PyTorchKR Papers

최신 논문

총 11,809편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1601.07533

Osteoporotic and Neoplastic Compression Fracture Classification on Longitudinal CT

Classification of vertebral compression fractures (VCF) having osteoporotic or neoplastic origin is fundamental to the planning of treatment. We developed a fracture classification system by acquiring quantitative morphologic and bone density determinants of fracture progression through the use of automated measurements from longitudinal studies. A total of 250 CT studies were acquired for the task, each having previously identified VCFs with osteoporosis or neoplasm. Thirty-six features or each identified VCF were computed and classified using a committee of support vector machines. Ten-fold cross validation on 695 identified fractured vertebrae showed classification accuracies of 0.812, 0.665, and 0.820 for the measured, longitudinal, and combined feature sets respectively.

arXiv:1601.07336

Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices

Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years. However, the existing SRC type methods apply only to vector data in Euclidean space. As such, there is still no satisfactory approach to conduct classification task for symmetric positive definite (SPD) matrices which is very useful in computer vision. To address this problem, in this paper, a neighborhood preserved kernel SRC method is proposed on SPD manifolds. Specifically, by embedding the SPD matrices into a Reproducing Kernel Hilbert Space (RKHS), the proposed method can perform classification on SPD manifolds through an appropriate Log-Euclidean kernel. Through exploiting the geodesic distance between SPD matrices, our method can effectively characterize the intrinsic local Riemannian geometry within data so as to well unravel the underlying sub-manifold structure. Despite its simplicity, experimental results on several famous database demonstrate that the proposed method achieves better classification results than the state-of-the-art approaches.

arXiv:1509.08971

Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition

Deep learning neural networks have emerged as one of the most powerful classification tools for vision related applications. However, the computational and energy requirements associated with such deep nets can be quite high, and hence their energy-efficient implementation is of great interest. Although traditionally the entire network is utilized for the recognition of all inputs, we observe that the classification difficulty varies widely across inputs in real-world datasets; only a small fraction of inputs require the full computational effort of a network, while a large majority can be classified correctly with very low effort. In this paper, we propose Conditional Deep Learning (CDL) where the convolutional layer features are used to identify the variability in the difficulty of input instances and conditionally activate the deeper layers of the network. We achieve this by cascading a linear network of output neurons for each convolutional layer and monitoring the output of the linear network to decide whether classification can be terminated at the current stage or not. The proposed methodology thus enables the network to dynamically adjust the computational effort depending upon the difficulty of the input data while maintaining competitive classification accuracy. We evaluate our approach on the MNIST dataset. Our experiments demonstrate that our proposed CDL yields 1.91x reduction in average number of operations per input, which translates to 1.84x improvement in energy. In addition, our results show an improvement in classification accuracy from 97.5% to 98.9% as compared to the original network.

arXiv:1504.02763

Performance measures for classification systems with rejection

Classifiers with rejection are essential in real-world applications where misclassifications and their effects are critical. However, if no problem specific cost function is defined, there are no established measures to assess the performance of such classifiers. We introduce a set of desired properties for performance measures for classifiers with rejection, based on which we propose a set of three performance measures for the evaluation of the performance of classifiers with rejection that satisfy the desired properties. The nonrejected accuracy measures the ability of the classifier to accurately classify nonrejected samples; the classification quality measures the correct decision making of the classifier with rejector; and the rejection quality measures the ability to concentrate all misclassified samples onto the set of rejected samples. From the measures, we derive the concept of relative optimality that allows us to connect the measures to a family of cost functions that take into account the trade-off between rejection and misclassification. We illustrate the use of the proposed performance measures on classifiers with rejection applied to synthetic and real-world data.

arXiv:1602.02123

Sequence Classification with Neural Conditional Random Fields

The proliferation of sensor devices monitoring human activity generates voluminous amount of temporal sequences needing to be interpreted and categorized. Moreover, complex behavior detection requires the personalization of multi-sensor fusion algorithms. Conditional random fields (CRFs) are commonly used in structured prediction tasks such as part-of-speech tagging in natural language processing. Conditional probabilities guide the choice of each tag/label in the sequence conflating the structured prediction task with the sequence classification task where different models provide different categorization of the same sequence. The claim of this paper is that CRF models also provide discriminative models to distinguish between types of sequence regardless of the accuracy of the labels obtained if we calibrate the class membership estimate of the sequence. We introduce and compare different neural network based linear-chain CRFs and we present experiments on two complex sequence classification and structured prediction tasks to support this claim.

arXiv:1602.00955

Unsupervised High-level Feature Learning by Ensemble Projection for Semi-supervised Image Classification and Image Clustering

