PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2102.06942공식 코드 · Papers with Code

Rotation-Equivariant Deep Learning for Diffusion MRI

Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. These new networks work better because they do not struggle with learning each possible orientation of each image feature separately. So far, they have been proposed for 2D and 3D data. Here we generalize them to 6D diffusion MRI data, ensuring joint equivariance under 3D roto-translations in image space and the matching 3D rotations in $q$-space, as dictated by the image formation. Such equivariant deep learning is appropriate for diffusion MRI, because microstructural and macrostructural features such as neural fibers can appear at many different orientations, and because even non-rotation-equivariant deep learning has so far been the best method for many diffusion MRI tasks. We validate our equivariant method on multiple-sclerosis lesion segmentation. Our proposed neural networks yield better results and require fewer scans for training compared to non-rotation-equivariant deep learning. They also inherit all the advantages of deep learning over classical diffusion MRI methods. Our implementation is available at https://github.com/philip-mueller/equivariant-deep-dmri and can be used off the shelf without understanding the mathematical background.

arXiv:2102.06744공식 코드 · Papers with Code

Hybrid phonetic-neural model for correction in speech recognition systems

Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular application domains. Some strategies have been explored to reduce errors in closed ASRs through post-processing, particularly automatic spell checking, and deep learning approaches. In this article, we explore using a deep neural network to refine the results of a phonetic correction algorithm applied to a telesales audio database. The results exhibit a reduction in the word error rate (WER), both in the original transcription and in the phonetic correction, which shows the viability of deep learning models together with post-processing correction strategies to reduce errors made by closed ASRs in specific language domains.

arXiv:2102.06725

Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives

While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design, speedy computation on distributed setting, and compatibility between different tools. In this paper, we introduce Neural Network Libraries (https://nnabla.org), a deep learning framework designed from engineer's perspective, with emphasis on usability and compatibility as its core design principles. We elaborate on each of our design principles and its merits, and validate our attempts via experiments.

arXiv:2102.07662

Overview of the TREC 2020 deep learning track

This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime. We again have a document retrieval task and a passage retrieval task, each with hundreds of thousands of human-labeled training queries. We evaluate using single-shot TREC-style evaluation, to give us a picture of which ranking methods work best when large data is available, with much more comprehensive relevance labeling on the small number of test queries. This year we have further evidence that rankers with BERT-style pretraining outperform other rankers in the large data regime.

arXiv:2102.06285공식 코드 · Papers with Code

COVID-19 detection from scarce chest x-ray image data using few-shot deep learning approach

In the current COVID-19 pandemic situation, there is an urgent need to screen infected patients quickly and accurately. Using deep learning models trained on chest X-ray images can become an efficient method for screening COVID-19 patients in these situations. Deep learning approaches are already widely used in the medical community. However, they require a large amount of data to be accurate. The open-source community collectively has made efforts to collect and annotate the data, but it is not enough to train an accurate deep learning model. Few-shot learning is a sub-field of machine learning that aims to learn the objective with less amount of data. In this work, we have experimented with well-known solutions for data scarcity in deep learning to detect COVID-19. These include data augmentation, transfer learning, and few-shot learning, and unsupervised learning. We have also proposed a custom few-shot learning approach to detect COVID-19 using siamese networks. Our experimental results showcased that we can implement an efficient and accurate deep learning model for COVID-19 detection by adopting the few-shot learning approaches even with less amount of data. Using our proposed approach we were able to achieve 96.4% accuracy an improvement from 83% using baseline models.

arXiv:2102.06684

DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting

We introduce DeepGLEAM, a hybrid model for COVID-19 forecasting. DeepGLEAM combines a mechanistic stochastic simulation model GLEAM with deep learning. It uses deep learning to learn the correction terms from GLEAM, which leads to improved performance. We further integrate various uncertainty quantification methods to generate confidence intervals. We demonstrate DeepGLEAM on real-world COVID-19 mortality forecasting tasks.

