PyTorchKR Papers

최신 논문

총 12,307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1909.09839

Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint

Class activation map (CAM) highlights regions of classes based on classification network, which is widely used in weakly supervised tasks. However, it faces the problem that the class activation regions are usually small and local. Although several efforts paid to the second step (the CAM generation step) have partially enhanced the generation, we believe such problem is also caused by the first step (training step), because single classification model trained on the entire classes contains finite discriminate information that limits the object region extraction. To this end, this paper solves CAM generation by using multiple classification models. To form multiple classification networks that carry different discriminative information, we try to capture the semantic relationships between classes to form different semantic levels of classification models. Specifically, hierarchical clustering based on class relationships is used to form hierarchical clustering results, where the clustering levels are treated as semantic levels to form the classification models. Moreover, a new orthogonal module and a two-branch based CAM generation method are proposed to generate class regions that are orthogonal and complementary. We use the PASCAL VOC 2012 dataset to verify the proposed method. Experimental results show that our approach improves the CAM generation.

arXiv:1909.09602

Metric-Based Few-Shot Learning for Video Action Recognition

In the few-shot scenario, a learner must effectively generalize to unseen classes given a small support set of labeled examples. While a relatively large amount of research has gone into few-shot learning for image classification, little work has been done on few-shot video classification. In this work, we address the task of few-shot video action recognition with a set of two-stream models. We evaluate the performance of a set of convolutional and recurrent neural network video encoder architectures used in conjunction with three popular metric-based few-shot algorithms. We train and evaluate using a few-shot split of the Kinetics 600 dataset. Our experiments confirm the importance of the two-stream setup, and find prototypical networks and pooled long short-term memory network embeddings to give the best performance as few-shot method and video encoder, respectively. For a 5-shot 5-way task, this setup obtains 84.2% accuracy on the test set and 59.4% on a special "challenge" test set, composed of highly confusable classes.

arXiv:1909.09484

Generative Dialog Policy for Task-oriented Dialog Systems

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role in task-oriented dialogue systems. As far as we know, the existing task-oriented dialogue systems obtain the dialogue policy through classification, which can assign either a dialogue act and its corresponding parameters or multiple dialogue acts without their corresponding parameters for a dialogue action. In fact, a good dialogue policy should construct multiple dialogue acts and their corresponding parameters at the same time. However, it's hard for existing classification-based methods to achieve this goal. Thus, to address the issue above, we propose a novel generative dialogue policy learning method. Specifically, the proposed method uses attention mechanism to find relevant segments of given dialogue context and input utterance and then constructs the dialogue policy by a seq2seq way for task-oriented dialogue systems. Extensive experiments on two benchmark datasets show that the proposed model significantly outperforms the state-of-the-art baselines. In addition, we have publicly released our codes.

arXiv:1909.09149공식 코드 · Papers with Code

Timage -- A Robust Time Series Classification Pipeline

Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.

arXiv:1909.09147

Differentially Private Regression and Classification with Sparse Gaussian Processes

A continuing challenge for machine learning is providing methods to perform computation on data while ensuring the data remains private. In this paper we build on the provable privacy guarantees of differential privacy which has been combined with Gaussian processes through the previously published \emph{cloaking method}. In this paper we solve several shortcomings of this method, starting with the problem of predictions in regions with low data density. We experiment with the use of inducing points to provide a sparse approximation and show that these can provide robust differential privacy in outlier areas and at higher dimensions. We then look at classification, and modify the Laplace approximation approach to provide differentially private predictions. We then combine this with the sparse approximation and demonstrate the capability to perform classification in high dimensions. We finally explore the issue of hyperparameter selection and develop a method for their private selection. This paper and associated libraries provide a robust toolkit for combining differential privacy and GPs in a practical manner.

