PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2111.03274

Pathological Analysis of Blood Cells Using Deep Learning Techniques

Pathology deals with the practice of discovering the reasons for disease by analyzing the body samples. The most used way in this field, is to use histology which is basically studying and viewing microscopic structures of cell and tissues. The slide viewing method is widely being used and converted into digital form to produce high resolution images. This enabled the area of deep learning and machine learning to deep dive into this field of medical sciences. In the present study, a neural based network has been proposed for classification of blood cells images into various categories. When input image is passed through the proposed architecture and all the hyper parameters and dropout ratio values are used in accordance with proposed algorithm, then model classifies the blood images with an accuracy of 95.24%. The performance of proposed model is better than existing standard architectures and work done by various researchers. Thus model will enable development of pathological system which will reduce human errors and daily load on laboratory men. This will in turn help pathologists in carrying out their work more efficiently and effectively.

논문 ID: document/9345705

New Generation Deep Learning For Video Object Dection:A Survery

Video object detection, a basic task in the computer vision field, is rapidly evolving and widely used. In recent years, deep learning methods have rapidly become widespread in the field of video object detection, achieving excellent results compared with those of traditional methods. However, the presence of duplicate information and abundant spatiotemporal information in video data poses a serious challenge to video object detection. Therefore, in recent years, many scholars have investigated deep learning detection algorithms in the context of video data and have achieved remarkable results. Considering the wide range of applications, a comprehensive review of the research related to video object detection is both a necessary and challenging task. This survey attempts to link and systematize the latest cutting-edge research on video object detection with the goal of classifying and analyzing video detection algorithms based on specific representative models. The differences and connections between video object detection and similar tasks are systematically demonstrated, and the evaluation metrics and video detection performance of nearly 40 models on two data sets are presented. Finally, the various applications and challenges facing video object detection are discussed.

arXiv:2111.03126

Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System

We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption. The deep learning model consists of a recurrent neural network, which aims to learn the time marching structure, and a generative adversarial network (GAN) to learn and sample from the probability distribution of the random dynamical system. Although GANs provide a powerful tool to model a complex probability distribution, the training often fails without a proper regularization. Here, we propose a regularization strategy for a GAN based on consistency conditions for the sequential inference problems. First, the maximum mean discrepancy (MMD) is used to enforce the consistency between conditional and marginal distributions of a stochastic process. Then, the marginal distributions of the multiple-step predictions are regularized by using MMD or from multiple discriminators. The behavior of the proposed model is studied by using three stochastic processes with complex noise structures.

arXiv:2111.02667

Physics Assisted Deep Learning for Indoor Imaging using Phaseless Wi-Fi Measurements

A physics assisted deep learning framework to perform accurate indoor imaging using phaseless Wi-Fi measurements is proposed. It is able to image objects that are large (compared to wavelength) and have high permittivity values, that existing radio frequency (RF) inverse scattering techniques find very challenging, making it suitable for indoor RF imaging. The technique utilizes a Rytov based inverse scattering model with a deep learning framework. The inverse scattering model is based on an extended Rytov approximation (xRA) that pre-reconstructs the RF measurements. Under strong scattering conditions, this pre-reconstruction is related to the actual permittivity profile by a non-linear function, which is learned by a modified U-Net model to obtain the permittivity profile of the object. Thus, our proposed approach not only reconstructs the shape of objects, but also estimates their permittivity values accurately. We demonstrate its imaging performance using simulations as well as experimental results in an actual indoor environment using 2.4 GHz Wi-Fi phaseless measurements. For incident wavelength $\lambda_0$, the proposed framework can reconstruct objects with relative permittivity as high as 77 and electrical size as large as $40 \lambda$, where $\lambda =\lambda_0/\sqrt{77}$. This is in contrast to existing phaseless imaging techniques which cannot reconstruct permittivity values beyond 3 or 4. Thus, our proposed method is the first inverse scattering-based deep learning framework which can image large scatterers with high permittivity and achieve accurate indoor RF imaging using phaseless Wi-Fi measurements.

arXiv:2111.02584

Real-time Wireless Transmitter Authorization: Adapting to Dynamic Authorized Sets with Information Retrieval

