PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1311.5591

PANDA: Pose Aligned Networks for Deep Attribute Modeling

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion. Convolutional Neural Nets (CNN) have been shown to perform very well on large scale object recognition problems. In the context of attribute classification, however, the signal is often subtle and it may cover only a small part of the image, while the image is dominated by the effects of pose and viewpoint. Discounting for pose variation would require training on very large labeled datasets which are not presently available. Part-based models, such as poselets and DPM have been shown to perform well for this problem but they are limited by shallow low-level features. We propose a new method which combines part-based models and deep learning by training pose-normalized CNNs. We show substantial improvement vs. state-of-the-art methods on challenging attribute classification tasks in unconstrained settings. Experiments confirm that our method outperforms both the best part-based methods on this problem and conventional CNNs trained on the full bounding box of the person.

arXiv:1405.4308

Coarse-to-Fine Classification via Parametric and Nonparametric Models for Computer-Aided Diagnosis

Classification is one of the core problems in Computer-Aided Diagnosis (CAD), targeting for early cancer detection using 3D medical imaging interpretation. High detection sensitivity with desirably low false positive (FP) rate is critical for a CAD system to be accepted as a valuable or even indispensable tool in radiologists' workflow. Given various spurious imagery noises which cause observation uncertainties, this remains a very challenging task. In this paper, we propose a novel, two-tiered coarse-to-fine (CTF) classification cascade framework to tackle this problem. We first obtain classification-critical data samples (e.g., samples on the decision boundary) extracted from the holistic data distributions using a robust parametric model (e.g., \cite{Raykar08}); then we build a graph-embedding based nonparametric classifier on sampled data, which can more accurately preserve or formulate the complex classification boundary. These two steps can also be considered as effective "sample pruning" and "feature pursuing + $k$NN/template matching", respectively. Our approach is validated comprehensively in colorectal polyp detection and lung nodule detection CAD systems, as the top two deadly cancers, using hospital scale, multi-site clinical datasets. The results show that our method achieves overall better classification/detection performance than existing state-of-the-art algorithms using single-layer classifiers, such as the support vector machine variants \cite{Wang08}, boosting \cite{Slabaugh10}, logistic regression \cite{Ravesteijn10}, relevance vector machine \cite{Raykar08}, $k$-nearest neighbor \cite{Murphy09} or spectral projections on graph \cite{Cai08}.

arXiv:1405.3729

Building a Classification Model for Enrollment In Higher Educational Courses using Data Mining Techniques

Data Mining is the process of extracting useful patterns from the huge amount of database and many data mining techniques are used for mining these patterns. Recently, one of the remarkable facts in higher educational institute is the rapid growth data and this educational data is expanding quickly without any advantage to the educational management. The main aim of the management is to refine the education standard; therefore by applying the various data mining techniques on this data one can get valuable information. This research study proposed the "classification model for the student's enrollment process in higher educational courses using data mining techniques". Additionally, this study contributes to finding some patterns that are meaningful to management.

arXiv:1405.3559

Credal Model Averaging for classification: representing prior ignorance and expert opinions

Bayesian model averaging (BMA) is the state of the art approach for overcoming model uncertainty. Yet, especially on small data sets, the results yielded by BMA might be sensitive to the prior over the models. Credal Model Averaging (CMA) addresses this problem by substituting the single prior over the models by a set of priors (credal set). Such approach solves the problem of how to choose the prior over the models and automates sensitivity analysis. We discuss various CMA algorithms for building an ensemble of logistic regressors characterized by different sets of covariates. We show how CMA can be appropriately tuned to the case in which one is prior-ignorant and to the case in which instead domain knowledge is available. CMA detects prior-dependent instances, namely instances in which a different class is more probable depending on the prior over the models. On such instances CMA suspends the judgment, returning multiple classes. We thoroughly compare different BMA and CMA variants on a real case study, predicting presence of Alpine marmot burrows in an Alpine valley. We find that BMA is almost a random guesser on the instances recognized as prior-dependent by CMA.

arXiv:1405.3410

Efficient classification using parallel and scalable compressed model and Its application on intrusion detection

In order to achieve high efficiency of classification in intrusion detection, a compressed model is proposed in this paper which combines horizontal compression with vertical compression. OneR is utilized as horizontal com-pression for attribute reduction, and affinity propagation is employed as vertical compression to select small representative exemplars from large training data. As to be able to computationally compress the larger volume of training data with scalability, MapReduce based parallelization approach is then implemented and evaluated for each step of the model compression process abovementioned, on which common but efficient classification methods can be directly used. Experimental application study on two publicly available datasets of intrusion detection, KDD99 and CMDC2012, demonstrates that the classification using the compressed model proposed can effectively speed up the detection procedure at up to 184 times, most importantly at the cost of a minimal accuracy difference with less than 1% on average.

arXiv:1405.3295

Effects of Sampling Methods on Prediction Quality. The Case of Classifying Land Cover Using Decision Trees

