PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1909.03459

Blind Geometric Distortion Correction on Images Through Deep Learning

We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction.

논문 ID: 2017.26903

Skeletonnet: Mining deep part features for 3-d action recognition

This letter presents SkeletonNet, a deep learning framework for skeleton-based 3-D action recognition. Given a skeleton sequence, the spatial structure of the skeleton joints in each frame and the temporal information between multiple frames are two important factors for action recognition. We first extract body-part-based features from each frame of the skeleton sequence. Compared to the original coordinates of the skeleton joints, the proposed features are translation, rotation, and scale invariant. To learn robust temporal information, instead of treating the features of all frames as a time series, we transform the features into images and feed them to the proposed deep learning network, which contains two parts: one to extract general features from the input images, while the other to generate a discriminative and compact representation for action recognition. The proposed method is tested on the SBU kinect interaction dataset, the CMU dataset, and the large-scale NTU RGB+D dataset and achieves state-of-the-art performance.

arXiv:1909.02803

Personalization of Deep Learning

We discuss training techniques, objectives and metrics toward personalization of deep learning models. In machine learning, personalization addresses the goal of a trained model to target a particular individual by optimizing one or more performance metrics, while conforming to certain constraints. To personalize, we investigate three methods of ``curriculum learning`` and two approaches for data grouping, i.e., augmenting the data of an individual by adding similar data identified with an auto-encoder. We show that both ``curriculuum learning'' and ``personalized'' data augmentation lead to improved performance on data of an individual. Mostly, this comes at the cost of reduced performance on a more general, broader dataset.

arXiv:1909.02625

On the Acceleration of Deep Learning Model Parallelism with Staleness

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward locking, backward locking, and update locking problems. Existing solutions for acceleration either can only handle one locking problem or lead to severe accuracy loss or memory inefficiency. Moreover, none of them consider the straggler problem among devices. In this paper, we propose Layer-wise Staleness and a novel efficient training algorithm, Diversely Stale Parameters (DSP), to address these challenges. We also analyze the convergence of DSP with two popular gradient-based methods and prove that both of them are guaranteed to converge to critical points for non-convex problems. Finally, extensive experimental results on training deep learning models demonstrate that our proposed DSP algorithm can achieve significant training speedup with stronger robustness than compared methods.

arXiv:1909.02437

ALIME: Autoencoder Based Approach for Local Interpretability

Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning. Nevertheless, deep learning models areopaque and often seen as black boxes. Thus, there is an inherent need tomake the models interpretable, especially so in the medical domain. Inthis work, we propose a locally interpretable method, which is inspiredby one of the recent tools that has gained a lot of interest, called localinterpretable model-agnostic explanations (LIME). LIME generates singleinstance level explanation by artificially generating a dataset aroundthe instance (by randomly sampling and using perturbations) and thentraining a local linear interpretable model. One of the major issues inLIME is the instability in the generated explanation, which is caused dueto the randomly generated dataset. Another issue in these kind of localinterpretable models is the local fidelity. We propose novel modificationsto LIME by employing an autoencoder, which serves as a better weightingfunction for the local model. We perform extensive comparisons withdifferent datasets and show that our proposed method results in bothimproved stability, as well as local fidelity.

arXiv:1909.01994

Quasi-Newton Optimization Methods For Deep Learning Applications

Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement learning (RL), are generally restricted to the class of first-order algorithms, like stochastic gradient descent (SGD). While SGD iterates are inexpensive to compute, they have slow theoretical convergence rates. Furthermore, they require exhaustive trial-and-error to fine-tune many learning parameters. Using second-order curvature information to find search directions can help with more robust convergence for non-convex optimization problems. However, computing Hessian matrices for large-scale problems is not computationally practical. Alternatively, quasi-Newton methods construct an approximate of the Hessian matrix to build a quadratic model of the objective function. Quasi-Newton methods, like SGD, require only first-order gradient information, but they can result in superlinear convergence, which makes them attractive alternatives to SGD. The limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) approach is one of the most popular quasi-Newton methods that construct positive definite Hessian approximations. In this chapter, we propose efficient optimization methods based on L-BFGS quasi-Newton methods using line search and trust-region strategies. Our methods bridge the disparity between first- and second-order methods by using gradient information to calculate low-rank updates to Hessian approximations. We provide formal convergence analysis of these methods as well as empirical results on deep learning applications, such as image classification tasks and deep reinforcement learning on a set of ATARI 2600 video games. Our results show a robust convergence with preferred generalization characteristics as well as fast training time.

