PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1905.10988

Natural Compression for Distributed Deep Learning

Modern deep learning models are often trained in parallel over a collection of distributed machines to reduce training time. In such settings, communication of model updates among machines becomes a significant performance bottleneck and various lossy update compression techniques have been proposed to alleviate this problem. In this work, we introduce a new, simple yet theoretically and practically effective compression technique: natural compression (NC). Our technique is applied individually to all entries of the to-be-compressed update vector and works by randomized rounding to the nearest (negative or positive) power of two, which can be computed in a "natural" way by ignoring the mantissa. We show that compared to no compression, NC increases the second moment of the compressed vector by not more than the tiny factor $\frac{9}{8}$, which means that the effect of NC on the convergence speed of popular training algorithms, such as distributed SGD, is negligible. However, the communications savings enabled by NC are substantial, leading to $3$-$4\times$ improvement in overall theoretical running time. For applications requiring more aggressive compression, we generalize NC to natural dithering, which we prove is exponentially better than the common random dithering technique. Our compression operators can be used on their own or in combination with existing operators for a more aggressive combined effect and offer new state-of-the-art both in theory and practice.

arXiv:1905.11248

Walsh-Hadamard Variational Inference for Bayesian Deep Learning

Over-parameterized models, such as DeepNets and ConvNets, form a class of models that are routinely adopted in a wide variety of applications, and for which Bayesian inference is desirable but extremely challenging. Variational inference offers the tools to tackle this challenge in a scalable way and with some degree of flexibility on the approximation, but for over-parameterized models this is challenging due to the over-regularization property of the variational objective. Inspired by the literature on kernel methods, and in particular on structured approximations of distributions of random matrices, this paper proposes Walsh-Hadamard Variational Inference (WHVI), which uses Walsh-Hadamard-based factorization strategies to reduce the parameterization and accelerate computations, thus avoiding over-regularization issues with the variational objective. Extensive theoretical and empirical analyses demonstrate that WHVI yields considerable speedups and model reductions compared to other techniques to carry out approximate inference for over-parameterized models, and ultimately show how advances in kernel methods can be translated into advances in approximate Bayesian inference.

arXiv:1905.11027

A Geometric Modeling of Occam's Razor in Deep Learning

Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs stunning performances in practice is all the more intriguing and not explainable using the standard theory of model selection for regular models. In this work, we propose a geometrically flavored information-theoretic approach to study this phenomenon. With the belief that simplicity is linked to better generalization, as grounded in the theory of minimum description length, the objective of our analysis is to examine and bound the complexity of DNNs. We introduce the locally varying dimensionality of the parameter space of neural network models by considering the number of significant dimensions of the Fisher information matrix, and model the parameter space as a manifold using the framework of singular semi-Riemannian geometry. We derive model complexity measures which yield short description lengths for deep neural network models based on their singularity analysis thus explaining the good performance of DNNs despite their large number of parameters.

arXiv:1905.09970

Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints

We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a least squares solution for the inverse 2D to 3D geometric mapping problem, using the camera projection matrix. The closed-form solution of the mathematical system, along with the initial output of the adapted Faster R-CNN are then passed through a final ShiftNet network that refines the result using our newly proposed Volume Displacement Loss. Our novel, geometrically constrained deep learning approach to monocular 3D object detection obtains top results on KITTI 3D Object Detection Benchmark, being the best among all monocular methods that do not use any pre-trained network for depth estimation.

arXiv:1905.09899

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this paper, by revisiting the design of Adagrad, we propose to split the network parameters into blocks, and use a blockwise adaptive stepsize. Intuitively, blockwise adaptivity is less aggressive than adaptivity to individual coordinates, and can have a better balance between adaptivity and generalization. We show theoretically that the proposed blockwise adaptive gradient descent has comparable convergence rate as its counterpart with coordinate-wise adaptive stepsize, but is faster up to some constant. We also study its uniform stability and show that blockwise adaptivity can lead to lower generalization error than coordinate-wise adaptivity. Experimental results show that blockwise adaptive gradient descent converges faster and improves generalization performance over Nesterov's accelerated gradient and Adam.