This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval. Unlike previous methods, which develop or learn sophisticated regularizers for classifiers, our method learns a new image representation by exploiting the distribution patterns of all available data for the task at hand. Particularly, a rich set of visual prototypes are sampled from all available data, and are taken as surrogate classes to train discriminative classifiers; images are projected via the classifiers; the projected values, similarities to the prototypes, are stacked to build the new feature vector. The training set is noisy. Hence, in the spirit of ensemble learning we create a set of such training sets which are all diverse, leading to diverse classifiers. The method is dubbed Ensemble Projection (EP). EP captures not only the characteristics of individual images, but also the relationships among images. It is conceptually simple and computationally efficient, yet effective and flexible. Experiments on eight standard datasets show that: (1) EP outperforms previous methods for semi-supervised image classification; (2) EP produces promising results for self-taught image classification, where unlabeled samples are a random collection of images rather than being from the same distribution as the labeled ones; and (3) EP improves over the original features for image clustering. The code of the method is available on the project page.

arXiv:1511.03260

A Hierarchical Spectral Method for Extreme Classification

Extreme classification problems are multiclass and multilabel classification problems where the number of outputs is so large that straightforward strategies are neither statistically nor computationally viable. One strategy for dealing with the computational burden is via a tree decomposition of the output space. While this typically leads to training and inference that scales sublinearly with the number of outputs, it also results in reduced statistical performance. In this work, we identify two shortcomings of tree decomposition methods, and describe two heuristic mitigations. We compose these with an eigenvalue technique for constructing the tree. The end result is a computationally efficient algorithm that provides good statistical performance on several extreme data sets.

arXiv:1202.2194

Efficient statistical classification of satellite measurements

Supervised statistical classification is a vital tool for satellite image processing. It is useful not only when a discrete result, such as feature extraction or surface type, is required, but also for continuum retrievals by dividing the quantity of interest into discrete ranges. Because of the high resolution of modern satellite instruments and because of the requirement for real-time processing, any algorithm has to be fast to be useful. Here we describe an algorithm based on kernel estimation called Adaptive Gaussian Filtering that incorporates several innovations to produce superior efficiency as compared to three other popular methods: k-nearest-neighbour (KNN), Learning Vector Quantization (LVQ) and Support Vector Machines (SVM). This efficiency is gained with no compromises: accuracy is maintained, while estimates of the conditional probabilities are returned. These are useful not only to gauge the accuracy of an estimate in the absence of its true value, but also to re-calibrate a retrieved image and as a proxy for a discretized continuum variable. The algorithm is demonstrated and compared with the other three on a pair of synthetic test classes and to map the waterways of the Netherlands. Software may be found at: http://libagf.sourceforge.net.

arXiv:1602.03145

A New Spatio-Spectral Morphological Segmentation For Multi-Spectral Remote-Sensing Images

A general framework of spatio-spectral segmentation for multi-spectral images is introduced in this paper. The method is based on classification-driven stochastic watershed (WS) by Monte Carlo simulations, and it gives more regular and reliable contours than standard WS. The present approach is decomposed into several sequential steps. First, a dimensionality-reduction stage is performed using the factor-correspondence analysis method. In this context, a new way to select the factor axes (eigenvectors) according to their spatial information is introduced. Then, a spectral classification produces a spectral pre-segmentation of the image. Subsequently, a probability density function (pdf) of contours containing spatial and spectral information is estimated by simulation using a stochastic WS approach driven by the spectral classification. The pdf of the contours is finally segmented by a WS controlled by markers from a regularization of the initial classification.

arXiv:1602.03027

Minimax Lower Bounds for Realizable Transductive Classification

Transductive learning considers a training set of $m$ labeled samples and a test set of $u$ unlabeled samples, with the goal of best labeling that particular test set. Conversely, inductive learning considers a training set of $m$ labeled samples drawn iid from $P(X,Y)$, with the goal of best labeling any future samples drawn iid from $P(X)$. This comparison suggests that transduction is a much easier type of inference than induction, but is this really the case? This paper provides a negative answer to this question, by proving the first known minimax lower bounds for transductive, realizable, binary classification. Our lower bounds show that $m$ should be at least $\Omega(d/\epsilon + \log(1/\delta)/\epsilon)$ when $\epsilon$-learning a concept class $\mathcal{H}$ of finite VC-dimension $d<\infty$ with confidence $1-\delta$, for all $m \leq u$. This result draws three important conclusions. First, general transduction is as hard as general induction, since both problems have $\Omega(d/m)$ minimax values. Second, the use of unlabeled data does not help general transduction, since supervised learning algorithms such as ERM and (Hanneke, 2015) match our transductive lower bounds while ignoring the unlabeled test set. Third, our transductive lower bounds imply lower bounds for semi-supervised learning, which add to the important discussion about the role of unlabeled data in machine learning.

