PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1504.04003공식 코드 · Papers with Code

Anatomy-specific classification of medical images using deep convolutional nets

Automated classification of human anatomy is an important prerequisite for many computer-aided diagnosis systems. The spatial complexity and variability of anatomy throughout the human body makes classification difficult. "Deep learning" methods such as convolutional networks (ConvNets) outperform other state-of-the-art methods in image classification tasks. In this work, we present a method for organ- or body-part-specific anatomical classification of medical images acquired using computed tomography (CT) with ConvNets. We train a ConvNet, using 4,298 separate axial 2D key-images to learn 5 anatomical classes. Key-images were mined from a hospital PACS archive, using a set of 1,675 patients. We show that a data augmentation approach can help to enrich the data set and improve classification performance. Using ConvNets and data augmentation, we achieve anatomy-specific classification error of 5.9 % and area-under-the-curve (AUC) values of an average of 0.998 in testing. We demonstrate that deep learning can be used to train very reliable and accurate classifiers that could initialize further computer-aided diagnosis.

arXiv:1504.03967

Deep convolutional networks for pancreas segmentation in CT imaging

Automatic organ segmentation is an important prerequisite for many computer-aided diagnosis systems. The high anatomical variability of organs in the abdomen, such as the pancreas, prevents many segmentation methods from achieving high accuracies when compared to other segmentation of organs like the liver, heart or kidneys. Recently, the availability of large annotated training sets and the accessibility of affordable parallel computing resources via GPUs have made it feasible for "deep learning" methods such as convolutional networks (ConvNets) to succeed in image classification tasks. These methods have the advantage that used classification features are trained directly from the imaging data. We present a fully-automated bottom-up method for pancreas segmentation in computed tomography (CT) images of the abdomen. The method is based on hierarchical coarse-to-fine classification of local image regions (superpixels). Superpixels are extracted from the abdominal region using Simple Linear Iterative Clustering (SLIC). An initial probability response map is generated, using patch-level confidences and a two-level cascade of random forest classifiers, from which superpixel regions with probabilities larger 0.5 are retained. These retained superpixels serve as a highly sensitive initial input of the pancreas and its surroundings to a ConvNet that samples a bounding box around each superpixel at different scales (and random non-rigid deformations at training time) in order to assign a more distinct probability of each superpixel region being pancreas or not. We evaluate our method on CT images of 82 patients (60 for training, 2 for validation, and 20 for testing). Using ConvNets we achieve average Dice scores of 68%+-10% (range, 43-80%) in testing. This shows promise for accurate pancreas segmentation, using a deep learning approach and compares favorably to state-of-the-art methods.

arXiv:1504.03874

Bridging belief function theory to modern machine learning

Machine learning is a quickly evolving field which now looks really different from what it was 15 years ago, when classification and clustering were major issues. This document proposes several trends to explore the new questions of modern machine learning, with the strong afterthought that the belief function framework has a major role to play.

arXiv:1504.03608

A data-based classification of Slavic languages: Indices of qualitative variation applied to grapheme frequencies

The Ord's graph is a simple graphical method for displaying frequency distributions of data or theoretical distributions in the two-dimensional plane. Its coordinates are proportions of the first three moments, either empirical or theoretical ones. A modification of the Ord's graph based on proportions of indices of qualitative variation is presented. Such a modification makes the graph applicable also to data of categorical character. In addition, the indices are normalized with values between 0 and 1, which enables comparing data files divided into different numbers of categories. Both the original and the new graph are used to display grapheme frequencies in eleven Slavic languages. As the original Ord's graph requires an assignment of numbers to the categories, graphemes were ordered decreasingly according to their frequencies. Data were taken from parallel corpora, i.e., we work with grapheme frequencies from a Russian novel and its translations to ten other Slavic languages. Then, cluster analysis is applied to the graph coordinates. While the original graph yields results which are not linguistically interpretable, the modification reveals meaningful relations among the languages.

arXiv:1504.03415

HHCART: An Oblique Decision Tree

Decision trees are a popular technique in statistical data classification. They recursively partition the feature space into disjoint sub-regions until each sub-region becomes homogeneous with respect to a particular class. The basic Classification and Regression Tree (CART) algorithm partitions the feature space using axis parallel splits. When the true decision boundaries are not aligned with the feature axes, this approach can produce a complicated boundary structure. Oblique decision trees use oblique decision boundaries to potentially simplify the boundary structure. The major limitation of this approach is that the tree induction algorithm is computationally expensive. In this article we present a new decision tree algorithm, called HHCART. The method utilizes a series of Householder matrices to reflect the training data at each node during the tree construction. Each reflection is based on the directions of the eigenvectors from each classes' covariance matrix. Considering axis parallel splits in the reflected training data provides an efficient way of finding oblique splits in the unreflected training data. Experimental results show that the accuracy and size of the HHCART trees are comparable with some benchmark methods in the literature. The appealing feature of HHCART is that it can handle both qualitative and quantitative features in the same oblique split.