arXiv:2102.06062

Deep Learning with Label Differential Privacy

The Randomized Response (RR) algorithm is a classical technique to improve robustness in survey aggregation, and has been widely adopted in applications with differential privacy guarantees. We propose a novel algorithm, Randomized Response with Prior (RRWithPrior), which can provide more accurate results while maintaining the same level of privacy guaranteed by RR. We then apply RRWithPrior to learn neural networks with label differential privacy (LabelDP), and show that when only the label needs to be protected, the model performance can be significantly improved over the previous state-of-the-art private baselines. Moreover, we study different ways to obtain priors, which when used with RRWithPrior can additionally improve the model performance, further reducing the accuracy gap between private and non-private models. We complement the empirical results with theoretical analysis showing that LabelDP is provably easier than protecting both the inputs and labels.

arXiv:2102.06103공식 코드 · Papers with Code

Measuring Robustness in Deep Learning Based Compressive Sensing

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness.

arXiv:2102.05218

FLOP: Federated Learning on Medical Datasets using Partial Networks

The outbreak of COVID-19 Disease due to the novel coronavirus has caused a shortage of medical resources. To aid and accelerate the diagnosis process, automatic diagnosis of COVID-19 via deep learning models has recently been explored by researchers across the world. While different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19, the data itself is still scarce due to patient privacy concerns. Federated Learning (FL) is a natural solution because it allows different organizations to cooperatively learn an effective deep learning model without sharing raw data. However, recent studies show that FL still lacks privacy protection and may cause data leakage. We investigate this challenging problem by proposing a simple yet effective algorithm, named \textbf{F}ederated \textbf{L}earning \textbf{o}n Medical Datasets using \textbf{P}artial Networks (FLOP), that shares only a partial model between the server and clients. Extensive experiments on benchmark data and real-world healthcare tasks show that our approach achieves comparable or better performance while reducing the privacy and security risks. Of particular interest, we conduct experiments on the COVID-19 dataset and find that our FLOP algorithm can allow different hospitals to collaboratively and effectively train a partially shared model without sharing local patients' data.

arXiv:2102.05182

A Deep Learning Approach for Characterizing Major Galaxy Mergers

Fine-grained estimation of galaxy merger stages from observations is a key problem useful for validation of our current theoretical understanding of galaxy formation. To this end, we demonstrate a CNN-based regression model that is able to predict, for the first time, using a single image, the merger stage relative to the first perigee passage with a median error of 38.3 million years (Myrs) over a period of 400 Myrs. This model uses no specific dynamical modeling and learns only from simulated merger events. We show that our model provides reasonable estimates on real observations, approximately matching prior estimates provided by detailed dynamical modeling. We provide a preliminary interpretability analysis of our models, and demonstrate first steps toward calibrated uncertainty estimation.

arXiv:2102.05105공식 코드 · Papers with Code

Deep learning architectural designs for super-resolution of noisy images

Recent advances in deep learning have led to significant improvements in single image super-resolution (SR) research. However, due to the amplification of noise during the upsampling steps, state-of-the-art methods often fail at reconstructing high-resolution images from noisy versions of their low-resolution counterparts. However, this is especially important for images from unknown cameras with unseen types of image degradation. In this work, we propose to jointly perform denoising and super-resolution. To this end, we investigate two architectural designs: "in-network" combines both tasks at feature level, while "pre-network" first performs denoising and then super-resolution. Our experiments show that both variants have specific advantages: The in-network design obtains the strongest results when the type of image corruption is aligned in the training and testing dataset, for any choice of denoiser. The pre-network design exhibits superior performance on unseen types of image corruption, which is a pathological failure case of existing super-resolution models. We hope that these findings help to enable super-resolution also in less constrained scenarios where source camera or imaging conditions are not well controlled. Source code and pretrained models are available at https://github.com/ angelvillar96/super-resolution-noisy-images.

