PyTorchKR Papers

최신 논문

총 11,809편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1811.12507

Regression and Classification by Zonal Kriging

Consider a family $Z=\{\boldsymbol{x_{i}},y_{i}$,$1\leq i\leq N\}$ of $N$ pairs of vectors $\boldsymbol{x_{i}} \in \mathbb{R}^d$ and scalars $y_{i}$ that we aim to predict for a new sample vector $\mathbf{x}_0$. Kriging models $y$ as a sum of a deterministic function $m$, a drift which depends on the point $\boldsymbol{x}$, and a random function $z$ with zero mean. The zonality hypothesis interprets $y$ as a weighted sum of $d$ random functions of a single independent variables, each of which is a kriging, with a quadratic form for the variograms drift. We can therefore construct an unbiased estimator $y^{*}(\boldsymbol{x_{0}})=\sum_{i}\lambda^{i}z(\boldsymbol{x_{i}})$ de $y(\boldsymbol{x_{0}})$ with minimal variance $E[y^{*}(\boldsymbol{x_{0}})-y(\boldsymbol{x_{0}})]^{2}$, with the help of the known training set points. We give the explicitly closed form for $\lambda^{i}$ without having calculated the inverse of the matrices.

arXiv:1811.02471공식 코드 · Papers with Code

Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery

Clouds frequently cover the Earth's surface and pose an omnipresent challenge to optical Earth observation methods. The vast majority of remote sensing approaches either selectively choose single cloud-free observations or employ a pre-classification strategy to identify and mask cloudy pixels. We follow a different strategy and treat cloud coverage as noise that is inherent to the observed satellite data. In prior work, we directly employed a straightforward \emph{convolutional long short-term memory} network for vegetation classification without explicit cloud filtering and achieved state-of-the-art classification accuracies. In this work, we investigate this cloud-robustness further by visualizing internal cell activations and performing an ablation experiment on datasets of different cloud coverage. In the visualizations of network states, we identified some cells in which modulation and input gates closed on cloudy pixels. This indicates that the network has internalized a cloud-filtering mechanism without being specifically trained on cloud labels. Overall, our results question the necessity of sophisticated pre-processing pipelines for multi-temporal deep learning approaches.

arXiv:1512.06303

Predicting the Sentiment Polarity and Rating of Yelp Reviews

Online reviews of businesses have become increasingly important in recent years, as customers and even competitors use them to judge the quality of a business. Yelp is one of the most popular websites for users to write such reviews, and it would be useful for them to be able to predict the sentiment or even the star rating of a review. In this paper, we develop two classifiers to perform positive/negative classification and 5-star classification. We use Naive Bayes, Support Vector Machines, and Logistic Regression as models, and achieved the best accuracy with Logistic Regression: 92.90% for positive/negative classification, and 63.92% for 5-star classification. These results demonstrate the quality of the Logistic Regression model using only the text of the review, yet there is a promising opportunity for improvement with more data, more features, and perhaps different models.

arXiv:1811.12748공식 코드 · Papers with Code

Improving Landmark Recognition using Saliency detection and Feature classification

Image Landmark Recognition has been one of the most sought-after classification challenges in the field of vision and perception. After so many years of generic classification of buildings and monuments from images, people are now focussing upon fine-grained problems - recognizing the category of each building or monument. We proposed an ensemble network for the purpose of classification of Indian Landmark Images. To this end, our method gives robust classification by ensembling the predictions from Graph-Based Visual Saliency (GBVS) network alongwith supervised feature-based classification algorithms such as kNN and Random Forest. The final architecture is an adaptive learning of all the mentioned networks. The proposed network produces a reliable score to eliminate false category cases. Evaluation of our model was done on a new dataset, which involves challenges such as landmark clutter, variable scaling, partial occlusion, etc.

