PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.07821

Gait-based Frailty Assessment using Image Representation of IMU Signals and Deep CNN

Frailty is a common and critical condition in elderly adults, which may lead to further deterioration of health. However, difficulties and complexities exist in traditional frailty assessments based on activity-related questionnaires. These can be overcome by monitoring the effects of frailty on the gait. In this paper, it is shown that by encoding gait signals as images, deep learning-based models can be utilized for the classification of gait type. Two deep learning models (a) SS-CNN, based on single stride input images, and (b) MS-CNN, based on 3 consecutive strides were proposed. It was shown that MS-CNN performs best with an accuracy of 85.1\%, while SS-CNN achieved an accuracy of 77.3\%. This is because MS-CNN can observe more features corresponding to stride-to-stride variations which is one of the key symptoms of frailty. Gait signals were encoded as images using STFT, CWT, and GAF. While the MS-CNN model using GAF images achieved the best overall accuracy and precision, CWT has a slightly better recall. This study demonstrates how image encoded gait data can be used to exploit the full potential of deep learning CNN models for the assessment of frailty.

arXiv:2110.07035

Bond Default Prediction with Text Embeddings, Undersampling and Deep Learning

The special and important problems of default prediction for municipal bonds are addressed using a combination of text embeddings from a pre-trained transformer network, a fully connected neural network, and synthetic oversampling. The combination of these techniques provides significant improvement in performance over human estimates, linear models, and boosted ensemble models, on data with extreme imbalance. Less than 0.2% of municipal bonds default, but our technique predicts 9 out of 10 defaults at the time of issue, without using bond ratings, at a cost of false positives on less than 0.1% non-defaulting bonds. The results hold the promise of reducing the cost of capital for local public goods, which are vital for society, and bring techniques previously used in personal credit and public equities (or national fixed income), as well as the current generation of embedding techniques, to sub-sovereign credit decisions.

arXiv:2110.07360

Domain generalization in deep learning for contrast-enhanced imaging

The domain generalization problem has been widely investigated in deep learning for non-contrast imaging over the last years, but it received limited attention for contrast-enhanced imaging. However, there are marked differences in contrast imaging protocols across clinical centers, in particular in the time between contrast injection and image acquisition, while access to multi-center contrast-enhanced image data is limited compared to available datasets for non-contrast imaging. This calls for new tools for generalizing single-domain, single-center deep learning models across new unseen domains and clinical centers in contrast-enhanced imaging. In this paper, we present an exhaustive evaluation of deep learning techniques to achieve generalizability to unseen clinical centers for contrast-enhanced image segmentation. To this end, several techniques are investigated, optimized and systematically evaluated, including data augmentation, domain mixing, transfer learning and domain adaptation. To demonstrate the potential of domain generalization for contrast-enhanced imaging, the methods are evaluated for ventricular segmentation in contrast-enhanced cardiac magnetic resonance imaging (MRI). The results are obtained based on a multi-center cardiac contrast-enhanced MRI dataset acquired in four hospitals located in three countries (France, Spain and China). They show that the combination of data augmentation and transfer learning can lead to single-center models that generalize well to new clinical centers not included during training. Single-domain neural networks enriched with suitable generalization procedures can reach and even surpass the performance of multi-center, multi-vendor models in contrast-enhanced imaging, hence eliminating the need for comprehensive multi-center datasets to train generalizable models.

arXiv:2110.07191

CNN-DST: ensemble deep learning based on Dempster-Shafer theory for vibration-based fault recognition

Nowadays, using vibration data in conjunction with pattern recognition methods is one of the most common fault detection strategies for structures. However, their performances depend on the features extracted from vibration data, the features selected to train the classifier, and the classifier used for pattern recognition. Deep learning facilitates the fault detection procedure by automating the feature extraction and selection, and classification procedure. Though, deep learning approaches have challenges in designing its structure and tuning its hyperparameters, which may result in a low generalization capability. Therefore, this study proposes an ensemble deep learning framework based on a convolutional neural network (CNN) and Dempster-Shafer theory (DST), called CNN-DST. In this framework, several CNNs with the proposed structure are first trained, and then, the outputs of the CNNs selected by the proposed technique are combined by using an improved DST-based method. To validate the proposed CNN-DST framework, it is applied to an experimental dataset created by the broadband vibrational responses of polycrystalline Nickel alloy first-stage turbine blades with different types and severities of damage. Through statistical analysis, it is shown that the proposed CNN-DST framework classifies the turbine blades with an average prediction accuracy of 97.19%. The proposed CNN-DST framework is benchmarked with other state-of-the-art classification methods, demonstrating its high performance. The robustness of the proposed CNN-DST framework with respect to measurement noise is investigated, showing its high noise-resistance. Further, bandwidth analysis reveals that most of the required information for detecting faulty samples is available in a small frequency range.