As the Internet of Things (IoT) continues to grow, ensuring the security of systems that rely on wireless IoT devices has become critically important. Deep learning-based passive physical layer transmitter authorization systems have been introduced recently for this purpose, as they accommodate the limited computational and power budget of such devices. These systems have been shown to offer excellent outlier detection accuracies when trained and tested on a fixed authorized transmitter set. However in a real-life deployment, a need may arise for transmitters to be added and removed as the authorized set of transmitters changes. In such cases, the system could experience long down-times, as retraining the underlying deep learning model is often a time-consuming process. In this paper, we draw inspiration from information retrieval to address this problem: by utilizing feature vectors as RF fingerprints, we first demonstrate that training could be simplified to indexing those feature vectors into a database using locality sensitive hashing (LSH). Then we show that approximate nearest neighbor search could be performed on the database to perform transmitter authorization that matches the accuracy of deep learning models, while allowing for more than 100x faster retraining. Furthermore, dimensionality reduction techniques are used on the feature vectors to show that the authorization latency of our technique could be reduced to approach that of traditional deep learning-based systems.

arXiv:2111.02736

Deep Learning Methods for Daily Wildfire Danger Forecasting

Wildfire forecasting is of paramount importance for disaster risk reduction and environmental sustainability. We approach daily fire danger prediction as a machine learning task, using historical Earth observation data from the last decade to predict next-day's fire danger. To that end, we collect, pre-process and harmonize an open-access datacube, featuring a set of covariates that jointly affect the fire occurrence and spread, such as weather conditions, satellite-derived products, topography features and variables related to human activity. We implement a variety of Deep Learning (DL) models to capture the spatial, temporal or spatio-temporal context and compare them against a Random Forest (RF) baseline. We find that either spatial or temporal context is enough to surpass the RF, while a ConvLSTM that exploits the spatio-temporal context performs best with a test Area Under the Receiver Operating Characteristic of 0.926. Our DL-based proof-of-concept provides national-scale daily fire danger maps at a much higher spatial resolution than existing operational solutions.

arXiv:2111.02520

Resampling and super-resolution of hexagonally sampled images using deep learning

Super-resolution (SR) aims to increase the resolution of imagery. Applications include security, medical imaging, and object recognition. We propose a deep learning-based SR system that takes a hexagonally sampled low-resolution image as an input and generates a rectangularly sampled SR image as an output. For training and testing, we use a realistic observation model that includes optical degradation from diffraction and sensor degradation from detector integration. Our SR approach first uses non-uniform interpolation to partially upsample the observed hexagonal imagery and convert it to a rectangular grid. We then leverage a state-of-the-art convolutional neural network (CNN) architecture designed for SR known as Residual Channel Attention Network (RCAN). In particular, we use RCAN to further upsample and restore the imagery to produce the final SR image estimate. We demonstrate that this system is superior to applying RCAN directly to rectangularly sampled LR imagery with equivalent sample density. The theoretical advantages of hexagonal sampling are well known. However, to the best of our knowledge, the practical benefit of hexagonal sampling in light of modern processing techniques such as RCAN SR is heretofore untested. Our SR system demonstrates a notable advantage of hexagonally sampled imagery when employing a modified RCAN for hexagonal SR.

arXiv:2111.01931공식 코드 · Papers with Code

Deep Learning Algorithms for Hedging with Frictions

This work studies the deep learning-based numerical algorithms for optimal hedging problems in markets with general convex transaction costs on the trading rates, focusing on their scalability of trading time horizon. Based on the comparison results of the FBSDE solver by Han, Jentzen, and E (2018) and the Deep Hedging algorithm by Buehler, Gonon, Teichmann, and Wood (2019), we propose a Stable Transfer Hedging (ST-Hedging) algorithm, to aggregate the convenience of the leading-order approximation formulas and the accuracy of the deep learning-based algorithms. Our ST-Hedging algorithm achieves the same state-of-the-art performance in short and moderately long time horizon as FBSDE solver and Deep Hedging, and generalize well to long time horizon when previous algorithms become suboptimal. With the transfer learning technique, ST-Hedging drastically reduce the training time, and shows great scalability to high-dimensional settings. This opens up new possibilities in model-based deep learning algorithms in economics, finance, and operational research, which takes advantages of the domain expert knowledge and the accuracy of the learning-based methods.