Clever sampling methods can be used to improve the handling of big data and increase its usefulness. The subject of this study is remote sensing, specifically airborne laser scanning point clouds representing different classes of ground cover. The aim is to derive a supervised learning model for the classification using CARTs. In order to measure the effect of different sampling methods on the classification accuracy, various experiments with varying types of sampling methods, sample sizes, and accuracy metrics have been designed. Numerical results for a subset of a large surveying project covering the lower Rhine area in Germany are shown. General conclusions regarding sampling design are drawn and presented.

arXiv:1403.6382

CNN Features off-the-shelf: an Astounding Baseline for Recognition

Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the \overfeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or $L2$ distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

arXiv:1402.1892

Thresholding Classifiers to Maximize F1 Score

This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a binary classifier when one class is rare. Micro average, macro average, and per instance average F1 scores are used in multilabel classification. For any classifier that produces a real-valued output, we derive the relationship between the best achievable F1 score and the decision-making threshold that achieves this optimum. As a special case, if the classifier outputs are well-calibrated conditional probabilities, then the optimal threshold is half the optimal F1 score. As another special case, if the classifier is completely uninformative, then the optimal behavior is to classify all examples as positive. Since the actual prevalence of positive examples typically is low, this behavior can be considered undesirable. As a case study, we discuss the results, which can be surprising, of applying this procedure when predicting 26,853 labels for Medline documents.

arXiv:1312.5419

Large-scale Multi-label Text Classification - Revisiting Neural Networks

Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural network (NN) architecture that aims at minimizing pairwise ranking error. Instead, we propose to use a comparably simple NN approach with recently proposed learning techniques for large-scale multi-label text classification tasks. In particular, we show that BP-MLL's ranking loss minimization can be efficiently and effectively replaced with the commonly used cross entropy error function, and demonstrate that several advances in neural network training that have been developed in the realm of deep learning can be effectively employed in this setting. Our experimental results show that simple NN models equipped with advanced techniques such as rectified linear units, dropout, and AdaGrad perform as well as or even outperform state-of-the-art approaches on six large-scale textual datasets with diverse characteristics.

arXiv:1405.6524

Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning

Automatic species classification of birds from their sound is a computational tool of increasing importance in ecology, conservation monitoring and vocal communication studies. To make classification useful in practice, it is crucial to improve its accuracy while ensuring that it can run at big data scales. Many approaches use acoustic measures based on spectrogram-type data, such as the Mel-frequency cepstral coefficient (MFCC) features which represent a manually-designed summary of spectral information. However, recent work in machine learning has demonstrated that features learnt automatically from data can often outperform manually-designed feature transforms. Feature learning can be performed at large scale and "unsupervised", meaning it requires no manual data labelling, yet it can improve performance on "supervised" tasks such as classification. In this work we introduce a technique for feature learning from large volumes of bird sound recordings, inspired by techniques that have proven useful in other domains. We experimentally compare twelve different feature representations derived from the Mel spectrum (of which six use this technique), using four large and diverse databases of bird vocalisations, with a random forest classifier. We demonstrate that MFCCs are of limited power in this context, leading to worse performance than the raw Mel spectral data. Conversely, we demonstrate that unsupervised feature learning provides a substantial boost over MFCCs and Mel spectra without adding computational complexity after the model has been trained. The boost is particularly notable for single-label classification tasks at large scale. The spectro-temporal activations learned through our procedure resemble spectro-temporal receptive fields calculated from avian primary auditory forebrain.

arXiv:1405.6472

Fast and Robust Archetypal Analysis for Representation Learning

We revisit a pioneer unsupervised learning technique called archetypal analysis, which is related to successful data analysis methods such as sparse coding and non-negative matrix factorization. Since it was proposed, archetypal analysis did not gain a lot of popularity even though it produces more interpretable models than other alternatives. Because no efficient implementation has ever been made publicly available, its application to important scientific problems may have been severely limited. Our goal is to bring back into favour archetypal analysis. We propose a fast optimization scheme using an active-set strategy, and provide an efficient open-source implementation interfaced with Matlab, R, and Python. Then, we demonstrate the usefulness of archetypal analysis for computer vision tasks, such as codebook learning, signal classification, and large image collection visualization.

arXiv:1405.6444

The role of dimensionality reduction in linear classification

Dimensionality reduction (DR) is often used as a preprocessing step in classification, but usually one first fixes the DR mapping, possibly using label information, and then learns a classifier (a filter approach). Best performance would be obtained by optimizing the classification error jointly over DR mapping and classifier (a wrapper approach), but this is a difficult nonconvex problem, particularly with nonlinear DR. Using the method of auxiliary coordinates, we give a simple, efficient algorithm to train a combination of nonlinear DR and a classifier, and apply it to a RBF mapping with a linear SVM. This alternates steps where we train the RBF mapping and a linear SVM as usual regression and classification, respectively, with a closed-form step that coordinates both. The resulting nonlinear low-dimensional classifier achieves classification errors competitive with the state-of-the-art but is fast at training and testing, and allows the user to trade off runtime for classification accuracy easily. We then study the role of nonlinear DR in linear classification, and the interplay between the DR mapping, the number of latent dimensions and the number of classes. When trained jointly, the DR mapping takes an extreme role in eliminating variation: it tends to collapse classes in latent space, erasing all manifold structure, and lay out class centroids so they are linearly separable with maximum margin.