arXiv:1504.03106

Learning Multiple Visual Tasks while Discovering their Structure

Multi-task learning is a natural approach for computer vision applications that require the simultaneous solution of several distinct but related problems, e.g. object detection, classification, tracking of multiple agents, or denoising, to name a few. The key idea is that exploring task relatedness (structure) can lead to improved performances. In this paper, we propose and study a novel sparse, non-parametric approach exploiting the theory of Reproducing Kernel Hilbert Spaces for vector-valued functions. We develop a suitable regularization framework which can be formulated as a convex optimization problem, and is provably solvable using an alternating minimization approach. Empirical tests show that the proposed method compares favorably to state of the art techniques and further allows to recover interpretable structures, a problem of interest in its own right.

arXiv:1504.02975

Classification with Extreme Learning Machine and Ensemble Algorithms Over Randomly Partitioned Data

In this age of Big Data, machine learning based data mining methods are extensively used to inspect large scale data sets. Deriving applicable predictive modeling from these type of data sets is a challenging obstacle because of their high complexity. Opportunity with high data availability levels, automated classification of data sets has become a critical and complicated function. In this paper, the power of applying MapReduce based Distributed AdaBoosting of Extreme Learning Machine (ELM) are explored to build reliable predictive bag of classification models. Thus, (i) dataset ensembles are build; (ii) ELM algorithm is used to build weak classification models; and (iii) build a strong classification model from a set of weak classification models. This training model is applied to the publicly available knowledge discovery and data mining datasets.

arXiv:1504.02902

Gradual Training Method for Denoising Auto Encoders

Stacked denoising auto encoders (DAEs) are well known to learn useful deep representations, which can be used to improve supervised training by initializing a deep network. We investigate a training scheme of a deep DAE, where DAE layers are gradually added and keep adapting as additional layers are added. We show that in the regime of mid-sized datasets, this gradual training provides a small but consistent improvement over stacked training in both reconstruction quality and classification error over stacked training on MNIST and CIFAR datasets.

arXiv:1504.02870

Quick sensitivity analysis for incremental data modification and its application to leave-one-out CV in linear classification problems

We introduce a novel sensitivity analysis framework for large scale classification problems that can be used when a small number of instances are incrementally added or removed. For quickly updating the classifier in such a situation, incremental learning algorithms have been intensively studied in the literature. Although they are much more efficient than solving the optimization problem from scratch, their computational complexity yet depends on the entire training set size. It means that, if the original training set is large, completely solving an incremental learning problem might be still rather expensive. To circumvent this computational issue, we propose a novel framework that allows us to make an inference about the updated classifier without actually re-optimizing it. Specifically, the proposed framework can quickly provide a lower and an upper bounds of a quantity on the unknown updated classifier. The main advantage of the proposed framework is that the computational cost of computing these bounds depends only on the number of updated instances. This property is quite advantageous in a typical sensitivity analysis task where only a small number of instances are updated. In this paper we demonstrate that the proposed framework is applicable to various practical sensitivity analysis tasks, and the bounds provided by the framework are often sufficiently tight for making desired inferences.

arXiv:1504.02800

High-Dimensional Classification for Brain Decoding

Brain decoding involves the determination of a subject's cognitive state or an associated stimulus from functional neuroimaging data measuring brain activity. In this setting the cognitive state is typically characterized by an element of a finite set, and the neuroimaging data comprise voluminous amounts of spatiotemporal data measuring some aspect of the neural signal. The associated statistical problem is one of classification from high-dimensional data. We explore the use of functional principal component analysis, mutual information networks, and persistent homology for examining the data through exploratory analysis and for constructing features characterizing the neural signal for brain decoding. We review each approach from this perspective, and we incorporate the features into a classifier based on symmetric multinomial logistic regression with elastic net regularization. The approaches are illustrated in an application where the task is to infer, from brain activity measured with magnetoencephalography (MEG), the type of video stimulus shown to a subject.

arXiv:1504.02518

Unsupervised Feature Learning from Temporal Data

Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.

arXiv:1503.08909

Beyond Short Snippets: Deep Networks for Video Classification

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 72.8%).

arXiv:1412.6856

Object Detectors Emerge in Deep Scene CNNs

With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discovers meaningful objects detectors, representative of the learned scene categories. With object detectors emerging as a result of learning to recognize scenes, our work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects.