논문 ID: document/9373916

Elastic Deep Learning in Multi-Tenant GPU Clusters

We study how to support elasticity, that is, the ability to dynamically adjust the parallelism (i.e., the number of GPUs), for deep neural network (DNN) training in a GPU cluster. Elasticity can benefit multi-tenant GPU cluster management in many ways, for example, achieving various scheduling objectives (e.g., job throughput, job completion time, GPU efficiency) according to cluster load variations, utilizing transient idle resources, and supporting performance profiling, job migration, and straggler mitigation. We propose EDL, which enables elastic deep learning with a simple API and can be easily integrated with existing deep learning frameworks such as TensorFlow and PyTorch. EDL also incorporates techniques that are necessary to reduce the overhead of parallelism adjustments, such as stop-free scaling and dynamic data pipeline. We demonstrate with experiments that EDL can indeed bring significant benefits to the above-listed applications in GPU cluster management.

arXiv:2111.01975

Binary classification of proteins by a Machine Learning approach

In this work we present a system based on a Deep Learning approach, by using a Convolutional Neural Network, capable of classifying protein chains of amino acids based on the protein description contained in the Protein Data Bank. Each protein is fully described in its chemical-physical-geometric properties in a file in XML format. The aim of the work is to design a prototypical Deep Learning machinery for the collection and management of a huge amount of data and to validate it through its application to the classification of a sequences of amino acids. We envisage applying the described approach to more general classification problems in biomolecules, related to structural properties and similarities.

arXiv:2111.01956

One Pass ImageNet

We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting. ImageNet is a widely known benchmark dataset that has helped drive and evaluate recent advancements in deep learning. Typically, deep learning methods are trained on static data that the models have random access to, using multiple passes over the dataset with a random shuffle at each epoch of training. Such data access assumption does not hold in many real-world scenarios where massive data is collected from a stream and storing and accessing all the data becomes impractical due to storage costs and privacy concerns. For OPIN, we treat the ImageNet data as arriving sequentially, and there is limited memory budget to store a small subset of the data. We observe that training a deep network in a single pass with the same training settings used for multi-epoch training results in a huge drop in prediction accuracy. We show that the performance gap can be significantly decreased by paying a small memory cost and utilizing techniques developed for continual learning, despite the fact that OPIN differs from typical continual problem settings. We propose using OPIN to study resource-efficient deep learning.

arXiv:2111.01867

Probabilistic Deep Learning for Real-Time Large Deformation Simulations

For many novel applications, such as patient-specific computer-aided surgery, conventional solution techniques of the underlying nonlinear problems are usually computationally too expensive and are lacking information about how certain can we be about their predictions. In the present work, we propose a highly efficient deep-learning surrogate framework that is able to accurately predict the response of bodies undergoing large deformations in real-time. The surrogate model has a convolutional neural network architecture, called U-Net, which is trained with force-displacement data obtained with the finite element method. We propose deterministic and probabilistic versions of the framework. The probabilistic framework utilizes the Variational Bayes Inference approach and is able to capture all the uncertainties present in the data as well as in the deep-learning model. Based on several benchmark examples, we show the predictive capabilities of the framework and discuss its possible limitations

arXiv:2111.02061

Deep-Learning-Based Single-Image Height Reconstruction from Very-High-Resolution SAR Intensity Data

Originally developed in fields such as robotics and autonomous driving with image-based navigation in mind, deep learning-based single-image depth estimation (SIDE) has found great interest in the wider image analysis community. Remote sensing is no exception, as the possibility to estimate height maps from single aerial or satellite imagery bears great potential in the context of topographic reconstruction. A few pioneering investigations have demonstrated the general feasibility of single image height prediction from optical remote sensing images and motivate further studies in that direction. With this paper, we present the first-ever demonstration of deep learning-based single image height prediction for the other important sensor modality in remote sensing: synthetic aperture radar (SAR) data. Besides the adaptation of a convolutional neural network (CNN) architecture for SAR intensity images, we present a workflow for the generation of training data, and extensive experimental results for different SAR imaging modes and test sites. Since we put a particular emphasis on transferability, we are able to confirm that deep learning-based single-image height estimation is not only possible, but also transfers quite well to unseen data, even if acquired by different imaging modes and imaging parameters.

