PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2009.10190

Federated Learning for Computational Pathology on Gigapixel Whole Slide Images

Deep Learning-based computational pathology algorithms have demonstrated profound ability to excel in a wide array of tasks that range from characterization of well known morphological phenotypes to predicting non-human-identifiable features from histology such as molecular alterations. However, the development of robust, adaptable, and accurate deep learning-based models often rely on the collection and time-costly curation large high-quality annotated training data that should ideally come from diverse sources and patient populations to cater for the heterogeneity that exists in such datasets. Multi-centric and collaborative integration of medical data across multiple institutions can naturally help overcome this challenge and boost the model performance but is limited by privacy concerns amongst other difficulties that may arise in the complex data sharing process as models scale towards using hundreds of thousands of gigapixel whole slide images. In this paper, we introduce privacy-preserving federated learning for gigapixel whole slide images in computational pathology using weakly-supervised attention multiple instance learning and differential privacy. We evaluated our approach on two different diagnostic problems using thousands of histology whole slide images with only slide-level labels. Additionally, we present a weakly-supervised learning framework for survival prediction and patient stratification from whole slide images and demonstrate its effectiveness in a federated setting. Our results show that using federated learning, we can effectively develop accurate weakly supervised deep learning models from distributed data silos without direct data sharing and its associated complexities, while also preserving differential privacy using randomized noise generation.

arXiv:2009.09346

TorchDyn: A Neural Differential Equations Library

Continuous-depth learning has recently emerged as a novel perspective on deep learning, improving performance in tasks related to dynamical systems and density estimation. Core to these approaches is the neural differential equation, whose forward passes are the solutions of an initial value problem parametrized by a neural network. Unlocking the full potential of continuous-depth models requires a different set of software tools, due to peculiar differences compared to standard discrete neural networks, e.g inference must be carried out via numerical solvers. We introduce TorchDyn, a PyTorch library dedicated to continuous-depth learning, designed to elevate neural differential equations to be as accessible as regular plug-and-play deep learning primitives. This objective is achieved by identifying and subdividing different variants into common essential components, which can be combined and freely repurposed to obtain complex compositional architectures. TorchDyn further offers step-by-step tutorials and benchmarks designed to guide researchers and contributors.

arXiv:2009.09326

UniNet: Next Term Course Recommendation using Deep Learning

Course enrollment recommendation is a relevant task that helps university students decide what is the best combination of courses to enroll in the next term. In particular, recommender system techniques like matrix factorization and collaborative filtering have been developed to try to solve this problem. As these techniques fail to represent the time-dependent nature of academic performance datasets we propose a deep learning approach using recurrent neural networks that aims to better represent how chronological order of course grades affects the probability of success. We have shown that it is possible to obtain a performance of 81.10% on AUC metric using only grade information and that it is possible to develop a recommender system with academic student performance prediction. This is shown to be meaningful across different student GPA levels and course difficulties

arXiv:2009.09875공식 코드 · Papers with Code

A Deep Learning Based Analysis-Synthesis Framework For Unison Singing

Unison singing is the name given to an ensemble of singers simultaneously singing the same melody and lyrics. While each individual singer in a unison sings the same principle melody, there are slight timing and pitch deviations between the singers, which, along with the ensemble of timbres, give the listener a perceived sense of "unison". In this paper, we present a study of unison singing in the context of choirs; utilising some recently proposed deep-learning based methodologies, we analyse the fundamental frequency (F0) distribution of the individual singers in recordings of unison mixtures. Based on the analysis, we propose a system for synthesising a unison signal from an a cappella input and a single voice prototype representative of a unison mixture. We use subjective listening tests to evaluate perceptual factors of our proposed system for synthesis, including quality, adherence to the melody as well the degree of perceived unison.

arXiv:2009.09748

A Deep Hybrid Model for Recommendation Systems

Recommendation has been a long-standing problem in many areas ranging from e-commerce to social websites. Most current studies focus only on traditional approaches such as content-based or collaborative filtering while there are relatively fewer studies in hybrid recommender systems. Due to the latest advances of deep learning achieved in different fields including computer vision and natural language processing, deep learning has also gained much attention in Recommendation Systems. There are several studies that utilize ID embeddings of users and items to implement collaborative filtering with deep neural networks. However, such studies do not take advantage of other categorical or continuous features of inputs. In this paper, we propose a new deep neural network architecture which consists of not only ID embeddings but also auxiliary information such as features of job postings and candidates for job recommendation system which is a reciprocal recommendation system. Experimental results on the dataset from a job-site show that the proposed method improves recommendation results over deep learning models utilizing ID embeddings.