arXiv:1905.10328

Tiresias: Predicting Security Events Through Deep Learning

With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps that will be taken by an adversary when performing an attack. However this is still an open research problem, and previous research in predicting malicious events only looked at binary outcomes (e.g., whether an attack would happen or not), but not at the specific steps that an attacker would undertake. To fill this gap we present Tiresias, a system that leverages Recurrent Neural Networks (RNNs) to predict future events on a machine, based on previous observations. We test Tiresias on a dataset of 3.4 billion security events collected from a commercial intrusion prevention system, and show that our approach is effective in predicting the next event that will occur on a machine with a precision of up to 0.93. We also show that the models learned by Tiresias are reasonably stable over time, and provide a mechanism that can identify sudden drops in precision and trigger a retraining of the system. Finally, we show that the long-term memory typical of RNNs is key in performing event prediction, rendering simpler methods not up to the task.

arXiv:1905.10296공식 코드 · Papers with Code

Uncertainty Estimation in One-Stage Object Detection

Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques huge progress was made over the last years in this field. However such deep learning based object detection models cannot predict how certain they are in their predictions, potentially hampering the performance of later steps such as tracking or sensor fusion. We present a viable approaches to estimate uncertainty in an one-stage object detector, while improving the detection performance of the baseline approach. The proposed model is evaluated on a large scale automotive pedestrian dataset. Experimental results show that the uncertainty outputted by our system is coupled with detection accuracy and the occlusion level of pedestrians.

arXiv:1905.10231

A Comparison and Strategy of Semantic Segmentation on Remote Sensing Images

In recent years, with the development of aerospace technology, we use more and more images captured by satellites to obtain information. But a large number of useless raw images, limited data storage resource and poor transmission capability on satellites hinder our use of valuable images. Therefore, it is necessary to deploy an on-orbit semantic segmentation model to filter out useless images before data transmission. In this paper, we present a detailed comparison on the recent deep learning models. Considering the computing environment of satellites, we compare methods from accuracy, parameters and resource consumption on the same public dataset. And we also analyze the relation between them. Based on experimental results, we further propose a viable on-orbit semantic segmentation strategy. It will be deployed on the TianZhi-2 satellite which supports deep learning methods and will be lunched soon.

arXiv:1905.09591공식 코드 · Papers with Code

A Direct Approach to Robust Deep Learning Using Adversarial Networks

Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly sensitive to small perturbations imperceptible to humans. Carefully crafted input images (adversarial examples) can force a well-trained neural network to provide arbitrary outputs. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. In this paper we propose a new defensive mechanism under the generative adversarial network (GAN) framework. We model the adversarial noise using a generative network, trained jointly with a classification discriminative network as a minimax game. We show empirically that our adversarial network approach works well against black box attacks, with performance on par with state-of-art methods such as ensemble adversarial training and adversarial training with projected gradient descent.

arXiv:1905.09533

Incorporating Human Domain Knowledge in 3D LiDAR-based Semantic Segmentation

This work studies semantic segmentation using 3D LiDAR data. Popular deep learning methods applied for this task require a large number of manual annotations to train the parameters. We propose a new method that makes full use of the advantages of traditional methods and deep learning methods via incorporating human domain knowledge into the neural network model to reduce the demand for large numbers of manual annotations and improve the training efficiency. We first pretrain a model with autogenerated samples from a rule-based classifier so that human knowledge can be propagated into the network. Based on the pretrained model, only a small set of annotations is required for further fine-tuning. Quantitative experiments show that the pretrained model achieves better performance than random initialization in almost all cases; furthermore, our method can achieve similar performance with fewer manual annotations.