arXiv:1405.5829

Node Classification in Uncertain Graphs

In many real applications that use and analyze networked data, the links in the network graph may be erroneous, or derived from probabilistic techniques. In such cases, the node classification problem can be challenging, since the unreliability of the links may affect the final results of the classification process. If the information about link reliability is not used explicitly, the classification accuracy in the underlying network may be affected adversely. In this paper, we focus on situations that require the analysis of the uncertainty that is present in the graph structure. We study the novel problem of node classification in uncertain graphs, by treating uncertainty as a first-class citizen. We propose two techniques based on a Bayes model and automatic parameter selection, and show that the incorporation of uncertainty in the classification process as a first-class citizen is beneficial. We experimentally evaluate the proposed approach using different real data sets, and study the behavior of the algorithms under different conditions. The results demonstrate the effectiveness and efficiency of our approach.

arXiv:1405.4589

A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm

A large number of experimental data shows that Support Vector Machine (SVM) algorithm has obvious advantages in text classification, handwriting recognition, image classification, bioinformatics, and some other fields. To some degree, the optimization of SVM depends on its kernel function and Slack variable, the determinant of which is its parameters $\delta$ and c in the classification function. That is to say,to optimize the SVM algorithm, the optimization of the two parameters play a huge role. Ant Colony Optimization (ACO) is optimization algorithm which simulate ants to find the optimal path.In the available literature, we mix the ACO algorithm and Parallel algorithm together to find a well parameters.

arXiv:1405.4574

Kronecker PCA Based Spatio-Temporal Modeling of Video for Dismount Classification

We consider the application of KronPCA spatio-temporal modeling techniques [Greenewald et al 2013, Tsiligkaridis et al 2013] to the extraction of spatiotemporal features for video dismount classification. KronPCA performs a low-rank type of dimensionality reduction that is adapted to spatio-temporal data and is characterized by the T frame multiframe mean and covariance of p spatial features. For further regularization and improved inverse estimation, we also use the diagonally corrected KronPCA shrinkage methods we presented in [Greenewald et al 2013]. We apply this very general method to the modeling of the multivariate temporal behavior of HOG features extracted from pedestrian bounding boxes in video, with gender classification in a challenging dataset chosen as a specific application. The learned covariances for each class are used to extract spatiotemporal features which are then classified, achieving competitive classification performance.

arXiv:1404.4095

Multi-borders classification

The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification problems into binary classification problems is specified using a recursive control language.

arXiv:1402.4437

Learning the Irreducible Representations of Commutative Lie Groups

We present a new probabilistic model of compact commutative Lie groups that produces invariant-equivariant and disentangled representations of data. To define the notion of disentangling, we borrow a fundamental principle from physics that is used to derive the elementary particles of a system from its symmetries. Our model employs a newfound Bayesian conjugacy relation that enables fully tractable probabilistic inference over compact commutative Lie groups -- a class that includes the groups that describe the rotation and cyclic translation of images. We train the model on pairs of transformed image patches, and show that the learned invariant representation is highly effective for classification.

arXiv:1406.0824

Supervised classification-based stock prediction and portfolio optimization

As the number of publicly traded companies as well as the amount of their financial data grows rapidly, it is highly desired to have tracking, analysis, and eventually stock selections automated. There have been few works focusing on estimating the stock prices of individual companies. However, many of those have worked with very small number of financial parameters. In this work, we apply machine learning techniques to address automated stock picking, while using a larger number of financial parameters for individual companies than the previous studies. Our approaches are based on the supervision of prediction parameters using company fundamentals, time-series properties, and correlation information between different stocks. We examine a variety of supervised learning techniques and found that using stock fundamentals is a useful approach for the classification problem, when combined with the high dimensional data handling capabilities of support vector machine. The portfolio our system suggests by predicting the behavior of stocks results in a 3% larger growth on average than the overall market within a 3-month time period, as the out-of-sample test suggests.

arXiv:1406.0231

Ambiguous Proximity Distribution

Proximity Distribution Kernel is an effective method for bag-of-featues based image representation. In this paper, we investigate the soft assignment of visual words to image features for proximity distribution. Visual word contribution function is proposed to model ambiguous proximity distributions. Three ambiguous proximity distributions is developed by three ambiguous contribution functions. The experiments are conducted on both classification and retrieval of medical image data sets. The results show that the performance of the proposed methods, Proximity Distribution Kernel (PDK), is better or comparable to the state-of-the-art bag-of-features based image representation methods.

arXiv:1406.0214

Topological and Statistical Behavior Classifiers for Tracking Applications

We introduce the first unified theory for target tracking using Multiple Hypothesis Tracking, Topological Data Analysis, and machine learning. Our string of innovations are 1) robust topological features are used to encode behavioral information, 2) statistical models are fitted to distributions over these topological features, and 3) the target type classification methods of Wigren and Bar Shalom et al. are employed to exploit the resulting likelihoods for topological features inside of the tracking procedure. To demonstrate the efficacy of our approach, we test our procedure on synthetic vehicular data generated by the Simulation of Urban Mobility package.