arXiv:2009.09571

Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images

Automated segmentation can assist radiotherapy treatment planning by saving manual contouring efforts and reducing intra-observer and inter-observer variations. The recent development of deep learning approaches has revoluted medical data processing, including semantic segmentation, by dramatically improving performance. However, training effective deep learning models usually require a large amount of high-quality labeled data, which are often costly to collect. We developed a novel semi-supervised adversarial deep learning approach for 3D pelvic CT image semantic segmentation. Unlike supervised deep learning methods, the new approach can utilize both annotated and un-annotated data for training. It generates un-annotated synthetic data by a data augmentation scheme using generative adversarial networks (GANs). We applied the new approach to segmenting multiple organs in male pelvic CT images, where CT images without annotations and GAN-synthesized un-annotated images were used in semi-supervised learning. Experimental results, evaluated by three metrics (Dice similarity coefficient, average Hausdorff distance, and average surface Hausdorff distance), showed that the new method achieved either comparable performance with substantially fewer annotated images or better performance with the same amount of annotated data, outperforming the existing state-of-the-art methods.

arXiv:2009.09535

Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts

Bayesian deep learning offers a principled way to address many issues concerning safety of artificial intelligence (AI), such as model uncertainty,model interpretability, and prediction bias. However, due to the lack of efficient Monte Carlo algorithms for sampling from the posterior of deep neural networks (DNNs), Bayesian deep learning has not yet powered our AI system. We propose a class of adaptive stochastic gradient Markov chain Monte Carlo (SGMCMC) algorithms, where the drift function is biased to enhance escape from saddle points and the bias is adaptively adjusted according to the gradient of past samples. We establish the convergence of the proposed algorithms under mild conditions, and demonstrate via numerical examples that the proposed algorithms can significantly outperform the existing SGMCMC algorithms, such as stochastic gradient Langevin dynamics (SGLD), stochastic gradient Hamiltonian Monte Carlo (SGHMC) and preconditioned SGLD, in both simulation and optimization tasks.

arXiv:2009.09523

VirtualFlow: Decoupling Deep Learning Models from the Underlying Hardware

State-of-the-art deep learning systems such as TensorFlow and PyTorch tightly couple the model with the underlying hardware. This coupling requires the user to modify application logic in order to run the same job across a different set of resources, thereby limiting the choice of hardware for a given workload and potentially forcing the user to forgo more efficient hardware configurations. We propose VirtualFlow, a system leveraging a novel abstraction called virtual node processing to decouple the model from the hardware. In each step of training or inference, the batch of input data is split across virtual nodes instead of hardware accelerators (e.g. GPUs and TPUs). Mapping multiple virtual nodes to each accelerator and processing them sequentially effectively time slices the batch, thereby allowing users to reduce the memory requirement of their workloads and mimic large batch sizes on small clusters. Using this technique, VirtualFlow enables many new use cases, such as reproducing training results across different hardware, resource elasticity, and heterogeneous training. In our evaluation, our implementation of VirtualFlow for TensorFlow achieved strong convergence guarantees across different hardware with out-of-the-box hyperparameters, up to 48% lower job completion times with resource elasticity, and up to 42% higher throughput with heterogeneous training.

arXiv:2009.10058공식 코드 · Papers with Code

Exploring Intensity Invariance in Deep Neural Networks for Brain Image Registration

Image registration is a widely-used technique in analysing large scale datasets that are captured through various imaging modalities and techniques in biomedical imaging such as MRI, X-Rays, etc. These datasets are typically collected from various sites and under different imaging protocols using a variety of scanners. Such heterogeneity in the data collection process causes inhomogeneity or variation in intensity (brightness) and noise distribution. These variations play a detrimental role in the performance of image registration, segmentation and detection algorithms. Classical image registration methods are computationally expensive but are able to handle these artifacts relatively better. However, deep learning-based techniques are shown to be computationally efficient for automated brain registration but are sensitive to the intensity variations. In this study, we investigate the effect of variation in intensity distribution among input image pairs for deep learning-based image registration methods. We find a performance degradation of these models when brain image pairs with different intensity distribution are presented even with similar structures. To overcome this limitation, we incorporate a structural similarity-based loss function in a deep neural network and test its performance on the validation split separated before training as well as on a completely unseen new dataset. We report that the deep learning models trained with structure similarity-based loss seems to perform better for both datasets. This investigation highlights a possible performance limiting factor in deep learning-based registration models and suggests a potential solution to incorporate the intensity distribution variation in the input image pairs. Our code and models are available at https://github.com/hassaanmahmood/DeepIntense.