arXiv:2110.07152

DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models

Statistical shape modeling (SSM) characterizes anatomical variations in a population of shapes generated from medical images. SSM requires consistent shape representation across samples in shape cohort. Establishing this representation entails a processing pipeline that includes anatomy segmentation, re-sampling, registration, and non-linear optimization. These shape representations are then used to extract low-dimensional shape descriptors that facilitate subsequent analyses in different applications. However, the current process of obtaining these shape descriptors from imaging data relies on human and computational resources, requiring domain expertise for segmenting anatomies of interest. Moreover, this same taxing pipeline needs to be repeated to infer shape descriptors for new image data using a pre-trained/existing shape model. Here, we propose DeepSSM, a deep learning-based framework for learning the functional mapping from images to low-dimensional shape descriptors and their associated shape representations, thereby inferring statistical representation of anatomy directly from 3D images. Once trained using an existing shape model, DeepSSM circumvents the heavy and manual pre-processing and segmentation and significantly improves the computational time, making it a viable solution for fully end-to-end SSM applications. In addition, we introduce a model-based data-augmentation strategy to address data scarcity. Finally, this paper presents and analyzes two different architectural variants of DeepSSM with different loss functions using three medical datasets and their downstream clinical application. Experiments showcase that DeepSSM performs comparably or better to the state-of-the-art SSM both quantitatively and on application-driven downstream tasks. Therefore, DeepSSM aims to provide a comprehensive blueprint for deep learning-based image-to-shape models.

arXiv:2110.07103공식 코드 · Papers with Code

Video-based cattle identification and action recognition

We demonstrate a working prototype for the monitoring of cow welfare by automatically analysing the animal behaviours. Deep learning models have been developed and tested with videos acquired in a farm, and a precision of 81.2\% has been achieved for cow identification. An accuracy of 84.4\% has been achieved for the detection of drinking events, and 94.4\% for the detection of grazing events. Experimental results show that the proposed deep learning method can be used to identify the behaviours of individual animals to enable automated farm provenance. Our raw and ground-truth dataset will be released as the first public video dataset for cow identification and action recognition. Recommendations for further development are also provided.

arXiv:2110.07531공식 코드 · Papers with Code

Deep learning models for predicting RNA degradation via dual crowdsourcing

Messenger RNA-based medicines hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydrolysis. Predicting the degradation of an RNA molecule is a key task in designing more stable RNA-based therapeutics. Here, we describe a crowdsourced machine learning competition ("Stanford OpenVaccine") on Kaggle, involving single-nucleotide resolution measurements on 6043 102-130-nucleotide diverse RNA constructs that were themselves solicited through crowdsourcing on the RNA design platform Eterna. The entire experiment was completed in less than 6 months, and 41% of nucleotide-level predictions from the winning model were within experimental error of the ground truth measurement. Furthermore, these models generalized to blindly predicting orthogonal degradation data on much longer mRNA molecules (504-1588 nucleotides) with improved accuracy compared to previously published models. Top teams integrated natural language processing architectures and data augmentation techniques with predictions from previous dynamic programming models for RNA secondary structure. These results indicate that such models are capable of representing in-line hydrolysis with excellent accuracy, supporting their use for designing stabilized messenger RNAs. The integration of two crowdsourcing platforms, one for data set creation and another for machine learning, may be fruitful for other urgent problems that demand scientific discovery on rapid timescales.