arXiv:1905.09509

Leveraging Uncertainty in Deep Learning for Selective Classification

The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the quantified uncertainty for each prediction. There have been recent efforts towards quantifying uncertainty in conventional deep learning methods (e.g., dropout as Bayesian approximation); however, their optimal use in decision making is often overlooked and understudied. In this study, we propose a mixed-integer programming framework for classification with reject option (also known as selective classification), that investigates and combines model uncertainty and predictive mean to identify optimal classification and rejection regions. Our results indicate superior performance of our framework both in non-rejected accuracy and rejection quality on several publicly available datasets. Moreover, we extend our framework to cost-sensitive settings and show that our approach outperforms industry standard methods significantly for online fraud management in real-world settings.

arXiv:1905.09201

Adaptive norms for deep learning with regularized Newton methods

We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks. This approach can be seen as a second-order counterpart of adaptive gradient methods, which we here show to be interpretable as first-order trust region methods with ellipsoidal constraints. In particular, we prove that the preconditioning matrix used in RMSProp and Adam satisfies the necessary conditions for provable convergence of second-order trust region methods with standard worst-case complexities on general non-convex objectives. Furthermore, we run experiments across different neural architectures and datasets to find that the ellipsoidal constraints constantly outperform their spherical counterpart both in terms of number of backpropagations and asymptotic loss value. Finally, we find comparable performance to state-of-the-art first-order methods in terms of backpropagations, but further advances in hardware are needed to render Newton methods competitive in terms of computational time.

arXiv:1905.09195

On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces

Deep learning has been applied to various tasks in the field of machine learning and has shown superiority to other common procedures such as kernel methods. To provide a better theoretical understanding of the reasons for its success, we discuss the performance of deep learning and other methods on a nonparametric regression problem with a Gaussian noise. Whereas existing theoretical studies of deep learning have been based mainly on mathematical theories of well-known function classes such as H\"{o}lder and Besov classes, we focus on function classes with discontinuity and sparsity, which are those naturally assumed in practice. To highlight the effectiveness of deep learning, we compare deep learning with a class of linear estimators representative of a class of shallow estimators. It is shown that the minimax risk of a linear estimator on the convex hull of a target function class does not differ from that of the original target function class. This results in the suboptimality of linear methods over a simple but non-convex function class, on which deep learning can attain nearly the minimax-optimal rate. In addition to this extreme case, we consider function classes with sparse wavelet coefficients. On these function classes, deep learning also attains the minimax rate up to log factors of the sample size, and linear methods are still suboptimal if the assumed sparsity is strong. We also point out that the parameter sharing of deep neural networks can remarkably reduce the complexity of the model in our setting.

arXiv:1905.08764

Performance Analysis of Deep Learning Workloads on Leading-edge Systems

This work examines the performance of leading-edge systems designed for machine learning computing, including the NVIDIA DGX-2, Amazon Web Services (AWS) P3, IBM Power System Accelerated Compute Server AC922, and a consumer-grade Exxact TensorEX TS4 GPU server. Representative deep learning workloads from the fields of computer vision and natural language processing are the focus of the analysis. Performance analysis is performed along with a number of important dimensions. Performance of the communication interconnects and large and high-throughput deep learning models are considered. Different potential use models for the systems as standalone and in the cloud also are examined. The effect of various optimization of the deep learning models and system configurations is included in the analysis.

arXiv:1905.08054공식 코드 · Papers with Code

Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi. We employ deep learning algorithms trained on received samples taken from a 10 MHz band in the 2.4 GHz ISM Band. We obtain a classification accuracy of around 89.5% using any of four different deep neural network architectures: CNN, ResNet, CLDNN, and LSTM, which demonstrate the generality of the effectiveness of deep learning at the considered task. Interestingly, our proposed CNN architecture requires approximately 60% of the training time required by the state of the art while achieving slightly larger classification accuracy. We then focus on the CNN architecture and further optimize its training time while incurring minimal loss in classification accuracy using three different approaches: 1- Band Selection, where we only use samples belonging to the lower and uppermost 2 MHz bands, 2- SNR Selection, where we only use training samples belonging to a single SNR value, and 3- Sample Selection, where we try various sub-Nyquist sampling methods to select the subset of samples most relevant to the classification task. Our results confirm the feasibility of fast deep learning for wireless interference identification, by showing that the training time can be reduced by as much as 30x with minimal loss in accuracy.