논문 ID: 2019.29334

Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network

Arrhythmia is a disease that threatens human life. Therefore, timely diagnosis of arrhythmia is of great significance in preventing heart disease and sudden cardiac death. The BiLSTM-Attention neural network model with heartbeat activity's global sequence features can effectively improve the accuracy of heartbeat classification. Firstly, the noise is removed by the continuous wavelet transform method. Secondly, the peak of the R wave is detected by the tagged database, and then the P-QRS-T wave morphology and the RR interval are extracted. This feature set is heartbeat activity's global sequence features, which combines single heartbeat morphology and 21 consecutive RR intervals. Finally, the Bi-LSTM algorithm and the BiLSTM-Attention algorithm are used to identify heartbeat category respectively, and the MIT-BIH arrhythmia database is used to verify the algorithm. The results show that the BiLSTM-Attention model combined with heartbeat activity's global sequence features has higher interpretability than other methods discussed in this paper.

논문 ID: 2019.29187

A Novel Deep Arrhythmia-Diagnosis Network for Atrial Fibrillation Classification Using Electrocardiogram Signals

Atrial fibrillation (AF), a common abnormal heartbeat rhythm, is a life-threatening recurrent disease that affects older adults. Automatic classification is one of the most valuable topics in medical sciences and bioinformatics, especially the detection of atrial fibrillation. However, it is difficult to accurately explain the local characteristics of electrocardiogram (ECG) signals by manual analysis, due to their small amplitude and short duration, coupled with the complexity and non-linearity. Hence, in this paper, we propose a novel deep arrhythmia-diagnosis method, named deep CNN-BLSTM network model, to automatically detect the AF heartbeats using the ECG signals. The model mainly consists of four convolution layers: two BLSTM layers and two fully connected layers. The datasets of RR intervals (called set A) and heartbeat sequences (P-QRS-T waves, called set B) are fed into the above-mentioned model. Most importantly, our proposed approach achieved favorable performances with an accuracy of 99.94% and 98.63% in the training and validation set of set A, respectively. In the testing set (unseen data sets), we obtained an accuracy of 96.59%, a sensitivity of 99.93%, and a specificity of 97.03%. To the best of our knowledge, the algorithm we proposed has shown excellent results compared to many state-of-art researches, which provides a new solution for the AF automatic detection.

논문 ID: 2019.00103

A Fast Machine Learning Model for ECG-Based Heartbeat Classification and Arrhythmia Detection

We present a fully automatic and fast ECG arrhythmia classifier based on a simple brain-inspired machine learning approach known as Echo State Networks. Our classifier has a low-demanding feature processing that only requires a single ECG lead. Its training and validation follows an inter-patient procedure. Our approach is compatible with an online classification that aligns well with recent advances in health-monitoring wireless devices and wearables. The use of a combination of ensembles allows us to exploit parallelism to train the classifier with remarkable speeds. The heartbeat classifier is evaluated over two ECG databases, the MIT-BIH AR and the AHA. In the MIT-BIH AR database, our classification approach provides a sensitivity of 92.7% and positive predictive value of 86.1% for the ventricular ectopic beats, using the single lead II, and a sensitivity of 95.7% and positive predictive value of 75.1% when using the lead V1'. These results are comparable with the state of the art in fully automatic ECG classifiers and even outperform other ECG classifiers that follow more complex feature-selection approaches.

논문 ID: 2014.71008

A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal

In this paper we used two new features i.e. T-wave integral and total integral as extracted feature from one cycle of normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our previous work we used some features of body surface potential map data for this aim. But we know the standard ECG is more popular, so we focused our detection and localization of MI on standard ECG. We use the T-wave integral because this feature is important impression of T-wave in MI. The second feature in this research is total integral of one ECG cycle, because we believe that the MI affects the morphology of the ECG signal which leads to total integral changes. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI, because this method has very good accuracy for classification of normal signal and abnormal signal. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 76% for accuracy in test data for localization and over 94% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve the accuracy of classification by adding more features in this method. A simple method based on using only two features which were extracted from standard ECG is presented and has good accuracy in MI localization.