arXiv:1412.6598

Automatic Discovery and Optimization of Parts for Image Classification

Part-based representations have been shown to be very useful for image classification. Learning part-based models is often viewed as a two-stage problem. First, a collection of informative parts is discovered, using heuristics that promote part distinctiveness and diversity, and then classifiers are trained on the vector of part responses. In this paper we unify the two stages and learn the image classifiers and a set of shared parts jointly. We generate an initial pool of parts by randomly sampling part candidates and selecting a good subset using L1/L2 regularization. All steps are driven "directly" by the same objective namely the classification loss on a training set. This lets us do away with engineered heuristics. We also introduce the notion of "negative parts", intended as parts that are negatively correlated with one or more classes. Negative parts are complementary to the parts discovered by other methods, which look only for positive correlations.

arXiv:1504.05473

Can FCA-based Recommender System Suggest a Proper Classifier?

The paper briefly introduces multiple classifier systems and describes a new algorithm, which improves classification accuracy by means of recommendation of a proper algorithm to an object classification. This recommendation is done assuming that a classifier is likely to predict the label of the object correctly if it has correctly classified its neighbors. The process of assigning a classifier to each object is based on Formal Concept Analysis. We explain the idea of the algorithm with a toy example and describe our first experiments with real-world datasets.

arXiv:1504.04646

Performance Evaluation of Machine Learning Algorithms in Post-operative Life Expectancy in the Lung Cancer Patients

The nature of clinical data makes it difficult to quickly select, tune and apply machine learning algorithms to clinical prognosis. As a result, a lot of time is spent searching for the most appropriate machine learning algorithms applicable in clinical prognosis that contains either binary-valued or multi-valued attributes. The study set out to identify and evaluate the performance of machine learning classification schemes applied in clinical prognosis of post-operative life expectancy in the lung cancer patients. Multilayer Perceptron, J48, and the Naive Bayes algorithms were used to train and test models on Thoracic Surgery datasets obtained from the University of California Irvine machine learning repository. Stratified 10-fold cross-validation was used to evaluate baseline performance accuracy of the classifiers. The comparative analysis shows that multilayer perceptron performed best with classification accuracy of 82.3%, J48 came out second with classification accuracy of 81.8%, and Naive Bayes came out the worst with classification accuracy of 74.4%. The quality and outcome of the chosen machine learning algorithms depends on the ingenuity of the clinical miner.

arXiv:1504.04588

The Nataf-Beta Random Field Classifier: An Extension of the Beta Conjugate Prior to Classification Problems

This paper presents the Nataf-Beta Random Field Classifier, a discriminative approach that extends the applicability of the Beta conjugate prior to classification problems. The approach's key feature is to model the probability of a class conditional on attribute values as a random field whose marginals are Beta distributed, and where the parameters of marginals are themselves described by random fields. Although the classification accuracy of the approach proposed does not statistically outperform the best accuracies reported in the literature, it ranks among the top tier for the six benchmark datasets tested. The Nataf-Beta Random Field Classifier is suited as a general purpose classification approach for real-continuous and real-integer attribute value problems.

arXiv:1504.04216

Genetic algorithm implementation for effective document subject search

This paper describes the software implementation of genetic algorithm for identifying and selecting most relevant results received during sequentially executed subject search operations. Simulated evolutionary process generates sustainable and effective population of search queries, forms search pattern of documents or semantic core, creates relevant sets of required documents, allows automatic classification of search results. The paper discusses the features of subject search, justifies the use of a genetic algorithm, describes arguments of the fitness function and describes basic steps and parameters of the algorithm.

arXiv:1502.02710

Scalable Multilabel Prediction via Randomized Methods

Modeling the dependence between outputs is a fundamental challenge in multilabel classification. In this work we show that a generic regularized nonlinearity mapping independent predictions to joint predictions is sufficient to achieve state-of-the-art performance on a variety of benchmark problems. Crucially, we compute the joint predictions without ever obtaining any independent predictions, while incorporating low-rank and smoothness regularization. We achieve this by leveraging randomized algorithms for matrix decomposition and kernel approximation. Furthermore, our techniques are applicable to the multiclass setting. We apply our method to a variety of multiclass and multilabel data sets, obtaining state-of-the-art results.

arXiv:1412.6881

On Learning Vector Representations in Hierarchical Label Spaces

An important problem in multi-label classification is to capture label patterns or underlying structures that have an impact on such patterns. This paper addresses one such problem, namely how to exploit hierarchical structures over labels. We present a novel method to learn vector representations of a label space given a hierarchy of labels and label co-occurrence patterns. Our experimental results demonstrate qualitatively that the proposed method is able to learn regularities among labels by exploiting a label hierarchy as well as label co-occurrences. It highlights the importance of the hierarchical information in order to obtain regularities which facilitate analogical reasoning over a label space. We also experimentally illustrate the dependency of the learned representations on the label hierarchy.