arXiv:2110.07253

Rethinking Point Cloud Filtering: A Non-Local Position Based Approach

Existing position based point cloud filtering methods can hardly preserve sharp geometric features. In this paper, we rethink point cloud filtering from a non-learning non-local non-normal perspective, and propose a novel position based approach for feature-preserving point cloud filtering. Unlike normal based techniques, our method does not require the normal information. The core idea is to first design a similarity metric to search the non-local similar patches of a queried local patch. We then map the non-local similar patches into a canonical space and aggregate the non-local information. The aggregated outcome (i.e. coordinate) will be inversely mapped into the original space. Our method is simple yet effective. Extensive experiments validate our method, and show that it generally outperforms position based methods (deep learning and non-learning), and generates better or comparable outcomes to normal based techniques (deep learning and non-learning).

arXiv:2110.07121

Secure Precoding in MIMO-NOMA: A Deep Learning Approach

A novel signaling design for secure transmission over two-user multiple-input multiple-output non-orthogonal multiple access channel using deep neural networks (DNNs) is proposed. The goal of the DNN is to form the covariance matrix of users' signals such that the message of each user is transmitted reliably while being confidential from its counterpart. The proposed DNN linearly precodes each user's signal before superimposing them and achieves near-optimal performance with significantly lower run time. Simulation results show that the proposed models reach about 98% of the secrecy capacity rates. The spectral efficiency of the DNN precoder is much higher than that of existing analytical linear precoders--e.g., generalized singular value decomposition--and its on-the-fly complexity is several times less than the existing iterative methods.

arXiv:2110.07007

Out-of-Distribution Robustness in Deep Learning Compression

In recent years, deep neural network (DNN) compression systems have proved to be highly effective for designing source codes for many natural sources. However, like many other machine learning systems, these compressors suffer from vulnerabilities to distribution shifts as well as out-of-distribution (OOD) data, which reduces their real-world applications. In this paper, we initiate the study of OOD robust compression. Considering robustness to two types of ambiguity sets (Wasserstein balls and group shifts), we propose algorithmic and architectural frameworks built on two principled methods: one that trains DNN compressors using distributionally-robust optimization (DRO), and the other which uses a structured latent code. Our results demonstrate that both methods enforce robustness compared to a standard DNN compressor, and that using a structured code can be superior to the DRO compressor. We observe tradeoffs between robustness and distortion and corroborate these findings theoretically for a specific class of sources.

arXiv:2110.06880

A Survey of Online Auction Mechanism Design Using Deep Learning Approaches

Online auction has been very widespread in the recent years. Platform administrators are working hard to refine their auction mechanisms that will generate high profits while maintaining a fair resource allocation. With the advancement of computing technology and the bottleneck in theoretical frameworks, researchers are shifting gears towards online auction designs using deep learning approaches. In this article, we summarized some common deep learning infrastructures adopted in auction mechanism designs and showed how these architectures are evolving. We also discussed how researchers are tackling with the constraints and concerns in the large and dynamic industrial settings. Finally, we pointed out several currently unresolved issues for future directions.

arXiv:2110.06751공식 코드 · Papers with Code

Improving the sample-efficiency of neural architecture search with reinforcement learning

Designing complex architectures has been an essential cogwheel in the revolution deep learning has brought about in the past decade. When solving difficult problems in a datadriven manner, a well-tried approach is to take an architecture discovered by renowned deep learning scientists as a basis (e.g. Inception) and try to apply it to a specific problem. This might be sufficient, but as of now, achieving very high accuracy on a complex or yet unsolved task requires the knowledge of highly-trained deep learning experts. In this work, we would like to contribute to the area of Automated Machine Learning (AutoML), specifically Neural Architecture Search (NAS), which intends to make deep learning methods available for a wider range of society by designing neural topologies automatically. Although several different approaches exist (e.g. gradient-based or evolutionary algorithms), our focus is on one of the most promising research directions, reinforcement learning. In this scenario, a recurrent neural network (controller) is trained to create problem-specific neural network architectures (child). The validation accuracies of the child networks serve as a reward signal for training the controller with reinforcement learning. The basis of our proposed work is Efficient Neural Architecture Search (ENAS), where parameter sharing is applied among the child networks. ENAS, like many other RL-based algorithms, emphasize the learning of child networks as increasing their convergence result in a denser reward signal for the controller, therefore significantly reducing training times. The controller was originally trained with REINFORCE. In our research, we propose to modify this to a more modern and complex algorithm, PPO, which has demonstrated to be faster and more stable in other environments. Then, we briefly discuss and evaluate our results.

