PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1911.11018

A Self-Adaptive Synthetic Over-Sampling Technique for Imbalanced Classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50% to 80%) is used for training and the rest for validation. In many problems, however, the data is highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesising feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesise data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesising data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, e.g. support vector machine, k-nearest neighbour, deep networks, rule-based classifiers, decision trees, etc. The results demonstrated that: i) a significantly more balanced (and fair) classification results can be achieved; ii) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.

arXiv:1911.10182

Universal adversarial examples in speech command classification

Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied in the image domain, classification tasks in the audio domain have received less attention. In this paper we address the existence of universal perturbations for speech command classification. We provide evidence that universal attacks can be generated for speech command classification tasks, which are able to generalize across different models to a significant extent. Additionally, a novel analytical framework is proposed for the evaluation of universal perturbations under different levels of universality, demonstrating that the feasibility of generating effective perturbations decreases as the universality level increases. Finally, we propose a more detailed and rigorous framework to measure the amount of distortion introduced by the perturbations, demonstrating that the methods employed by convention are not realistic in audio-based problems.

arXiv:1911.10130공식 코드 · Papers with Code

A Data Set of Internet Claims and Comparison of their Sentiments with Credibility

In this modern era, communication has become faster and easier. This means fallacious information can spread as fast as reality. Considering the damage that fake news kindles on the psychology of people and the fact that such news proliferates faster than truth, we need to study the phenomenon that helps spread fake news. An unbiased data set that depends on reality for rating news is necessary to construct predictive models for its classification. This paper describes the methodology to create such a data set. We collect our data from snopes.com which is a fact-checking organization. Furthermore, we intend to create this data set not only for classification of the news but also to find patterns that reason the intent behind misinformation. We also formally define an Internet Claim, its credibility, and the sentiment behind such a claim. We try to realize the relationship between the sentiment of a claim with its credibility. This relationship pours light on the bigger picture behind the propagation of misinformation. We pave the way for further research based on the methodology described in this paper to create the data set and usage of predictive modeling along with research-based on psychology/mentality of people to understand why fake news spreads much faster than reality.

arXiv:1911.10129

Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis

Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a discrepancy between 3D imaging data, which is represented in Euclidean space, and the non-Euclidean geometry of the highly-convoluted brain surface. Recent advances in machine learning have enabled the use of neural networks for non-Euclidean spaces. These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph. This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information. The proposed method innovates by learning an intrinsic aggregation of graph nodes based on graph spectral embedding. We illustrate the advantages of our approach with in-depth experiments on two large-scale benchmark datasets. The flexibility of the pooling strategy is evaluated on four different prediction tasks, namely, subject-sex classification, regression of cortical region sizes, classification of Alzheimer's disease stages, and brain age regression. Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolution networks, with results improving the state-of-the-art in brain surface analysis.

arXiv:1911.10059

Deriving star cluster parameters with convolutional neural networks. II. Extinction and cluster/background classification

Context. Convolutional neural networks (CNNs) have been established as the go-to method for fast object detection and classification on natural images. This opens the door for astrophysical parameter inference on the exponentially increasing amount of sky survey data. Until now, star cluster analysis was based on integral or resolved stellar photometry, which limits the amount of information that can be extracted from individual pixels of cluster images. Aims. We aim to create a CNN capable of inferring star cluster evolutionary, structural, and environmental parameters from multi-band images, as well to demonstrate its capabilities in discriminating genuine clusters from galactic stellar backgrounds. Methods. A CNN based on the deep residual network (ResNet) architecture was created and trained to infer cluster ages, masses, sizes, and extinctions, with respect to the degeneracies between them. Mock clusters placed on M83 Hubble Space Telescope (HST) images utilizing three photometric passbands (F336W, F438W, and F814W) were used. The CNN is also capable of predicting the likelihood of a cluster's presence in an image, as well as quantifying its visibility (signal-to-noise). Results. The CNN was tested on mock images of artificial clusters and has demonstrated reliable inference results for clusters of ages $\lesssim$100 Myr, extinctions $A_V$ between 0 and 3 mag, masses between $3\times10^3$ and $3\times10^5$ ${\rm M_\odot}$, and sizes between 0.04 and 0.4 arcsec at the distance of the M83 galaxy. Real M83 galaxy cluster parameter inference tests were performed with objects taken from previous studies and have demonstrated consistent results.

