PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1912.03735

Security of Deep Learning Methodologies: Challenges and Opportunities

Despite the plethora of studies about security vulnerabilities and defenses of deep learning models, security aspects of deep learning methodologies, such as transfer learning, have been rarely studied. In this article, we highlight the security challenges and research opportunities of these methodologies, focusing on vulnerabilities and attacks unique to them.

arXiv:1912.03700

Deep Learning-based Hybrid Graph-Coloring Algorithm for Register Allocation

Register allocation, which is a crucial phase of a good optimizing compiler, relies on graph coloring. Hence, an efficient graph coloring algorithm is of paramount importance. In this work we try to learn a good heuristic for coloring interference graphs that are used in the register allocation phase. We aim to handle moderate sized interference graphs which have 100 nodes or less. For such graphs we can get the optimal allocation of colors to the nodes. Such optimal coloring is then used to train our Deep Learning network which is based on several layers of LSTM that output a color for each node of the graph. However, the current network may allocate the same color to the nodes connected by an edge resulting in an invalid coloring of the interference graph. Since it is difficult to encode constraints in an LSTM to avoid invalid coloring, we augment our deep learning network with a color correction phase that runs after the colors have been allocated by the network. Thus, our algorithm is hybrid in nature consisting of a mix of a deep learning algorithm followed by a more traditional correction phase. We have trained our network using several thousand random graphs of varying sparsity. On application of our hybrid algorithm to various popular graphs found in literature we see that our algorithm does very well when compared to the optimal coloring of these graphs. We have also run our algorithm against LLVMs popular greedy register allocator for several SPEC CPU 2017 benchmarks and notice that the hybrid algorithm performs on par or better than such a well-tuned allocator for most of these benchmarks.

arXiv:1912.03685

SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery

Renewable energy such as solar power is critical to fight the ever more serious climate change. China is the world leading installer of solar panel and numerous solar power plants were built. In this paper, we proposed a deep learning framework named SolarNet which is designed to perform semantic segmentation on large scale satellite imagery data to detect solar farms. SolarNet has successfully mapped 439 solar farms in China, covering near 2000 square kilometers, equivalent to the size of whole Shenzhen city or two and a half of New York city. To the best of our knowledge, it is the first time that we used deep learning to reveal the locations and sizes of solar farms in China, which could provide insights for solar power companies, market analysts and the government.

arXiv:1912.03673공식 코드 · Papers with Code

Detection of False Positive and False Negative Samples in Semantic Segmentation

In recent years, deep learning methods have outperformed other methods in image recognition. This has fostered imagination of potential application of deep learning technology including safety relevant applications like the interpretation of medical images or autonomous driving. The passage from assistance of a human decision maker to ever more automated systems however increases the need to properly handle the failure modes of deep learning modules. In this contribution, we review a set of techniques for the self-monitoring of machine-learning algorithms based on uncertainty quantification. In particular, we apply this to the task of semantic segmentation, where the machine learning algorithm decomposes an image according to semantic categories. We discuss false positive and false negative error modes at instance-level and review techniques for the detection of such errors that have been recently proposed by the authors. We also give an outlook on future research directions.

arXiv:1912.03980

Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems

We present a Bayesian machine learning architecture that combines a physically motivated parametrization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals. This combination yields an interpretable and differentiable generative model, allows the incorporation of prior knowledge, and can be utilized for observations with different data quality without having to retrain the deep network. We demonstrate our approach with an example of astronomical source separation in current imaging data, yielding a physical and interpretable model of astronomical scenes.

arXiv:1912.02911

Deep learning with noisy labels: exploring techniques and remedies in medical image analysis