arXiv:2009.08920공식 코드 · Papers with Code

Deep Learning for 3D Point Cloud Understanding: A Survey

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points. To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances. More information regarding this survey can be found at: https://github.com/SHI-Labs/3D-Point-Cloud-Learning.

arXiv:2009.08809

Deep learning denoising for EOG artifacts removal from EEG signals

There are many sources of interference encountered in the electroencephalogram (EEG) recordings, specifically ocular, muscular, and cardiac artifacts. Rejection of EEG artifacts is an essential process in EEG analysis since such artifacts cause many problems in EEG signals analysis. One of the most challenging issues in EEG denoising processes is removing the ocular artifacts where Electrooculographic (EOG), and EEG signals have an overlap in both frequency and time domains. In this paper, we build and train a deep learning model to deal with this challenge and remove the ocular artifacts effectively. In the proposed scheme, we convert each EEG signal to an image to be fed to a U-NET model, which is a deep learning model usually used in image segmentation tasks. We proposed three different schemes and made our U-NET based models learn to purify contaminated EEG signals similar to the process used in the image segmentation process. The results confirm that one of our schemes can achieve a reliable and promising accuracy to reduce the Mean square error between the target signal (Pure EEGs) and the predicted signal (Purified EEGs).

arXiv:2009.08674

TopNet: Topology Preserving Metric Learning for Vessel Tree Reconstruction and Labelling

Reconstructing Portal Vein and Hepatic Vein trees from contrast enhanced abdominal CT scans is a prerequisite for preoperative liver surgery simulation. Existing deep learning based methods treat vascular tree reconstruction as a semantic segmentation problem. However, vessels such as hepatic and portal vein look very similar locally and need to be traced to their source for robust label assignment. Therefore, semantic segmentation by looking at local 3D patch results in noisy misclassifications. To tackle this, we propose a novel multi-task deep learning architecture for vessel tree reconstruction. The network architecture simultaneously solves the task of detecting voxels on vascular centerlines (i.e. nodes) and estimates connectivity between center-voxels (edges) in the tree structure to be reconstructed. Further, we propose a novel connectivity metric which considers both inter-class distance and intra-class topological distance between center-voxel pairs. Vascular trees are reconstructed starting from the vessel source using the learned connectivity metric using the shortest path tree algorithm. A thorough evaluation on public IRCAD dataset shows that the proposed method considerably outperforms existing semantic segmentation based methods. To the best of our knowledge, this is the first deep learning based approach which learns multi-label tree structure connectivity from images.

arXiv:2009.08525공식 코드 · Papers with Code

Deep Learning & Software Engineering: State of Research and Future Directions

Given the current transformative potential of research that sits at the intersection of Deep Learning (DL) and Software Engineering (SE), an NSF-sponsored community workshop was conducted in co-location with the 34th IEEE/ACM International Conference on Automated Software Engineering (ASE'19) in San Diego, California. The goal of this workshop was to outline high priority areas for cross-cutting research. While a multitude of exciting directions for future work were identified, this report provides a general summary of the research areas representing the areas of highest priority which were discussed at the workshop. The intent of this report is to serve as a potential roadmap to guide future work that sits at the intersection of SE & DL.

arXiv:2009.08510

Automatic deep learning for trend prediction in time series data

Recently, Deep Neural Network (DNN) algorithms have been explored for predicting trends in time series data. In many real world applications, time series data are captured from dynamic systems. DNN models must provide stable performance when they are updated and retrained as new observations becomes available. In this work we explore the use of automatic machine learning techniques to automate the algorithm selection and hyperparameter optimisation process for trend prediction. We demonstrate how a recent AutoML tool, specifically the HpBandSter framework, can be effectively used to automate DNN model development. Our AutoML experiments found optimal configurations that produced models that compared well against the average performance and stability levels of configurations found during the manual experiments across four data sets.

arXiv:2006.11373공식 코드 · Papers with Code

Deceiving computers in Reverse Turing Test through Deep Learning

It is increasingly becoming difficult for human beings to work on their day to day life without going through the process of reverse Turing test, where the Computers tests the users to be humans or not. Almost every website and service providers today have the process of checking whether their website is being crawled or not by automated bots which could extract valuable information from their site. In the process the bots are getting more intelligent by the use of Deep Learning techniques to decipher those tests and gain unwanted automated access to data while create nuisance by posting spam. Humans spend a considerable amount of time almost every day when trying to decipher CAPTCHAs. The aim of this investigation is to check whether the use of a subset of commonly used CAPTCHAs, known as the text CAPTCHA is a reliable process for verifying their human customers. We mainly focused on the preprocessing step for every CAPTCHA which converts them in binary intensity and removes the confusion as much as possible and developed various models to correctly label as many CAPTCHAs as possible. We also suggested some ways to improve the process of verifying the humans which makes it easy for humans to solve the existing CAPTCHAs and difficult for bots to do the same.