arXiv:1811.11819

Unsupervised Meta-Learning For Few-Shot Image Classification

Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. In this paper, we propose UMTRA, an algorithm that performs unsupervised, model-agnostic meta-learning for classification tasks. The meta-learning step of UMTRA is performed on a flat collection of unlabeled images. While we assume that these images can be grouped into a diverse set of classes and are relevant to the target task, no explicit information about the classes or any labels are needed. UMTRA uses random sampling and augmentation to create synthetic training tasks for meta-learning phase. Labels are only needed at the final target task learning step, and they can be as little as one sample per class. On the Omniglot and Mini-Imagenet few-shot learning benchmarks, UMTRA outperforms every tested approach based on unsupervised learning of representations, while alternating for the best performance with the recent CACTUs algorithm. Compared to supervised model-agnostic meta-learning approaches, UMTRA trades off some classification accuracy for a reduction in the required labels of several orders of magnitude.

arXiv:1811.12081

Deep Haar Scattering Networks in Pattern Recognition: A promising approach

The aim of this paper is to discuss the use of Haar scattering networks, which is a very simple architecture that naturally supports a large number of stacked layers, yet with very few parameters, in a relatively broad set of pattern recognition problems, including regression and classification tasks. This architecture, basically, consists of stacking convolutional filters, that can be thought as a generalization of Haar wavelets, followed by non-linear operators which aim to extract symmetries and invariances that are later fed in a classification/regression algorithm. We show that good results can be obtained with the proposed method for both kind of tasks. We have outperformed the best available algorithms in 4 out of 18 important data classification problems, and have obtained a more robust performance than ARIMA and ETS time series methods in regression problems for data with strong periodicities.

arXiv:1811.12044

A snapshot on nonstandard supervised learning problems: taxonomy, relationships and methods

Machine learning is a field which studies how machines can alter and adapt their behavior, improving their actions according to the information they are given. This field is subdivided into multiple areas, among which the best known are supervised learning (e.g. classification and regression) and unsupervised learning (e.g. clustering and association rules). Within supervised learning, most studies and research are focused on well known standard tasks, such as binary classification, multiclass classification and regression with one dependent variable. However, there are many other less known problems. These are what we generically call nonstandard supervised learning problems. The literature about them is much more sparse, and each study is directed to a specific task. Therefore, the definitions, relations and applications of this kind of learners are hard to find. The goal of this paper is to provide the reader with a broad view on the distinct variations of nonstandard supervised problems. A comprehensive taxonomy summarizing their traits is proposed. A review of the common approaches followed to accomplish them and their main applications is provided as well.

arXiv:1811.11243

eXclusive Autoencoder (XAE) for Nucleus Detection and Classification on Hematoxylin and Eosin (H&E) Stained Histopathological Images

In this paper, we introduced a novel feature extraction approach, named exclusive autoencoder (XAE), which is a supervised version of autoencoder (AE), able to largely improve the performance of nucleus detection and classification on hematoxylin and eosin (H&E) histopathological images. The proposed XAE can be used in any AE-based algorithm, as long as the data labels are also provided in the feature extraction phase. In the experiments, we evaluated the performance of an approach which is the combination of an XAE and a fully connected neural network (FCN) and compared with some AE-based methods. For a nucleus detection problem (considered as a nucleus/non-nucleus classification problem) on breast cancer H&E images, the F-score of the proposed XAE+FCN approach achieved 96.64% while the state-of-the-art was at 84.49%. For nucleus classification on colorectal cancer H&E images, with the annotations of four categories of epithelial, inflammatory, fibroblast and miscellaneous nuclei. The F-score of the proposed method reached 70.4%. We also proposed a lymphocyte segmentation method. In the step of lymphocyte detection, we have compared with cutting-edge technology and gained improved performance from 90% to 98.67%. We also proposed an algorithm for lymphocyte segmentation based on nucleus detection and classification. The obtained Dice coefficient achieved 88.31% while the cutting-edge approach was at 74%.

arXiv:1811.11353

Multi-label classification search space in the MEKA software

This supplementary material aims to describe the proposed multi-label classification (MLC) search spaces based on the MEKA and WEKA softwares. First, we overview 26 MLC algorithms and meta-algorithms in MEKA, presenting their main characteristics, such as hyper-parameters, dependencies and constraints. Second, we review 28 single-label classification (SLC) algorithms, preprocessing algorithms and meta-algorithms in the WEKA software. These SLC algorithms were also studied because they are part of the proposed MLC search spaces. Fundamentally, this occurs due to the problem transformation nature of several MLC algorithms used in this work. These algorithms transform an MLC problem into one or several SLC problems in the first place and solve them with SLC model(s) in a next step. Therefore, understanding their main characteristics is crucial to this work. Finally, we present a formal description of the search spaces by proposing a context-free grammar that encompasses the 54 learning algorithms. This grammar basically comprehends the possible combinations, the constraints and dependencies among the learning algorithms.