arXiv:2110.06663공식 코드 · Papers with Code

Tutorial on Deep Learning for Human Activity Recognition

Activity recognition systems that are capable of estimating human activities from wearable inertial sensors have come a long way in the past decades. Not only have state-of-the-art methods moved away from feature engineering and have fully adopted end-to-end deep learning approaches, best practices for setting up experiments, preparing datasets, and validating activity recognition approaches have similarly evolved. This tutorial was first held at the 2021 ACM International Symposium on Wearable Computers (ISWC'21) and International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'21). The tutorial, after a short introduction in the research field of activity recognition, provides a hands-on and interactive walk-through of the most important steps in the data pipeline for the deep learning of human activities. All presentation slides shown during the tutorial, which also contain links to all code exercises, as well as the link of the GitHub page of the tutorial can be found on: https://mariusbock.github.io/dl-for-har

arXiv:2110.06367

Voice-assisted Image Labelling for Endoscopic Ultrasound Classification using Neural Networks

Ultrasound imaging is a commonly used technology for visualising patient anatomy in real-time during diagnostic and therapeutic procedures. High operator dependency and low reproducibility make ultrasound imaging and interpretation challenging with a steep learning curve. Automatic image classification using deep learning has the potential to overcome some of these challenges by supporting ultrasound training in novices, as well as aiding ultrasound image interpretation in patient with complex pathology for more experienced practitioners. However, the use of deep learning methods requires a large amount of data in order to provide accurate results. Labelling large ultrasound datasets is a challenging task because labels are retrospectively assigned to 2D images without the 3D spatial context available in vivo or that would be inferred while visually tracking structures between frames during the procedure. In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure. We use a CNN composed of two branches, one for voice data and another for image data, which are joined to predict image labels from the spoken names of anatomical landmarks. The network was trained using recorded verbal comments from expert operators. Our results show a prediction accuracy of 76% at image level on a dataset with 5 different labels. We conclude that the addition of spoken commentaries can increase the performance of ultrasound image classification, and eliminate the burden of manually labelling large EUS datasets necessary for deep learning applications.

arXiv:2110.06601

Vibration-Based Condition Monitoring By Ensemble Deep Learning

Vibration-based techniques are among the most common condition monitoring approaches. With the advancement of computers, these approaches have also been improved such that recently, these approaches in conjunction with deep learning methods attract attention among researchers. This is mostly due to the nature of the deep learning method that could facilitate the monitoring procedure by integrating the feature extraction, feature selection, and classification steps into one automated step. However, this can be achieved at the expense of challenges in designing the architecture of a deep learner, tuning its hyper-parameters. Moreover, it sometimes gives low generalization capability. As a remedy to these problems, this study proposes a framework based on ensemble deep learning methodology. The framework was initiated by creating a pool of Convolutional neural networks (CNN). To create diversity to the CNNs, they are fed by frequency responses which are passed through different functions. As the next step, proper CNNs are selected based on an information criterion to be used for fusion. The fusion is then carried out by improved Dempster-Shafer theory. The proposed framework is applied to real test data collected from Equiax Polycrystalline Nickel alloy first-stage turbine blades with complex geometry.

arXiv:2110.06461공식 코드 · Papers with Code

Fake News Detection in Spanish Using Deep Learning Techniques

This paper addresses the problem of fake news detection in Spanish using Machine Learning techniques. It is fundamentally the same problem tackled for the English language; however, there is not a significant amount of publicly available and adequately labeled fake news in Spanish to effectively train a Machine Learning model, similarly to those proposed for the English language. Therefore, this work explores different training strategies and architectures to establish a baseline for further research in this area. Four datasets were used, two in English and two in Spanish, and four experimental schemes were tested, including a baseline with classical Machine Learning models, trained and validated using a small dataset in Spanish. The remaining schemes include state-of-the-art Deep Learning models trained (or fine-tuned) and validated in English, trained and validated in Spanish, and fitted in English and validated with automatic translated Spanish sentences. The Deep Learning architectures were built on top of different pre-trained Word Embedding representations, including GloVe, ELMo, BERT, and BETO (a BERT version trained on a large corpus in Spanish). According to the results, the best strategy was a combination of a pre-trained BETO model and a Recurrent Neural Network based on LSTM layers, yielding an accuracy of up to 80%; nonetheless, a baseline model using a Random Forest estimator obtained similar outcomes. Additionally, the translation strategy did not yield acceptable results because of the propagation error; there was also observed a significant difference in models performance when trained in English or Spanish, mainly attributable to the number of samples available for each language.