Supervised training of deep learning models requires large labeled datasets. There is a growing interest in obtaining such datasets for medical image analysis applications. However, the impact of label noise has not received sufficient attention. Recent studies have shown that label noise can significantly impact the performance of deep learning models in many machine learning and computer vision applications. This is especially concerning for medical applications, where datasets are typically small, labeling requires domain expertise and suffers from high inter- and intra-observer variability, and erroneous predictions may influence decisions that directly impact human health. In this paper, we first review the state-of-the-art in handling label noise in deep learning. Then, we review studies that have dealt with label noise in deep learning for medical image analysis. Our review shows that recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image analysis community. To help achieve a better understanding of the extent of the problem and its potential remedies, we conducted experiments with three medical imaging datasets with different types of label noise, where we investigated several existing strategies and developed new methods to combat the negative effect of label noise. Based on the results of these experiments and our review of the literature, we have made recommendations on methods that can be used to alleviate the effects of different types of label noise on deep models trained for medical image analysis. We hope that this article helps the medical image analysis researchers and developers in choosing and devising new techniques that effectively handle label noise in deep learning.

arXiv:1912.03280

Recent advances in deep learning applied to skin cancer detection

Skin cancer is a major public health problem around the world. Its early detection is very important to increase patient prognostics. However, the lack of qualified professionals and medical instruments are significant issues in this field. In this context, over the past few years, deep learning models applied to automated skin cancer detection have become a trend. In this paper, we present an overview of the recent advances reported in this field as well as a discussion about the challenges and opportunities for improvement in the current models. In addition, we also present some important aspects regarding the use of these models in smartphones and indicate future directions we believe the field will take.

arXiv:1912.03221

Tree bark re-identification using a deep-learning feature descriptor

The ability to visually re-identify objects is a fundamental capability in vision systems. Oftentimes, it relies on collections of visual signatures based on descriptors, such as SIFT or SURF. However, these traditional descriptors were designed for a certain domain of surface appearances and geometries (limited relief). Consequently, highly-textured surfaces such as tree bark pose a challenge to them. In turn, this makes it more difficult to use trees as identifiable landmarks for navigational purposes (robotics) or to track felled lumber along a supply chain (logistics). We thus propose to use data-driven descriptors trained on bark images for tree surface re-identification. To this effect, we collected a large dataset containing 2,400 bark images with strong illumination changes, annotated by surface and with the ability to pixel-align them. We used this dataset to sample from more than 2 million 64x64 pixel patches to train our novel local descriptors DeepBark and SqueezeBark. Our DeepBark method has shown a clear advantage against the hand-crafted descriptors SIFT and SURF. For instance, we demonstrated that DeepBark can reach a mAP of 87.2% when retrieving 11 relevant bark images, i.e. corresponding to the same physical surface, to a bark query against 7,900 images. Our work thus suggests that re-identifying tree surfaces in a challenging illuminations context is possible. We also make public our dataset, which can be used to benchmark surface re-identification techniques.

arXiv:1912.03216

Modeling the Chlorophyll-a from Sea Surface Reflectance in West Africa by Deep Learning Methods: A Comparison of Multiple Algorithms

Deep learning provide successful applications in many fields. Recently, machines learning are involved for oceans remote sensing applications. In this study, we use and compare about eight (8) deep learning estimators for retrieval of a mainly pigment of phytoplankton. Depending on the water case and the multiple instruments simultaneouslyobserving the earth on a variety of platforms, several algorithm are used to estimate the chlolophyll-a from marine reflectance. By using a long-term multi-sensor time-series of satellite ocean-colour data, as MODIS, SeaWifs, VIIRS, MERIS, etc, we make a unique deep network model able to establish a relationship between sea surface reflectance and chlorophyll-a from any measurement satellite sensor over West Africa. These data fusion take into account the bias between case water and instruments. We construct several chlorophyll-a concentration prediction deep learning based models, compare them and therefore use the best for our study. Results obtained for accuracy training and test are quite good. The mean absolute error are very low and vary between 0,07 to 0,13 mg/m3.

arXiv:1912.03041

Integrating Deep Learning with Logic Fusion for Information Extraction

Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However, most of them fail to associate the complex relationships inherent in the task itself, which has proven to be especially crucial. For example, the relation between 2 entities is highly dependent on their entity types. These dependencies can be regarded as complex constraints that can be efficiently expressed as logical rules. To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner. The integrated framework is able to enhance neural outputs with knowledge regularization via logic rules, and at the same time update the weights of logic rules to comply with the characteristics of the training data. We demonstrate the effectiveness and generalization of the proposed model on multiple IE tasks.