arXiv:2102.04828

Consensus Control for Decentralized Deep Learning

Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal that, even in a data-center setup, decentralized training often suffers from the degradation in the quality of the model: the training and test performance of models trained in a decentralized fashion is in general worse than that of models trained in a centralized fashion, and this performance drop is impacted by parameters such as network size, communication topology and data partitioning. We identify the changing consensus distance between devices as a key parameter to explain the gap between centralized and decentralized training. We show in theory that when the training consensus distance is lower than a critical quantity, decentralized training converges as fast as the centralized counterpart. We empirically validate that the relation between generalization performance and consensus distance is consistent with this theoretical observation. Our empirical insights allow the principled design of better decentralized training schemes that mitigate the performance drop. To this end, we provide practical training guidelines and exemplify its effectiveness on the data-center setup as the important first step.

arXiv:2102.04761공식 코드 · Papers with Code

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge and may severely deteriorate the generalization performance. In this paper, we investigate and identify the limitation of several decentralized optimization algorithms for different degrees of data heterogeneity. We propose a novel momentum-based method to mitigate this decentralized training difficulty. We show in extensive empirical experiments on various CV/NLP datasets (CIFAR-10, ImageNet, and AG News) and several network topologies (Ring and Social Network) that our method is much more robust to the heterogeneity of clients' data than other existing methods, by a significant improvement in test performance ($1\% \!-\! 20\%$). Our code is publicly available.

arXiv:2102.05001

An application of a pseudo-parabolic modeling to texture image recognition

In this work, we present a novel methodology for texture image recognition using a partial differential equation modeling. More specifically, we employ the pseudo-parabolic Buckley-Leverett equation to provide a dynamics to the digital image representation and collect local descriptors from those images evolving in time. For the local descriptors we employ the magnitude and signal binary patterns and a simple histogram of these features was capable of achieving promising results in a classification task. We compare the accuracy over well established benchmark texture databases and the results demonstrate competitiveness, even with the most modern deep learning approaches. The achieved results open space for future investigation on this type of modeling for image analysis, especially when there is no large amount of data for training deep learning models and therefore model-based approaches arise as suitable alternatives.

arXiv:2102.03987

Deep Learning Based Walking Tasks Classification in Older Adults using fNIRS

Decline in gait features is common in older adults and an indicator of increased risk of disability, morbidity, and mortality. Under dual task walking (DTW) conditions, further degradation in the performance of both the gait and the secondary cognitive task were found in older adults which were significantly correlated to falls history. Cortical control of gait, specifically in the pre-frontal cortex (PFC) as measured by functional near infrared spectroscopy (fNIRS), during DTW in older adults has recently been studied. However, the automatic classification of differences in cognitive activations under single and dual task gait conditions has not been extensively studied yet. In this paper, we formulate this as a classification task and leverage deep learning to perform automatic classification of STW, DTW and single cognitive task (STA). We conduct analysis on the data samples which reveals the characteristics on the difference between HbO2 and Hb values that are subsequently used as additional features. We perform feature engineering to formulate the fNIRS features as a 3-channel image and apply various image processing techniques for data augmentation to enhance the performance of deep learning models. Experimental results show that pre-trained deep learning models that are fine-tuned using the collected fNIRS dataset together with gender and cognitive status information can achieve around 81\% classification accuracy which is about 10\% higher than the traditional machine learning algorithms. We further perform an ablation study to identify rankings of features such as the fNIRS levels and/or voxel locations on the contribution of the classification task.

arXiv:2102.03869공식 코드 · Papers with Code

Structured Sparsity Inducing Adaptive Optimizers for Deep Learning

The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance. To prune out unimportant groups of parameters, we can include some non-differentiable penalty to the objective function, and minimize it using proximal gradient methods. In this paper, we derive the weighted proximal operator, which is a necessary component of these proximal methods, of two structured sparsity inducing penalties. Moreover, they can be approximated efficiently with a numerical solver, and despite this approximation, we prove that existing convergence guarantees are preserved when these operators are integrated as part of a generic adaptive proximal method. Finally, we show that this adaptive method, together with the weighted proximal operators derived here, is indeed capable of finding solutions with structure in their sparsity patterns, on representative examples from computer vision and natural language processing.