논문 ID: document/9014714

Violence Recognition from Videos using Deep Learning Techniques

Automatic recognition of violence between individuals or crowds in videos has a broad interest. In this work, an end-to-end deep neural network model for the purpose of recognizing violence in videos is proposed. The proposed model uses a pre-trained VGG-16 on ImageNet as spatial feature extractor followed by Long Short-Term Memory (LSTM) as temporal feature extractor and sequence of fully connected layers for classification purpose. The achieved accuracy is near state-of-the-art. Also, we contribute by introducing a new benchmark called Real- Life Violence Situations which contains 2000 short videos divided into 1000 violence videos and 1000 non-violence videos. The new benchmark is used for fine-tuning the proposed models achieving a best accuracy of 88.2%.

arXiv:2110.05479

Towards Robust Representation of Limit Orders Books for Deep Learning Models

The success of deep learning-based limit order book forecasting models is highly dependent on the quality and the robustness of the input data representation. A significant body of the quantitative finance literature focuses on utilising different deep learning architectures without taking into consideration the key assumptions these models make with respect to the input data representation. In this paper, we highlight the issues associated with the commonly-used representations of limit order book data from both a theoretical and practical perspectives. We also show the fragility of the representations under adversarial perturbations and propose two simple modifications to the existing representations that match the theoretical assumptions of deep learning models. Finally, we show experimentally how our proposed representations lead to state-of-the-art performance in both accuracy and robustness utilising very simple neural network architectures.

arXiv:2110.05476

Image Compression and Classification Using Qubits and Quantum Deep Learning

Recent work suggests that quantum machine learning techniques can be used for classical image classification by encoding the images in quantum states and using a quantum neural network for inference. However, such work has been restricted to very small input images, at most 4 x 4, that are unrealistic and cannot even be accurately labeled by humans. The primary difficulties in using larger input images is that hitherto-proposed encoding schemes necessitate more qubits than are physically realizable. We propose a framework to classify larger, realistic images using quantum systems. Our approach relies on a novel encoding mechanism that embeds images in quantum states while necessitating fewer qubits than prior work. Our framework is able to classify images that are larger than previously possible, up to 16 x 16 for the MNIST dataset on a personal laptop, and obtains accuracy comparable to classical neural networks with the same number of learnable parameters. We also propose a technique for further reducing the number of qubits needed to represent images that may result in an easier physical implementation at the expense of final performance. Our work enables quantum machine learning and classification on classical datasets of dimensions that were previously intractable by physically realizable quantum computers or classical simulation

arXiv:2110.05960공식 코드 · Papers with Code

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

Understanding the training dynamics of deep learning models is perhaps a necessary step toward demystifying the effectiveness of these models. In particular, how do data from different classes gradually become separable in their feature spaces when training neural networks using stochastic gradient descent? In this study, we model the evolution of features during deep learning training using a set of stochastic differential equations (SDEs) that each corresponds to a training sample. As a crucial ingredient in our modeling strategy, each SDE contains a drift term that reflects the impact of backpropagation at an input on the features of all samples. Our main finding uncovers a sharp phase transition phenomenon regarding the {intra-class impact: if the SDEs are locally elastic in the sense that the impact is more significant on samples from the same class as the input, the features of the training data become linearly separable, meaning vanishing training loss; otherwise, the features are not separable, regardless of how long the training time is. Moreover, in the presence of local elasticity, an analysis of our SDEs shows that the emergence of a simple geometric structure called the neural collapse of the features. Taken together, our results shed light on the decisive role of local elasticity in the training dynamics of neural networks. We corroborate our theoretical analysis with experiments on a synthesized dataset of geometric shapes and CIFAR-10.