arXiv:1909.01940

Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification

While deep learning models become more widespread, their ability to handle unseen data and generalize for any scenario is yet to be challenged. In medical imaging, there is a high heterogeneity of distributions among images based on the equipment that generates them and their parametrization. This heterogeneity triggers a common issue in machine learning called domain shift, which represents the difference between the training data distribution and the distribution of where a model is employed. A high domain shift tends to implicate in a poor generalization performance from the models. In this work, we evaluate the extent of domain shift on four of the largest datasets of chest radiographs. We show how training and testing with different datasets (e.g., training in ChestX-ray14 and testing in CheXpert) drastically affects model performance, posing a big question over the reliability of deep learning models trained on public datasets. We also show that models trained on CheXpert and MIMIC-CXR generalize better to other datasets.

arXiv:1909.01736공식 코드 · Papers with Code

Beyond Human-Level Accuracy: Computational Challenges in Deep Learning

Deep learning (DL) research yields accuracy and product improvements from both model architecture changes and scale: larger data sets and models, and more computation. For hardware design, it is difficult to predict DL model changes. However, recent prior work shows that as dataset sizes grow, DL model accuracy and model size grow predictably. This paper leverages the prior work to project the dataset and model size growth required to advance DL accuracy beyond human-level, to frontier targets defined by machine learning experts. Datasets will need to grow $33$--$971 \times$, while models will need to grow $6.6$--$456\times$ to achieve target accuracies. We further characterize and project the computational requirements to train these applications at scale. Our characterization reveals an important segmentation of DL training challenges for recurrent neural networks (RNNs) that contrasts with prior studies of deep convolutional networks. RNNs will have comparatively moderate operational intensities and very large memory footprint requirements. In contrast to emerging accelerator designs, large-scale RNN training characteristics suggest designs with significantly larger memory capacity and on-chip caches.

arXiv:1909.01606

Model Asset eXchange: Path to Ubiquitous Deep Learning Deployment

A recent trend observed in traditionally challenging fields such as computer vision and natural language processing has been the significant performance gains shown by deep learning (DL). In many different research fields, DL models have been evolving rapidly and become ubiquitous. Despite researchers' excitement, unfortunately, most software developers are not DL experts and oftentimes have a difficult time following the booming DL research outputs. As a result, it usually takes a significant amount of time for the latest superior DL models to prevail in industry. This issue is further exacerbated by the common use of sundry incompatible DL programming frameworks, such as Tensorflow, PyTorch, Theano, etc. To address this issue, we propose a system, called Model Asset Exchange (MAX), that avails developers of easy access to state-of-the-art DL models. Regardless of the underlying DL programming frameworks, it provides an open source Python library (called the MAX framework) that wraps DL models and unifies programming interfaces with our standardized RESTful APIs. These RESTful APIs enable developers to exploit the wrapped DL models for inference tasks without the need to fully understand different DL programming frameworks. Using MAX, we have wrapped and open-sourced more than 30 state-of-the-art DL models from various research fields, including computer vision, natural language processing and signal processing, etc. In the end, we selectively demonstrate two web applications that are built on top of MAX, as well as the process of adding a DL model to MAX.

arXiv:1909.01730공식 코드 · Papers with Code

Deep Convolutional Networks in System Identification

Recent developments within deep learning are relevant for nonlinear system identification problems. In this paper, we establish connections between the deep learning and the system identification communities. It has recently been shown that convolutional architectures are at least as capable as recurrent architectures when it comes to sequence modeling tasks. Inspired by these results we explore the explicit relationships between the recently proposed temporal convolutional network (TCN) and two classic system identification model structures; Volterra series and block-oriented models. We end the paper with an experimental study where we provide results on two real-world problems, the well-known Silverbox dataset and a newer dataset originating from ground vibration experiments on an F-16 fighter aircraft.

arXiv:1909.01683

Deep Learning-Aided Tabu Search Detection for Large MIMO Systems

In this study, we consider the application of deep learning (DL) to tabu search (TS) detection in large multiple-input multiple-output (MIMO) systems. First, we propose a deep neural network architecture for symbol detection, termed the fast-convergence sparsely connected detection network (FS-Net), which is obtained by optimizing the prior detection networks called DetNet and ScNet. Then, we propose the DL-aided TS algorithm, in which the initial solution is approximated by the proposed FS-Net. Furthermore, in this algorithm, an adaptive early termination algorithm and a modified searching process are performed based on the predicted approximation error, which is determined from the FS-Net-based initial solution, so that the optimal solution can be reached earlier. The simulation results show that the proposed algorithm achieves approximately 90% complexity reduction for a $32 \times 32$ MIMO system with QPSK with respect to the existing TS algorithms, while maintaining almost the same performance.