arXiv:1602.02899

Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data

Especially in the Big Data era, the usage of different classification methods is increasing day by day. The success of these classification methods depends on the effectiveness of learning methods. Extreme learning machine (ELM) classification algorithm is a relatively new learning method built on feed-forward neural-network. ELM classification algorithm is a simple and fast method that can create a model from high-dimensional data sets. Traditional ELM learning algorithm implicitly assumes complete access to whole data set. This is a major privacy concern in most of cases. Sharing of private data (i.e. medical records) is prevented because of security concerns. In this research, we propose an efficient and secure privacy-preserving learning algorithm for ELM classification over data that is vertically partitioned among several parties. The new learning method preserves the privacy on numerical attributes, builds a classification model without sharing private data without disclosing the data of each party to others.

arXiv:1602.02617

Adaptive imputation of missing values for incomplete pattern classification

In classification of incomplete pattern, the missing values can either play a crucial role in the class determination, or have only little influence (or eventually none) on the classification results according to the context. We propose a credal classification method for incomplete pattern with adaptive imputation of missing values based on belief function theory. At first, we try to classify the object (incomplete pattern) based only on the available attribute values. As underlying principle, we assume that the missing information is not crucial for the classification if a specific class for the object can be found using only the available information. In this case, the object is committed to this particular class. However, if the object cannot be classified without ambiguity, it means that the missing values play a main role for achieving an accurate classification. In this case, the missing values will be imputed based on the K-nearest neighbor (K-NN) and self-organizing map (SOM) techniques, and the edited pattern with the imputation is then classified. The (original or edited) pattern is respectively classified according to each training class, and the classification results represented by basic belief assignments are fused with proper combination rules for making the credal classification. The object is allowed to belong with different masses of belief to the specific classes and meta-classes (which are particular disjunctions of several single classes). The credal classification captures well the uncertainty and imprecision of classification, and reduces effectively the rate of misclassifications thanks to the introduction of meta-classes. The effectiveness of the proposed method with respect to other classical methods is demonstrated based on several experiments using artificial and real data sets.

arXiv:1602.02210

Classification accuracy as a proxy for two sample testing

When data analysts train a classifier and check if its accuracy is significantly different from chance, they are implicitly performing a two-sample test. We investigate the statistical properties of this flexible approach in the high-dimensional setting. We prove two results that hold for all classifiers in any dimensions: if its true error remains $\epsilon$-better than chance for some $\epsilon>0$ as $d,n \to \infty$, then (a) the permutation-based test is consistent (has power approaching to one), (b) a computationally efficient test based on a Gaussian approximation of the null distribution is also consistent. To get a finer understanding of the rates of consistency, we study a specialized setting of distinguishing Gaussians with mean-difference $\delta$ and common (known or unknown) covariance $\Sigma$, when $d/n \to c \in (0,\infty)$. We study variants of Fisher's linear discriminant analysis (LDA) such as "naive Bayes" in a nontrivial regime when $\epsilon \to 0$ (the Bayes classifier has true accuracy approaching 1/2), and contrast their power with corresponding variants of Hotelling's test. Surprisingly, the expressions for their power match exactly in terms of $n,d,\delta,\Sigma$, and the LDA approach is only worse by a constant factor, achieving an asymptotic relative efficiency (ARE) of $1/\sqrt{\pi}$ for balanced samples. We also extend our results to high-dimensional elliptical distributions with finite kurtosis. Other results of independent interest include minimax lower bounds, and the optimality of Hotelling's test when $d=o(n)$. Simulation results validate our theory, and we present practical takeaway messages along with natural open problems.

arXiv:1511.06744

Training CNNs with Low-Rank Filters for Efficient Image Classification

We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versions, we learn a set of small basis filters from scratch; during training, the network learns to combine these basis filters into more complex filters that are discriminative for image classification. To train such networks, a novel weight initialization scheme is used. This allows effective initialization of connection weights in convolutional layers composed of groups of differently-shaped filters. We validate our approach by applying it to several existing CNN architectures and training these networks from scratch using the CIFAR, ILSVRC and MIT Places datasets. Our results show similar or higher accuracy than conventional CNNs with much less compute. Applying our method to an improved version of VGG-11 network using global max-pooling, we achieve comparable validation accuracy using 41% less compute and only 24% of the original VGG-11 model parameters; another variant of our method gives a 1 percentage point increase in accuracy over our improved VGG-11 model, giving a top-5 center-crop validation accuracy of 89.7% while reducing computation by 16% relative to the original VGG-11 model. Applying our method to the GoogLeNet architecture for ILSVRC, we achieved comparable accuracy with 26% less compute and 41% fewer model parameters. Applying our method to a near state-of-the-art network for CIFAR, we achieved comparable accuracy with 46% less compute and 55% fewer parameters.