arXiv:1909.09566

Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video

Objective monitoring and assessment of human motor behavior can improve the diagnosis and management of several medical conditions. Over the past decade, significant advances have been made in the use of wearable technology for continuously monitoring human motor behavior in free-living conditions. However, wearable technology remains ill-suited for applications which require monitoring and interpretation of complex motor behaviors (e.g. involving interactions with the environment). Recent advances in computer vision and deep learning have opened up new possibilities for extracting information from video recordings. In this paper, we present a hierarchical vision-based behavior phenotyping method for classification of basic human actions in video recordings performed using a single RGB camera. Our method addresses challenges associated with tracking multiple human actors and classification of actions in videos recorded in changing environments with different fields of view. We implement a cascaded pose tracker that uses temporal relationships between detections for short-term tracking and appearance-based tracklet fusion for long-term tracking. Furthermore, for action classification, we use pose evolution maps derived from the cascaded pose tracker as low-dimensional and interpretable representations of the movement sequences for training a convolutional neural network. The cascaded pose tracker achieves an average accuracy of 88\% in tracking the target human actor in our video recordings, and overall system achieves average test accuracy of 84\% for target-specific action classification in untrimmed video recordings.

arXiv:1909.09552공식 코드 · Papers with Code

Defending Against Physically Realizable Attacks on Image Classification

We study the problem of defending deep neural network approaches for image classification from physically realizable attacks. First, we demonstrate that the two most scalable and effective methods for learning robust models, adversarial training with PGD attacks and randomized smoothing, exhibit very limited effectiveness against three of the highest profile physical attacks. Next, we propose a new abstract adversarial model, rectangular occlusion attacks, in which an adversary places a small adversarially crafted rectangle in an image, and develop two approaches for efficiently computing the resulting adversarial examples. Finally, we demonstrate that adversarial training using our new attack yields image classification models that exhibit high robustness against the physically realizable attacks we study, offering the first effective generic defense against such attacks.

arXiv:1909.09481공식 코드 · Papers with Code

Adversarial Learning with Margin-based Triplet Embedding Regularization

The Deep neural networks (DNNs) have achieved great success on a variety of computer vision tasks, however, they are highly vulnerable to adversarial attacks. To address this problem, we propose to improve the local smoothness of the representation space, by integrating a margin-based triplet embedding regularization term into the classification objective, so that the obtained model learns to resist adversarial examples. The regularization term consists of two steps optimizations which find potential perturbations and punish them by a large margin in an iterative way. Experimental results on MNIST, CASIA-WebFace, VGGFace2 and MS-Celeb-1M reveal that our approach increases the robustness of the network against both feature and label adversarial attacks in simple object classification and deep face recognition.

arXiv:1909.09389공식 코드 · Papers with Code

Sampling Bias in Deep Active Classification: An Empirical Study

The exploding cost and time needed for data labeling and model training are bottlenecks for training DNN models on large datasets. Identifying smaller representative data samples with strategies like active learning can help mitigate such bottlenecks. Previous works on active learning in NLP identify the problem of sampling bias in the samples acquired by uncertainty-based querying and develop costly approaches to address it. Using a large empirical study, we demonstrate that active set selection using the posterior entropy of deep models like FastText.zip (FTZ) is robust to sampling biases and to various algorithmic choices (query size and strategies) unlike that suggested by traditional literature. We also show that FTZ based query strategy produces sample sets similar to those from more sophisticated approaches (e.g ensemble networks). Finally, we show the effectiveness of the selected samples by creating tiny high-quality datasets, and utilizing them for fast and cheap training of large models. Based on the above, we propose a simple baseline for deep active text classification that outperforms the state-of-the-art. We expect the presented work to be useful and informative for dataset compression and for problems involving active, semi-supervised or online learning scenarios. Code and models are available at: https://github.com/drimpossible/Sampling-Bias-Active-Learning

arXiv:1909.09031

Argumentative Relation Classification as Plausibility Ranking

We formulate argumentative relation classification (support vs. attack) as a text-plausibility ranking task. To this aim, we propose a simple reconstruction trick which enables us to build minimal pairs of plausible and implausible texts by simulating natural contexts in which two argumentative units are likely or unlikely to appear. We show that this method is competitive with previous work albeit it is considerably simpler. In a recently introduced content-based version of the task, where contextual discourse clues are hidden, the approach offers a performance increase of more than 10% macro F1. With respect to the scarce attack-class, the method achieves a large increase in precision while the incurred loss in recall is small or even nonexistent.

arXiv:1909.08987

Automated detection of oral pre-cancerous tongue lesions using deep learning for early diagnosis of oral cavity cancer