arXiv:2102.04362공식 코드 · Papers with Code

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties. To the best of our knowledge, one of the prominent deep learning models - Generative Adversarial Networks (GANs) which has been widely used to create photorealistic image are totally unprotected despite the existence of pioneering IPR protection methodology for Convolutional Neural Networks (CNNs). This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. Empirically, we show that the proposed method does not compromise the original GANs performance (i.e. image generation, image super-resolution, style transfer), and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks.

arXiv:2102.04331

Soccer Event Detection Using Deep Learning

Event detection is an important step in extracting knowledge from the video. In this paper, we propose a deep learning approach to detect events in a soccer match emphasizing the distinction between images of red and yellow cards and the correct detection of the images of selected events from other images. This method includes the following three modules: i) the variational autoencoder (VAE) module to differentiate between soccer images and others image, ii) the image classification module to classify the images of events, and iii) the fine-grain image classification module to classify the images of red and yellow cards. Additionally, a new dataset was introduced for soccer images classification that is employed to train the networks mentioned in the paper. In the final section, 10 UEFA Champions League matches are used to evaluate the networks' performance and precision in detecting the events. The experiments demonstrate that the proposed method achieves better performance than state-of-the-art methods.

arXiv:2102.04297

Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise

The empirical success of deep learning is often attributed to SGD's mysterious ability to avoid sharp local minima in the loss landscape, as sharp minima are known to lead to poor generalization. Recently, empirical evidence of heavy-tailed gradient noise was reported in many deep learning tasks, and it was shown in \c{S}im\c{s}ekli (2019a,b) that SGD can escape sharp local minima under the presence of such heavy-tailed gradient noise, providing a partial solution to the mystery. In this work, we analyze a popular variant of SGD where gradients are truncated above a fixed threshold. We show that it achieves a stronger notion of avoiding sharp minima: it can effectively eliminate sharp local minima entirely from its training trajectory. We characterize the dynamics of truncated SGD driven by heavy-tailed noises. First, we show that the truncation threshold and width of the attraction field dictate the order of the first exit time from the associated local minimum. Moreover, when the objective function satisfies appropriate structural conditions, we prove that as the learning rate decreases, the dynamics of heavy-tailed truncated SGD closely resemble those of a continuous-time Markov chain that never visits any sharp minima. Real data experiments on deep learning confirm our theoretical prediction that heavy-tailed SGD with gradient clipping finds a "flatter" local minima and achieves better generalization.

arXiv:2102.03393공식 코드 · Papers with Code

MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning

Segmentation and analysis of individual pores and grains of mudrocks from scanning electron microscope images is non-trivial because of noise, imaging artifacts, variation in pixel grayscale values across images, and overlaps in grayscale values among different physical features such as silt grains, clay grains, and pores in an image, which make their identification difficult. Moreover, because grains and pores often have overlapping grayscale values, direct application of threshold-based segmentation techniques is not sufficient. Recent advances in the field of computer vision have made it easier and faster to segment images and identify multiple occurrences of such features in an image, provided that ground-truth data for training the algorithm is available. Here, we propose a deep learning SEM image segmentation model, MudrockNet based on Google's DeepLab-v3+ architecture implemented with the TensorFlow library. The ground-truth data was obtained from an image-processing workflow applied to scanning electron microscope images of uncemented muds from the Kumano Basin offshore Japan at depths < 1.1 km. The trained deep learning model obtained a pixel-accuracy about 90%, and predictions for the test data obtained a mean intersection over union (IoU) of 0.6591 for silt grains and 0.6642 for pores. We also compared our model with the random forest classifier using trainable Weka segmentation in ImageJ, and it was observed that MudrockNet gave better predictions for both silt grains and pores. The size, concentration, and spatial arrangement of the silt and clay grains can affect the petrophysical properties of a mudrock, and an automated method to accurately identify the different grains and pores in mudrocks can help improve reservoir and seal characterization for petroleum exploration and anthropogenic waste sequestration.