arXiv:1909.01127공식 코드 · Papers with Code

MRI Reconstruction Using Deep Bayesian Estimation

Purpose: To develop a deep learning-based Bayesian inference for MRI reconstruction. Methods: We modeled the MRI reconstruction problem with Bayes's theorem, following the recently proposed PixelCNN++ method. The image reconstruction from incomplete k-space measurement was obtained by maximizing the posterior possibility. A generative network was utilized as the image prior, which was computationally tractable, and the k-space data fidelity was enforced by using an equality constraint. The stochastic backpropagation was utilized to calculate the descent gradient in the process of maximum a posterior, and a projected subgradient method was used to impose the equality constraint. In contrast to the other deep learning reconstruction methods, the proposed one used the likelihood of prior as the training loss and the objective function in reconstruction to improve the image quality. Results: The proposed method showed an improved performance in preserving image details and reducing aliasing artifacts, compared with GRAPPA, $\ell_1$-ESPRiT, and MODL, a state-of-the-art deep learning reconstruction method. The proposed method generally achieved more than 5 dB peak signal-to-noise ratio improvement for compressed sensing and parallel imaging reconstructions compared with the other methods. Conclusion: The Bayesian inference significantly improved the reconstruction performance, compared with the conventional $\ell_1$-sparsity prior in compressed sensing reconstruction tasks. More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios.

arXiv:1909.01019

On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement

Many deep learning-based speech enhancement algorithms are designed to minimize the mean-square error (MSE) in some transform domain between a predicted and a target speech signal. However, optimizing for MSE does not necessarily guarantee high speech quality or intelligibility, which is the ultimate goal of many speech enhancement algorithms. Additionally, only little is known about the impact of the loss function on the emerging class of time-domain deep learning-based speech enhancement systems. We study how popular loss functions influence the performance of deep learning-based speech enhancement systems. First, we demonstrate that perceptually inspired loss functions might be advantageous if the receiver is the human auditory system. Furthermore, we show that the learning rate is a crucial design parameter even for adaptive gradient-based optimizers, which has been generally overlooked in the literature. Also, we found that waveform matching performance metrics must be used with caution as they in certain situations can fail completely. Finally, we show that a loss function based on scale-invariant signal-to-distortion ratio (SI-SDR) achieves good general performance across a range of popular speech enhancement evaluation metrics, which suggests that SI-SDR is a good candidate as a general-purpose loss function for speech enhancement systems.

arXiv:1908.01974

Omni SCADA Intrusion Detection Using Deep Learning Algorithms

We investigate deep learning based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks. Regarding the IDSs developed in this paper, a feedforward neural network (FNN) can detect temporally uncorrelated attacks at an {F$_{1}$} of {99.967${\pm}$0.005\%} but correlated attacks as low as {58${\pm}$2\%}. In contrast, long-short term memory (LSTM) detects correlated attacks at {99.56${\pm}$0.01\%} while uncorrelated attacks at {99.3${\pm}$0.1\%}. Combining LSTM and FNN through an ensemble approach further improves the IDS performance with {F$_{1}$} of {99.68${\pm}$0.04\%} regardless the temporal correlations among the data packets.

arXiv:1909.00337공식 코드 · Papers with Code

Neural Architecture Search for Joint Optimization of Predictive Power and Biological Knowledge

We report a neural architecture search framework, BioNAS, that is tailored for biomedical researchers to easily build, evaluate, and uncover novel knowledge from interpretable deep learning models. The introduction of knowledge dissimilarity functions in BioNAS enables the joint optimization of predictive power and biological knowledge through searching architectures in a model space. By optimizing the consistency with existing knowledge, we demonstrate that BioNAS optimal models reveal novel knowledge in both simulated data and in real data of functional genomics. BioNAS provides a useful tool for domain experts to inject their prior belief into automated machine learning and therefore making deep learning easily accessible to practitioners. BioNAS is available at https://github.com/zj-zhang/BioNAS-pub.

arXiv:1909.00311

Scalable Reinforcement-Learning-Based Neural Architecture Search for Cancer Deep Learning Research

Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power. Consequently, there is a growing need for the development of data-driven and, in particular, deep learning methods for various tasks such as cancer diagnosis, detection, prognosis, and prediction. Despite recent successes, however, designing high-performing deep learning models for nonimage and nontext cancer data is a time-consuming, trial-and-error, manual task that requires both cancer domain and deep learning expertise. To that end, we develop a reinforcement-learning-based neural architecture search to automate deep-learning-based predictive model development for a class of representative cancer data. We develop custom building blocks that allow domain experts to incorporate the cancer-data-specific characteristics. We show that our approach discovers deep neural network architectures that have significantly fewer trainable parameters, shorter training time, and accuracy similar to or higher than those of manually designed architectures. We study and demonstrate the scalability of our approach on up to 1,024 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.

arXiv:1909.00133

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

Substantial efforts have been devoted more recently to presenting various methods for object detection in optical remote sensing images. However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate. Moreover, most of the existing datasets have some shortcomings, for example, the numbers of images and object categories are small scale, and the image diversity and variations are insufficient. These limitations greatly affect the development of deep learning based object detection methods. In the paper, we provide a comprehensive review of the recent deep learning based object detection progress in both the computer vision and earth observation communities. Then, we propose a large-scale, publicly available benchmark for object DetectIon in Optical Remote sensing images, which we name as DIOR. The dataset contains 23463 images and 192472 instances, covering 20 object classes. The proposed DIOR dataset 1) is large-scale on the object categories, on the object instance number, and on the total image number; 2) has a large range of object size variations, not only in terms of spatial resolutions, but also in the aspect of inter- and intra-class size variability across objects; 3) holds big variations as the images are obtained with different imaging conditions, weathers, seasons, and image quality; and 4) has high inter-class similarity and intra-class diversity. The proposed benchmark can help the researchers to develop and validate their data-driven methods. Finally, we evaluate several state-of-the-art approaches on our DIOR dataset to establish a baseline for future research.

arXiv:1908.11848

Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning

Deep learning is a popular machine learning technique and has been applied to many real-world problems. However, training a deep neural network is very time-consuming, especially on big data. It has become difficult for a single machine to train a large model over large datasets. A popular solution is to distribute and parallelize the training process across multiple machines using the parameter server framework. In this paper, we present a distributed paradigm on the parameter server framework called Dynamic Stale Synchronous Parallel (DSSP) which improves the state-of-the-art Stale Synchronous Parallel (SSP) paradigm by dynamically determining the staleness threshold at the run time. Conventionally to run distributed training in SSP, the user needs to specify a particular staleness threshold as a hyper-parameter. However, a user does not usually know how to set the threshold and thus often finds a threshold value through trial and error, which is time-consuming. Based on workers' recent processing time, our approach DSSP adaptively adjusts the threshold per iteration at running time to reduce the waiting time of faster workers for synchronization of the globally shared parameters, and consequently increases the frequency of parameters updates (increases iteration throughput), which speedups the convergence rate. We compare DSSP with other paradigms such as Bulk Synchronous Parallel (BSP), Asynchronous Parallel (ASP), and SSP by running deep neural networks (DNN) models over GPU clusters in both homogeneous and heterogeneous environments. The results show that in a heterogeneous environment where the cluster consists of mixed models of GPUs, DSSP converges to a higher accuracy much earlier than SSP and BSP and performs similarly to ASP. In a homogeneous distributed cluster, DSSP has more stable and slightly better performance than SSP and ASP, and converges much faster than BSP.

arXiv:1908.11498

Predicting Consumer Default: A Deep Learning Approach

We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model is interpretable and is able to provide a score to a larger class of borrowers relative to standard credit scoring models while accurately tracking variations in systemic risk. We argue that these properties can provide valuable insights for the design of policies targeted at reducing consumer default and alleviating its burden on borrowers and lenders, as well as macroprudential regulation.

arXiv:1908.11486

Fast Scenario Reduction for Power Systems by Deep Learning

Scenario reduction is an important topic in stochastic programming problems. Due to the random behavior of load and renewable energy, stochastic programming becomes a useful technique to optimize power systems. Thus, scenario reduction gets more attentions in recent years. Many scenario reduction methods have been proposed to reduce the scenario set in a fast speed. However, the speed of scenario reduction is still very slow, in which it takes at least several seconds to several minutes to finish the reduction. This limitation of speed prevents stochastic programming to be implemented in real-time optimal control problems. In this paper, a fast scenario reduction method based on deep learning is proposed to solve this problem. Inspired by the deep learning based image process, recognition and generation methods, the scenario data are transformed into a 2D image-like data and then to be fed into a deep convolutional neural network (DCNN). The output of the DCNN will be an "image" of the reduced scenario set. Since images can be processed in a very high speed by neural networks, the scenario reduction by neural network can also be very fast. The results of the simulation show that the scenario reduction with the proposed DCNN method can be completed in very high speed.