arXiv:1811.11103

Bayesian graph convolutional neural networks for semi-supervised classification

Recently, techniques for applying convolutional neural networks to graph-structured data have emerged. Graph convolutional neural networks (GCNNs) have been used to address node and graph classification and matrix completion. Although the performance has been impressive, the current implementations have limited capability to incorporate uncertainty in the graph structure. Almost all GCNNs process a graph as though it is a ground-truth depiction of the relationship between nodes, but often the graphs employed in applications are themselves derived from noisy data or modelling assumptions. Spurious edges may be included; other edges may be missing between nodes that have very strong relationships. In this paper we adopt a Bayesian approach, viewing the observed graph as a realization from a parametric family of random graphs. We then target inference of the joint posterior of the random graph parameters and the node (or graph) labels. We present the Bayesian GCNN framework and develop an iterative learning procedure for the case of assortative mixed-membership stochastic block models. We present the results of experiments that demonstrate that the Bayesian formulation can provide better performance when there are very few labels available during the training process.

arXiv:1811.11079

Robust Classification of Financial Risk

Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that real-world systems are also susceptible to manipulation or misclassification, which especially poses a challenge to machine learning models used in financial services. We use the loan grade classification problem to explore how machine learning models are sensitive to small changes in user-reported data, using adversarial attacks documented in the literature and an original, domain-specific attack. Our work shows that a robust optimization algorithm can build models for financial services that are resistant to misclassification on perturbations. To the best of our knowledge, this is the first study of adversarial attacks and defenses for deep learning in financial services.

arXiv:1811.10419

Multi-Task Generative Adversarial Network for Handling Imbalanced Clinical Data

We propose a new generative adversarial architecture to mitigate imbalance data problem for the task of medical image semantic segmentation where the majority of pixels belong to a healthy region and few belong to lesion or non-health region. A model trained with imbalanced data tends to bias towards healthy data which is not desired in clinical applications. We design a new conditional GAN with two components: a generative model and a discriminative model to mitigate imbalanced data problem through selective weighted loss. While the generator is trained on sequential magnetic resonance images (MRI) to learn semantic segmentation and disease classification, the discriminator classifies whether a generated output is real or fake. The proposed architecture achieved state-of-the-art results on ACDC-2017 for cardiac segmentation and diseases classification. We have achieved competitive results on BraTS-2017 for brain tumor segmentation and brain diseases classification.

arXiv:1811.09863

MEMOIR: Multi-class Extreme Classification with Inexact Margin

Multi-class classification with a very large number of classes, or extreme classification, is a challenging problem from both statistical and computational perspectives. Most of the classical approaches to multi-class classification, including one-vs-rest or multi-class support vector machines, require the exact estimation of the classifier's margin, at both the training and the prediction steps making them intractable in extreme classification scenarios. In this paper, we study the impact of computing an approximate margin using nearest neighbor (ANN) search structures combined with locality-sensitive hashing (LSH). This approximation allows to dramatically reduce both the training and the prediction time without a significant loss in performance. We theoretically prove that this approximation does not lead to a significant loss of the risk of the model and provide empirical evidence over five publicly available large scale datasets, showing that the proposed approach is highly competitive with respect to state-of-the-art approaches on time, memory and performance measures.

arXiv:1811.09607

Towards Emotion Recognition: A Persistent Entropy Application

Emotion recognition and classification is a very active area of research. In this paper, we present a first approach to emotion classification using persistent entropy and support vector machines. A topology-based model is applied to obtain a single real number from each raw signal. These data are used as input of a support vector machine to classify signals into 8 different emotions (calm, happy, sad, angry, fearful, disgust and surprised).