arXiv:2009.08328

Review: Deep Learning in Electron Microscopy

Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Afterwards, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.

arXiv:2009.08114공식 코드 · Papers with Code

A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching

Recognizing toponyms and resolving them to their real-world referents is required for providing advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the task of identifying the potential entities that can be referred to by a toponym previously recognized. While it has traditionally received little attention in the research community, it has been shown that candidate selection has a significant impact on downstream tasks (i.e. entity resolution), especially in noisy or non-standard text. In this paper, we introduce a flexible deep learning method for candidate selection through toponym matching, using state-of-the-art neural network architectures. We perform an intrinsic toponym matching evaluation based on several new realistic datasets, which cover various challenging scenarios (cross-lingual and regional variations, as well as OCR errors). We report its performance on candidate selection in the context of the downstream task of toponym resolution, both on existing datasets and on a new manually-annotated resource of nineteenth-century English OCR'd text.

arXiv:2009.07460

MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework

With the tremendous success of deep learning, there exists imminent need to deploy deep learning models onto edge devices. To tackle the limited computing and storage resources in edge devices, model compression techniques have been widely used to trim deep neural network (DNN) models for on-device inference execution. This paper targets the commonly used FPGA (field programmable gate array) devices as the hardware platforms for DNN edge computing. We focus on the DNN quantization as the main model compression technique, since DNN quantization has been of great importance for the implementations of DNN models on the hardware platforms. The novelty of this work comes in twofold: (i) We propose a mixed-scheme DNN quantization method that incorporates both the linear and non-linear number systems for quantization, with the aim to boost the utilization of the heterogeneous computing resources, i.e., LUTs (look up tables) and DSPs (digital signal processors) on an FPGA. Note that all the existing (single-scheme) quantization methods can only utilize one type of resources (either LUTs or DSPs for the MAC (multiply-accumulate) operations in deep learning computations. (ii) We use a quantization method that supports multiple precisions along the intra-layer dimension, while the existing quantization methods apply multi-precision quantization along the inter-layer dimension. The intra-layer multi-precision method can uniform the hardware configurations for different layers to reduce computation overhead and at the same time preserve the model accuracy as the inter-layer approach.

arXiv:2009.07386공식 코드 · Papers with Code

Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Development

We developed a rich dataset of Chest X-Ray (CXR) images to assist investigators in artificial intelligence. The data were collected using an eye tracking system while a radiologist reviewed and reported on 1,083 CXR images. The dataset contains the following aligned data: CXR image, transcribed radiology report text, radiologist's dictation audio and eye gaze coordinates data. We hope this dataset can contribute to various areas of research particularly towards explainable and multimodal deep learning / machine learning methods. Furthermore, investigators in disease classification and localization, automated radiology report generation, and human-machine interaction can benefit from these data. We report deep learning experiments that utilize the attention maps produced by eye gaze dataset to show the potential utility of this data.

arXiv:2009.07780

Deep Learning Approaches for Extracting Adverse Events and Indications of Dietary Supplements from Clinical Text

The objective of our work is to demonstrate the feasibility of utilizing deep learning models to extract safety signals related to the use of dietary supplements (DS) in clinical text. Two tasks were performed in this study. For the named entity recognition (NER) task, Bi-LSTM-CRF (Bidirectional Long-Short-Term-Memory Conditional Random Fields) and BERT (Bidirectional Encoder Representations from Transformers) models were trained and compared with CRF model as a baseline to recognize the named entities of DS and Events from clinical notes. In the relation extraction (RE) task, two deep learning models, including attention-based Bi-LSTM and CNN (Convolutional Neural Network), and a random forest model were trained to extract the relations between DS and Events, which were categorized into three classes: positive (i.e., indication), negative (i.e., adverse events), and not related. The best performed NER and RE models were further applied on clinical notes mentioning 88 DS for discovering DS adverse events and indications, which were compared with a DS knowledge base. For the NER task, deep learning models achieved a better performance than CRF, with F1 scores above 0.860. The attention-based Bi-LSTM model performed the best in the relation extraction task, with the F1 score of 0.893. When comparing DS event pairs generated by the deep learning models with the knowledge base for DS and Event, we found both known and unknown pairs. Deep learning models can detect adverse events and indication of DS in clinical notes, which hold great potential for monitoring the safety of DS use.