arXiv:1911.10022

Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study

Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [$\pm$0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [$\pm$0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.

arXiv:1911.10003공식 코드 · Papers with Code

Locality Constraint Dictionary Learning with Support Vector for Pattern Classification

Discriminative dictionary learning (DDL) has recently gained significant attention due to its impressive performance in various pattern classification tasks. However, the locality of atoms is not fully explored in conventional DDL approaches which hampers their classification performance. In this paper, we propose a locality constraint dictionary learning with support vector discriminative term (LCDL-SV), in which the locality information is preserved by employing the graph Laplacian matrix of the learned dictionary. To jointly learn a classifier during the training phase, a support vector discriminative term is incorporated into the proposed objective function. Moreover, in the classification stage, the identity of test data is jointly determined by the regularized residual and the learned multi-class support vector machine. Finally, the resulting optimization problem is solved by utilizing the alternative strategy. Experimental results on benchmark databases demonstrate the superiority of our proposed method over previous dictionary learning approaches on both hand-crafted and deep features. The source code of our proposed LCDL-SV is accessible at https://github.com/yinhefeng/LCDL-SV

arXiv:1911.09996공식 코드 · Papers with Code

Orderless Recurrent Models for Multi-label Classification

Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE.

arXiv:1911.09977

Artificial neural networks in action for an automated cell-type classification of biological neural networks

Identification of different neuronal cell types is critical for understanding their contribution to brain functions. Yet, automated and reliable classification of neurons remains a challenge, primarily because of their biological complexity. Typical approaches include laborious and expensive immunohistochemical analysis while feature extraction algorithms based on cellular characteristics have recently been proposed. The former rely on molecular markers, which are often expressed in many cell types, while the latter suffer from similar issues: finding features that are distinctive for each class has proven to be equally challenging. Moreover, both approaches are time consuming and demand a lot of human intervention. In this work we establish the first, automated cell-type classification method that relies on neuronal activity rather than molecular or cellular features. We test our method on a real-world dataset comprising of raw calcium activity signals for four neuronal types. We compare the performance of three different deep learning models and demonstrate that our method can achieve automated classification of neuronal cell types with unprecedented accuracy.

arXiv:1911.09953공식 코드 · Papers with Code

Class-specific residual constraint non-negative representation for pattern classification

Representation based classification method (RBCM) remains one of the hottest topics in the community of pattern recognition, and the recently proposed non-negative representation based classification (NRC) achieved impressive recognition results in various classification tasks. However, NRC ignores the relationship between the coding and classification stages. Moreover, there is no regularization term other than the reconstruction error term in the formulation of NRC, which may result in unstable solution leading to misclassification. To overcome these drawbacks of NRC, in this paper, we propose a class-specific residual constraint non-negative representation (CRNR) for pattern classification. CRNR introduces a class-specific residual constraint into the formulation of NRC, which encourages training samples from different classes to competitively represent the test sample. Based on the proposed CRNR, we develop a CRNR based classifier (CRNRC) for pattern classification. Experimental results on several benchmark datasets demonstrate the superiority of CRNRC over conventional RBCM as well as the recently proposed NRC. Moreover, CRNRC works better or comparable to some state-of-the-art deep approaches on diverse challenging pattern classification tasks. The source code of our proposed CRNRC is accessible at https://github.com/yinhefeng/CRNRC.

arXiv:1911.09883

Classifying Vietnamese Disease Outbreak Reports with Important Sentences and Rich Features