arXiv:1811.10166공식 코드 · Papers with Code

Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series

New remote sensing sensors now acquire high spatial and spectral Satellite Image Time Series (SITS) of the world. These series of images are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth's surfaces. More specifically, the combination of the temporal, spectral and spatial resolutions of new SITS makes possible to monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied for SITS classification, these algorithms do not make the most of the temporal domain. Conversely, some approaches that take into account the temporal dimension have recently been tested, especially Recurrent Neural Networks (RNNs). This paper proposes an exhaustive study of another deep learning approaches, namely Temporal Convolutional Neural Networks (TempCNNs) where convolutions are applied in the temporal dimension. The goal is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification. This paper proposes a set of experiments performed on one million time series extracted from 46 Formosat-2 images. The experimental results show that TempCNNs are more accurate than RF and RNNs, that are the current state of the art for SITS classification. We also highlight some differences with results obtained in computer vision, e.g. about pooling layers. Moreover, we provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size. Finally, we assess the visual quality of the land cover maps produced by TempCNNs.

arXiv:1811.10501

Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification

We present a generative approach to classify scarcely observed longitudinal patient trajectories. The available time series are represented as tensors and factorized using generative deep recurrent neural networks. The learned factors represent the patient data in a compact way and can then be used in a downstream classification task. For more robustness and accuracy in the predictions, we used an ensemble of those deep generative models to mimic Bayesian posterior sampling. We illustrate the performance of our architecture on an intensive-care case study of in-hospital mortality prediction with 96 longitudinal measurement types measured across the first 48-hour from admission. Our combination of generative and ensemble strategies achieves an AUC of over 0.85, and outperforms the SAPS-II mortality score and GRU baselines.

arXiv:1811.09128

Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs

Understanding driver activity is vital for in-vehicle systems that aim to reduce the incidence of car accidents rooted in cognitive distraction. Automating real-time behavior recognition while ensuring actions classification with high accuracy is however challenging, given the multitude of circumstances surrounding drivers, the unique traits of individuals, and the computational constraints imposed by in-vehicle embedded platforms. Prior work fails to jointly meet these runtime/accuracy requirements and mostly rely on a single sensing modality, which in turn can be a single point of failure. In this paper, we harness the exceptional feature extraction abilities of deep learning and propose a dedicated Interwoven Deep Convolutional Neural Network (InterCNN) architecture to tackle the problem of accurate classification of driver behaviors in real-time. The proposed solution exploits information from multi-stream inputs, i.e., in-vehicle cameras with different fields of view and optical flows computed based on recorded images, and merges through multiple fusion layers abstract features that it extracts. This builds a tight ensembling system, which significantly improves the robustness of the model. In addition, we introduce a temporal voting scheme based on historical inference instances, to enhance the classification accuracy. Experiments conducted with a dataset that we collect in a mock-up car environment demonstrate that the proposed InterCNN with MobileNet convolutional blocks can classify 9 different behaviors with 73.97% accuracy, and 5 'aggregated' behaviors with 81.66% accuracy. We further show that our architecture is highly computationally efficient, as it performs inferences within 15ms, which satisfies the real-time constraints of intelligent cars. Nevertheless, our InterCNN is robust to lossy input, as the classification remains accurate when two input streams are occluded.

arXiv:1811.08919

Robust Active Learning for Electrocardiographic Signal Classification

The classification of electrocardiographic (ECG) signals is a challenging problem for healthcare industry. Traditional supervised learning methods require a large number of labeled data which is usually expensive and difficult to obtain for ECG signals. Active learning is well-suited for ECG signal classification as it aims at selecting the best set of labeled data in order to maximize the classification performance. Motivated by the fact that ECG data are usually heavily unbalanced among different classes and the class labels are noisy as they are manually labeled, this paper proposes a novel solution based on robust active learning for addressing these challenges. The key idea is to first apply the clustering of the data in a low dimensional embedded space and then select the most information instances within local clusters. By selecting the most informative instances relying on local average minimal distances, the algorithm tends to select the data for labelling in a more diversified way. Finally, the robustness of the model is further enhanced by adding a novel noisy label reduction scheme after the selection of the labeled data. Experiments on the ECG signal classification from the MIT-BIH arrhythmia database demonstrate the effectiveness of the proposed algorithm.

arXiv:1811.09595

Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size. Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes. To this end, we propose a novel multigraph network that learns from multi-relational graphs. We model learned edges with abstract meaning and experiment with different ways to fuse the representations extracted from annotated and learned edges, achieving competitive results on a variety of chemical classification benchmarks.