arXiv:1602.04489

Convolutional Tables Ensemble: classification in microseconds

We study classifiers operating under severe classification time constraints, corresponding to 1-1000 CPU microseconds, using Convolutional Tables Ensemble (CTE), an inherently fast architecture for object category recognition. The architecture is based on convolutionally-applied sparse feature extraction, using trees or ferns, and a linear voting layer. Several structure and optimization variants are considered, including novel decision functions, tree learning algorithm, and distillation from CNN to CTE architecture. Accuracy improvements of 24-45% over related art of similar speed are demonstrated on standard object recognition benchmarks. Using Pareto speed-accuracy curves, we show that CTE can provide better accuracy than Convolutional Neural Networks (CNN) for a certain range of classification time constraints, or alternatively provide similar error rates with 5-200X speedup.

arXiv:1503.01436

Class Probability Estimation via Differential Geometric Regularization

We study the problem of supervised learning for both binary and multiclass classification from a unified geometric perspective. In particular, we propose a geometric regularization technique to find the submanifold corresponding to a robust estimator of the class probability $P(y|\pmb{x})$. The regularization term measures the volume of this submanifold, based on the intuition that overfitting produces rapid local oscillations and hence large volume of the estimator. This technique can be applied to regularize any classification function that satisfies two requirements: firstly, an estimator of the class probability can be obtained; secondly, first and second derivatives of the class probability estimator can be calculated. In experiments, we apply our regularization technique to standard loss functions for classification, our RBF-based implementation compares favorably to widely used regularization methods for both binary and multiclass classification.

arXiv:1602.05310

Large Scale Kernel Learning using Block Coordinate Descent

We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points. Armed with this capability, we conduct a thorough comparison between the full kernel, the Nystr\"om method, and random features on three large classification tasks from various domains. Our results suggest that the Nystr\"om method generally achieves better statistical accuracy than random features, but can require significantly more iterations of optimization. Lastly, we derive new rates for block coordinate descent which support our experimental findings when specialized to kernel methods.

arXiv:1602.00489

Real Time Video Quality Representation Classification of Encrypted HTTP Adaptive Video Streaming - the Case of Safari

The increasing popularity of HTTP adaptive video streaming services has dramatically increased bandwidth requirements on operator networks, which attempt to shape their traffic through Deep Packet Inspection (DPI). However, Google and certain content providers have started to encrypt their video services. As a result, operators often encounter difficulties in shaping their encrypted video traffic via DPI. This highlights the need for new traffic classification methods for encrypted HTTP adaptive video streaming to enable smart traffic shaping. These new methods will have to effectively estimate the quality representation layer and playout buffer. We present a new method and show for the first time that video quality representation classification for (YouTube) encrypted HTTP adaptive streaming is possible. We analyze the performance of this classification method with Safari over HTTPS. Based on a large number of offline and online traffic classification experiments, we demonstrate that it can independently classify, in real time, every video segment into one of the quality representation layers with 97.18% average accuracy.

arXiv:1508.01720

Mismatch in the Classification of Linear Subspaces: Sufficient Conditions for Reliable Classification

This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix. We also assume that the classifier knows only a mismatched version of the parameters of input distribution in lieu of the true parameters. By constructing an asymptotic low-noise expansion of an upper bound to the error probability of such a mismatched classifier, we provide sufficient conditions for reliable classification in the low-noise regime that are able to sharply predict the absence of a classification error floor. Such conditions are a function of the geometry of the true signal distribution, the geometry of the mismatched signal distributions as well as the interplay between such geometries, namely, the principal angles and the overlap between the true and the mismatched signal subspaces. Numerical results demonstrate that our conditions for reliable classification can sharply predict the behavior of a mismatched classifier both with synthetic data and in a motion segmentation and a hand-written digit classification applications.

arXiv:1506.08230

Convolutional networks and learning invariant to homogeneous multiplicative scalings

The conventional classification schemes -- notably multinomial logistic regression -- used in conjunction with convolutional networks (convnets) are classical in statistics, designed without consideration for the usual coupling with convnets, stochastic gradient descent, and backpropagation. In the specific application to supervised learning for convnets, a simple scale-invariant classification stage turns out to be more robust than multinomial logistic regression, appears to result in slightly lower errors on several standard test sets, has similar computational costs, and features precise control over the actual rate of learning. "Scale-invariant" means that multiplying the input values by any nonzero scalar leaves the output unchanged.