Text classification is an important field of research from mid 90s up to now. It has many applications, one of them is in Web-based biosurveillance systems which identify and summarize online disease outbreak reports. In this paper we focus on classifying Vietnamese disease outbreak reports. We investigate important properties of disease outbreak reports, e.g., sentences containing names of outbreak disease, locations. Evaluation on 10-time 10- fold cross-validation using the Support Vector Machine algorithm shows that using sentences containing disease outbreak names with its preceding/following sentences in combination with location features achieve the best F-score with 86.67% - an improvement of 0.38% in comparison to using all raw text. Our results suggest that using important sentences and rich feature can improve performance of Vietnamese disease outbreak text classification.

arXiv:1911.09389

Classification-driven Single Image Dehazing

Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e.g. image classification. In this paper, we investigate a new point of view in addressing this problem. Instead of focusing only on achieving good quantitative performance on pixel-based metrics such as Peak Signal to Noise Ratio (PSNR), we also ensure that the dehazed image itself does not degrade the performance of the high-level vision tasks such as image classification. To this end, we present an unified CNN architecture that includes three parts: a dehazing sub-network (DNet), a classification-driven Conditional Generative Adversarial Networks sub-network (CCGAN) and a classification sub-network (CNet) related to image classification, which has better performance both on visual appeal and image classification. We conduct comprehensive experiments on two challenging benchmark datasets for fine-grained and object classification: CUB-200-2011 and Caltech-256. Experimental results demonstrate that the proposed method outperforms many recent state-of-the-art single image dehazing methods in terms of image dehazing metrics and classification accuracy.

arXiv:1911.09375

ChartNet: Visual Reasoning over Statistical Charts using MAC-Networks

Despite the improvements in perception accuracies brought about via deep learning, developing systems combining accurate visual perception with the ability to reason over the visual percepts remains extremely challenging. A particular application area of interest from an accessibility perspective is that of reasoning over statistical charts such as bar and pie charts. To this end, we formulate the problem of reasoning over statistical charts as a classification task using MAC-Networks to give answers from a predefined vocabulary of generic answers. Additionally, we enhance the capabilities of MAC-Networks to give chart-specific answers to open-ended questions by replacing the classification layer by a regression layer to localize the textual answers present over the images. We call our network ChartNet, and demonstrate its efficacy on predicting both in vocabulary and out of vocabulary answers. To test our methods, we generated our own dataset of statistical chart images and corresponding question answer pairs. Results show that ChartNet consistently outperform other state-of-the-art methods on reasoning over these questions and may be a viable candidate for applications containing images of statistical charts.

arXiv:1911.09359

Multi-Scale RCNN Model for Financial Time-series Classification

Financial time-series classification (FTC) is extremely valuable for investment management. In past decades, it draws a lot of attention from a wide extent of research areas, especially Artificial Intelligence (AI). Existing researches majorly focused on exploring the effects of the Multi-Scale (MS) property or the Temporal Dependency (TD) within financial time-series. Unfortunately, most previous researches fail to combine these two properties effectively and often fall short of accuracy and profitability. To effectively combine and utilize both properties of financial time-series, we propose a Multi-Scale Temporal Dependent Recurrent Convolutional Neural Network (MSTD-RCNN) for FTC. In the proposed method, the MS features are simultaneously extracted by convolutional units to precisely describe the state of the financial market. Moreover, the TD and complementary across different scales are captured through a Recurrent Neural Network. The proposed method is evaluated on three financial time-series datasets which source from the Chinese stock market. Extensive experimental results indicate that our model achieves the state-of-the-art performance in trend classification and simulated trading, compared with classical and advanced baseline models.

arXiv:1911.09349

An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even overlapping. This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy. Compared to human-designed features which have been widely used in existing research, raw waveforms contain more complete information and are more appropriate for multi-label classification. Taking raw waveforms as input, our network consists of two variants of ResNet structure which can learn a discriminative representation. To explore the information in intermediate layers, a multi-level prediction with attention structure is applied in our model. Furthermore, we design a mix-training strategy to break the performance limitation caused by the amount of training data. Experiments show that the mean average precision of the proposed audio classification system on Audio Set dataset is 37.2%. Without using extra training data, our system exceeds the state-of-the-art multi-level attention model.