arXiv:1905.07726

Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces

Reconfigurable Intelligent Surfaces (RISs) comprised of tunable unit elements have been recently considered in indoor communication environments for focusing signal reflections to intended user locations. However, the current proofs of concept require complex operations for the RIS configuration, which are mainly realized via wired control connections. In this paper, we present a deep learning method for efficient online wireless configuration of RISs when deployed in indoor communication environments. According to the proposed method, a database of coordinate fingerprints is implemented during an offline training phase. This fingerprinting database is used to train the weights and bias of a properly designed Deep Neural Network (DNN), whose role is to unveil the mapping between the measured coordinate information at a user location and the configuration of the RIS's unit cells that maximizes this user's received signal strength. During the online phase of the presented method, the trained DNN is fed with the measured position information at the target user to output the optimal phase configurations of the RIS for signal power focusing on this intended location. Our realistic simulation results using ray tracing on a three dimensional indoor environment demonstrate that the proposed DNN-based configuration method exhibits its merits for all considered cases, and effectively increases the achievable throughput at the target user location.

arXiv:1905.08110

Image Captioning based on Deep Learning Methods: A Survey

Image captioning is a challenging task and attracting more and more attention in the field of Artificial Intelligence, and which can be applied to efficient image retrieval, intelligent blind guidance and human-computer interaction, etc. In this paper, we present a survey on advances in image captioning based on Deep Learning methods, including Encoder-Decoder structure, improved methods in Encoder, improved methods in Decoder, and other improvements. Furthermore, we discussed future research directions.

arXiv:1905.07923

Transmitter Classification With Supervised Deep Learning

Hardware imperfections in RF transmitters introduce features that can be used to identify a specific transmitter amongst others. Supervised deep learning has shown good performance in this task but using datasets not applicable to real world situations where topologies evolve over time. To remedy this, the work rests on a series of datasets gathered in the Future Internet of Things / Cognitive Radio Testbed [4] (FIT/CorteXlab) to train a convolutional neural network (CNN), where focus has been given to reduce channel bias that has plagued previous works and constrained them to a constant environment or to simulations. The most challenging scenarios provide the trained neural network with resilience and show insight on the best signal type to use for identification , namely packet preamble. The generated datasets are published on the Machine Learning For Communications Emerging Technologies Initiatives web site 4 in the hope that they serve as stepping stones for future progress in the area. The community is also invited to reproduce the studied scenarios and results by generating new datasets in FIT/CorteXlab.

arXiv:1905.07203

Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset

Annotated training data insufficiency remains to be one of the challenges of applying deep learning in medical data classification problems. Transfer learning from an already trained deep convolutional network can be used to reduce the cost of training from scratch and to train with small training data for deep learning. This raises the question of whether we can use transfer learning to overcome the training data insufficiency problem in deep learning based medical data classifications. Deep convolutional networks have been achieving high performance results on the ImageNet Large Scale Visual Recognition Competition (ILSVRC) image classification challenge. One example is the Inception-V3 model that was the first runner up on the ILSVRC 2015 challenge. Inception modules that help to extract different sized features of input images in one level of convolution are the unique features of the Inception-V3. In this work, we have used a pretrained Inception-V3 model to take advantage of its Inception modules for Diabetic Retinopathy detection. In order to tackle the labelled data insufficiency problem, we sub-sampled a smaller version of the Kaggle Diabetic Retinopathy classification challenge dataset for model training, and tested the model's accuracy on a previously unseen data subset. Our technique could be used in other deep learning based medical image classification problems facing the challenge of labeled training data insufficiency.

arXiv:1905.07187

An Essay on Optimization Mystery of Deep Learning

Despite the huge empirical success of deep learning, theoretical understanding of neural networks learning process is still lacking. This is the reason, why some of its features seem "mysterious". We emphasize two mysteries of deep learning: generalization mystery, and optimization mystery. In this essay we review and draw connections between several selected works concerning the latter.