arXiv:2111.01657

LogLAB: Attention-Based Labeling of Log Data Anomalies via Weak Supervision

With increasing scale and complexity of cloud operations, automated detection of anomalies in monitoring data such as logs will be an essential part of managing future IT infrastructures. However, many methods based on artificial intelligence, such as supervised deep learning models, require large amounts of labeled training data to perform well. In practice, this data is rarely available because labeling log data is expensive, time-consuming, and requires a deep understanding of the underlying system. We present LogLAB, a novel modeling approach for automated labeling of log messages without requiring manual work by experts. Our method relies on estimated failure time windows provided by monitoring systems to produce precise labeled datasets in retrospect. It is based on the attention mechanism and uses a custom objective function for weak supervision deep learning techniques that accounts for imbalanced data. Our evaluation shows that LogLAB consistently outperforms nine benchmark approaches across three different datasets and maintains an F1-score of more than 0.98 even at large failure time windows.

arXiv:2111.01561

Sub-cortical structure segmentation database for young population

Segmentation of sub-cortical structures from MRI scans is of interest in many neurological diagnosis. Since this is a laborious task machine learning and specifically deep learning (DL) methods have become explored. The structural complexity of the brain demands a large, high quality segmentation dataset to develop good DL-based solutions for sub-cortical structure segmentation. Towards this, we are releasing a set of 114, 1.5 Tesla, T1 MRI scans with manual delineations for 14 sub-cortical structures. The scans in the dataset were acquired from healthy young (21-30 years) subjects ( 58 male and 56 female) and all the structures are manually delineated by experienced radiology experts. Segmentation experiments have been conducted with this dataset and results demonstrate that accurate results can be obtained with deep-learning methods. Our sub-cortical structure segmentation dataset, Indian Brain Segmentation Dataset (IBSD) is made openly available at \url{https://doi.org/10.5281/zenodo.5656776}.

arXiv:2111.00030공식 코드 · Papers with Code

Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers

Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over classification-based, such as continuous direction-of-arrival estimation of static and moving sources. However, multi-source scenarios require multiple regressors without a clear training strategy up-to-date, that does not rely on auxiliary information such as simultaneous sound classification. We investigate end-to-end training of such methods with a technique recently proposed for video object detectors, adapted to the SSL setting. A differentiable network is constructed that can be plugged to the output of the localizer to solve the optimal assignment between predictions and references, optimizing directly the popular CLEAR-MOT tracking metrics. Results indicate large improvements over directly optimizing mean squared errors, in terms of localization error, detection metrics, and tracking capabilities.

arXiv:2111.00856

Large-Scale Deep Learning Optimizations: A Comprehensive Survey

Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication. In this survey, we aim to provide a clear sketch about the optimizations for large-scale deep learning with regard to the model accuracy and model efficiency. We investigate algorithms that are most commonly used for optimizing, elaborate the debatable topic of generalization gap arises in large-batch training, and review the SOTA strategies in addressing the communication overhead and reducing the memory footprints.

arXiv:2111.00418

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human--computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

arXiv:2111.00961

Robustness of deep learning algorithms in astronomy -- galaxy morphology studies

Deep learning models are being increasingly adopted in wide array of scientific domains, especially to handle high-dimensionality and volume of the scientific data. However, these models tend to be brittle due to their complexity and overparametrization, especially to the inadvertent adversarial perturbations that can appear due to common image processing such as compression or blurring that are often seen with real scientific data. It is crucial to understand this brittleness and develop models robust to these adversarial perturbations. To this end, we study the effect of observational noise from the exposure time, as well as the worst case scenario of a one-pixel attack as a proxy for compression or telescope errors on performance of ResNet18 trained to distinguish between galaxies of different morphologies in LSST mock data. We also explore how domain adaptation techniques can help improve model robustness in case of this type of naturally occurring attacks and help scientists build more trustworthy and stable models.

arXiv:2111.00734공식 코드 · Papers with Code

Robust Deep Learning from Crowds with Belief Propagation

Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers. We address the inference and learning problems using such a crowdsourced dataset with noise. Due to the nature of sparsity in crowdsourcing, it is critical to exploit both probabilistic model to capture worker prior and neural network to extract task feature despite risks from wrong prior and overfitted feature in practice. We hence establish a neural-powered Bayesian framework, from which we devise deepMF and deepBP with different choice of variational approximation methods, mean field (MF) and belief propagation (BP), respectively. This provides a unified view of existing methods, which are special cases of deepMF with different priors. In addition, our empirical study suggests that deepBP is a new approach, which is more robust against wrong prior, feature overfitting and extreme workers thanks to the more sophisticated BP than MF.