multi-task approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

arXiv:1403.3602

Spontaneous expression classification in the encrypted domain

To date, most facial expression analysis have been based on posed image databases and is carried out without being able to protect the identity of the subjects whose expressions are being recognised. In this paper, we propose and implement a system for classifying facial expressions of images in the encrypted domain based on a Paillier cryptosystem implementation of Fisher Linear Discriminant Analysis and k-nearest neighbour (FLDA + kNN). We present results of experiments carried out on a recently developed natural visible and infrared facial expression (NVIE) database of spontaneous images. To the best of our knowledge, this is the first system that will allow the recog-nition of encrypted spontaneous facial expressions by a remote server on behalf of a client.

arXiv:1403.2950

Cancer Prognosis Prediction Using Balanced Stratified Sampling

High accuracy in cancer prediction is important to improve the quality of the treatment and to improve the rate of survivability of patients. As the data volume is increasing rapidly in the healthcare research, the analytical challenge exists in double. The use of effective sampling technique in classification algorithms always yields good prediction accuracy. The SEER public use cancer database provides various prominent class labels for prognosis prediction. The main objective of this paper is to find the effect of sampling techniques in classifying the prognosis variable and propose an ideal sampling method based on the outcome of the experimentation. In the first phase of this work the traditional random sampling and stratified sampling techniques have been used. At the next level the balanced stratified sampling with variations as per the choice of the prognosis class labels have been tested. Much of the initial time has been focused on performing the pre_processing of the SEER data set. The classification model for experimentation has been built using the breast cancer, respiratory cancer and mixed cancer data sets with three traditional classifiers namely Decision Tree, Naive Bayes and K-Nearest Neighbor. The three prognosis factors survival, stage and metastasis have been used as class labels for experimental comparisons. The results shows a steady increase in the prediction accuracy of balanced stratified model as the sample size increases, but the traditional approach fluctuates before the optimum results.

arXiv:1403.2654

Flying Insect Classification with Inexpensive Sensors

The ability to use inexpensive, noninvasive sensors to accurately classify flying insects would have significant implications for entomological research, and allow for the development of many useful applications in vector control for both medical and agricultural entomology. Given this, the last sixty years have seen many research efforts on this task. To date, however, none of this research has had a lasting impact. In this work, we explain this lack of progress. We attribute the stagnation on this problem to several factors, including the use of acoustic sensing devices, the over-reliance on the single feature of wingbeat frequency, and the attempts to learn complex models with relatively little data. In contrast, we show that pseudo-acoustic optical sensors can produce vastly superior data, that we can exploit additional features, both intrinsic and extrinsic to the insect's flight behavior, and that a Bayesian classification approach allows us to efficiently learn classification models that are very robust to over-fitting. We demonstrate our findings with large scale experiments that dwarf all previous works combined, as measured by the number of insects and the number of species considered.

arXiv:1403.2484

Transfer Learning across Networks for Collective Classification

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which the instances are assumed to be independent and identically distributed, how to effectively transfer knowledge across different information networks has not been well studied, mainly because networks may have their distinct node features and link relationships between nodes. In this paper, we propose a new transfer learning algorithm that attempts to transfer common latent structure features across the source and target networks. The proposed algorithm discovers these latent features by constructing label propagation matrices in the source and target networks, and mapping them into a shared latent feature space. The latent features capture common structure patterns shared by two networks, and serve as domain-independent features to be transferred between networks. Together with domain-dependent node features, we thereafter propose an iterative classification algorithm that leverages label correlations to predict node labels in the target network. Experiments on real-world networks demonstrate that our proposed algorithm can successfully achieve knowledge transfer between networks to help improve the accuracy of classifying nodes in the target network.