Discovering oral cavity cancer (OCC) at an early stage is an effective way to increase patient survival rate. However, current initial screening process is done manually and is expensive for the average individual, especially in developing countries worldwide. This problem is further compounded due to the lack of specialists in such areas. Automating the initial screening process using artificial intelligence (AI) to detect pre-cancerous lesions can prove to be an effective and inexpensive technique that would allow patients to be triaged accordingly to receive appropriate clinical management. In this study, we have applied and evaluated the efficacy of six deep convolutional neural network (DCNN) models using transfer learning, for identifying pre-cancerous tongue lesions directly using a small data set of clinically annotated photographic images to diagnose early signs of OCC. DCNN model based on Vgg19 architecture was able to differentiate between benign and pre-cancerous tongue lesions with a mean classification accuracy of 0.98, sensitivity 0.89 and specificity 0.97. Additionally, the ResNet50 DCNN model was able to distinguish between five types of tongue lesions i.e. hairy tongue, fissured tongue, geographic tongue, strawberry tongue and oral hairy leukoplakia with a mean classification accuracy of 0.97. Preliminary results using an (AI+Physician) ensemble model demonstrate that an automated initial screening process of tongue lesions using DCNNs can achieve near-human level classification performance for diagnosing early signs of OCC in patients.

arXiv:1909.08961

Acoustic scene analysis with multi-head attention networks

Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activities could have overlapping sounds patterns (e.g. both cooking and dishwashing could have silverware clinking sound). In this paper, we propose a multi-head attention network to model the complex temporal input structures for ASC. The proposed network takes the audio's time-frequency representation as input, and it leverages standard VGG plus LSTM layers to extract high-level feature representation. Further more, it applies multiple attention heads to summarize various patterns of sound events into fixed dimensional representation, for the purpose of final scene classification. The whole network is trained in an end-to-end fashion with back-propagation. Experimental results confirm that our model discovers meaningful sound patterns through the attention mechanism, without using explicit supervision in the alignment. We evaluated our proposed model using DCASE 2018 Task 5 dataset, and achieved competitive performance on par with previous winner's results.

arXiv:1909.08898

Efficient Prealignment of CT Scans for Registration through a Bodypart Regressor

Convolutional neural networks have not only been applied for classification of voxels, objects, or images, for instance, but have also been proposed as a bodypart regressor. We pick up this underexplored idea and evaluate its value for registration: A CNN is trained to output the relative height within the human body in axial CT scans, and the resulting scores are used for quick alignment between different timepoints. Preliminary results confirm that this allows both fast and robust prealignment compared with iterative approaches.

arXiv:1909.08864

Adversarial Vulnerability Bounds for Gaussian Process Classification

Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devise an adversarial bound (AB) for a Gaussian process classifier, that holds for the entire input domain, bounding the potential for any future adversarial method to cause such misclassification. This is a formal guarantee of robustness, not just an empirically derived result. We investigate how to configure the classifier to maximise the bound, including the use of a sparse approximation, leading to the method producing a practical, useful and provably robust classifier, which we test using a variety of datasets.

arXiv:1909.08856

Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification

Attribution methods are an easy to use tool for investigating and validating machine learning models. Multiple methods have been suggested in the literature and it is not yet clear which method is most suitable for a given task. In this study, we tested the robustness of four attribution methods, namely gradient*input, guided backpropagation, layer-wise relevance propagation and occlusion, for the task of Alzheimer's disease classification. We have repeatedly trained a convolutional neural network (CNN) with identical training settings in order to separate structural MRI data of patients with Alzheimer's disease and healthy controls. Afterwards, we produced attribution maps for each subject in the test data and quantitatively compared them across models and attribution methods. We show that visual comparison is not sufficient and that some widely used attribution methods produce highly inconsistent outcomes.

arXiv:1909.08756

Bibliothèque de la communauté assomptionniste : saisie informatique et classement Dewey

The Library of Saint Peter in Gallicantu has had an eventful history and different phases of classification. It was constituted by the contribution of various private libraries of Religious of the Holy Land. Its history is intimately linked to the Assumptionist presence in Jerusalem. The computerization work carried out from 2018 onwards made it possible to clarify the classification framework based on Dewey's decimal classification and to use the databases - Wikidata, VIAF - to improve the BNF catalogue.