arXiv:1911.09319

An Empirical Study of Sections in Classifying Disease Outbreak Reports

Identifying articles that relate to infectious diseases is a necessary step for any automatic bio-surveillance system that monitors news articles from the Internet. Unlike scientific articles which are available in a strongly structured form, news articles are usually loosely structured. In this chapter, we investigate the importance of each section and the effect of section weighting on performance of text classification. The experimental results show that (1) classification models using the headline and leading sentence achieve a high performance in terms of F-score compared to other parts of the article; (2) all section with bag-of-word representation (full text) achieves the highest recall; and (3) section weighting information can help to improve accuracy.

arXiv:1911.09304공식 코드 · Papers with Code

Automatic Text-based Personality Recognition on Monologues and Multiparty Dialogues Using Attentive Networks and Contextual Embeddings

Previous works related to automatic personality recognition focus on using traditional classification models with linguistic features. However, attentive neural networks with contextual embeddings, which have achieved huge success in text classification, are rarely explored for this task. In this project, we have two major contributions. First, we create the first dialogue-based personality dataset, FriendsPersona, by annotating 5 personality traits of speakers from Friends TV Show through crowdsourcing. Second, we present a novel approach to automatic personality recognition using pre-trained contextual embeddings (BERT and RoBERTa) and attentive neural networks. Our models largely improve the state-of-art results on the monologue Essays dataset by 2.49%, and establish a solid benchmark on our FriendsPersona. By comparing results in two datasets, we demonstrate the challenges of modeling personality in multi-party dialogue.

arXiv:1911.09243

Multi-Label Classification with Label Graph Superimposing

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects. Firstly, we model the label correlations by superimposing label graph built from statistical co-occurrence information into the graph constructed from knowledge priors of labels, and then multi-layer graph convolutions are applied on the final superimposed graph for label embedding abstraction. Secondly, we propose to leverage embedding of the whole label system for better representation learning. In detail, lateral connections between GCN and CNN are added at shallow, middle and deep layers to inject information of label system into backbone CNN for label-awareness in the feature learning process. Extensive experiments are carried out on MS-COCO and Charades datasets, showing that our proposed solution can greatly improve the recognition performance and achieves new state-of-the-art recognition performance.

arXiv:1911.09188

Localized Compression: Applying Convolutional Neural Networks to Compressed Images

We address the challenge of applying existing convolutional neural network (CNN) architectures to compressed images. Existing CNN architectures represent images as a matrix of pixel intensities with a specified dimension; this desired dimension is achieved by downgrading or cropping. Downgrading and cropping are attractive in that the result is also an image; however, an algorithm producing an alternative "compressed" representation could yield better classification performance. This compression algorithm need not be reversible, but must be compatible with the CNN's operations. This problem is thus the counterpart of the well-studied problem of applying compressed CNNs to uncompressed images, which has attracted great interest as CNNs are deployed to size-, weight-, and power- (SWaP)-limited devices. We introduce Localized Compression, a generalization of downgrading in which the original image is divided into blocks and each block is compressed to a smaller size using either sampling- or random-matrix-based techniques. By aligning the size of the compressed blocks with the size of the CNN's convolutional region, localized compression can be made compatible with any CNN architecture. Our experimental results show that Localized Compression results in classification accuracy approximately 1-2% higher than is achieved by downgrading to the equivalent resolution.

arXiv:1911.09669공식 코드 · Papers with Code

Regularizing Neural Networks by Stochastically Training Layer Ensembles

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic regularization while explicitly averaging outputs. This provides stronger regularization with no additional computational cost at test time. We show consistent improvement on various image classification tasks using standard network topologies.