arXiv:1912.03026

Data Augmentation for Deep Learning-based Radio Modulation Classification

Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-of-the-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning algorithm. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and shorter the classification response time.

arXiv:1912.02523

Towards Explainable Deep Neural Networks (xDNN)

In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers a clearly explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds). The proposed approach, xDNN is using prototypes. Prototypes are actual training data samples (images), which are local peaks of the empirical data distribution called typicality as well as of the data density. This generative model is identified in a closed form and equates to the pdf but is derived automatically and entirely from the training data with no user- or problem-specific thresholds, parameters or intervention. The proposed xDNN offers a new deep learning architecture that combines reasoning and learning in a synergy. It is non-iterative and non-parametric, which explains its efficiency in terms of time and computational resources. From the user perspective, the proposed approach is clearly understandable to human users. We tested it on some well-known benchmark data sets such as iRoads and Caltech-256. xDNN outperforms the other methods including deep learning in terms of accuracy, time to train and offers a clearly explainable classifier. In fact, the result on the very hard Caltech-256 problem (which has 257 classes) represents a world record.

arXiv:1912.01842공식 코드 · Papers with Code

Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics

The most popular face recognition benchmarks assume a distribution of subjects without much attention to their demographic attributes. In this work, we perform a comprehensive discrimination-aware experimentation of deep learning-based face recognition. The main aim of this study is focused on a better understanding of the feature space generated by deep models, and the performance achieved over different demographic groups. We also propose a general formulation of algorithmic discrimination with application to face biometrics. The experiments are conducted over the new DiveFace database composed of 24K identities from six different demographic groups. Two popular face recognition models are considered in the experimental framework: ResNet-50 and VGG-Face. We experimentally show that demographic groups highly represented in popular face databases have led to popular pre-trained deep face models presenting strong algorithmic discrimination. That discrimination can be observed both qualitatively at the feature space of the deep models and quantitatively in large performance differences when applying those models in different demographic groups, e.g. for face biometrics.

arXiv:1912.01816

Handwriting-Based Gender Classification Using End-to-End Deep Neural Networks

Handwriting-based gender classification is a well-researched problem that has been approached mainly by traditional machine learning techniques. In this paper, we propose a novel deep learning-based approach for this task. Specifically, we present a convolutional neural network (CNN), which performs automatic feature extraction from a given handwritten image, followed by classification of the writer's gender. Also, we introduce a new dataset of labeled handwritten samples, in Hebrew and English, of 405 participants. Comparing the gender classification accuracy on this dataset against human examiners, our results show that the proposed deep learning-based approach is substantially more accurate than that of humans.

arXiv:1912.01703공식 코드 · Papers with Code

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.

arXiv:1912.01412

Deep Learning for Symbolic Mathematics

Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.

arXiv:1912.01385

TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking

The usage of neural network models puts multiple objectives in conflict with each other: Ideally we would like to create a neural model that is effective, efficient, and interpretable at the same time. However, in most instances we have to choose which property is most important to us. We used the opportunity of the TREC 2019 Deep Learning track to evaluate the effectiveness of a balanced neural re-ranking approach. We submitted results of the TK (Transformer-Kernel) model: a neural re-ranking model for ad-hoc search using an efficient contextualization mechanism. TK employs a very small number of lightweight Transformer layers to contextualize query and document word embeddings. To score individual term interactions, we use a document-length enhanced kernel-pooling, which enables users to gain insight into the model. Our best result for the passage ranking task is: 0.420 MAP, 0.671 nDCG, 0.598 P@10 (TUW19-p3 full). Our best result for the document ranking task is: 0.271 MAP, 0.465 nDCG, 0.730 P@10 (TUW19-d3 re-ranking).

arXiv:1912.01144

Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations

We present a deep learning method for single-station earthquake location, which we approach as a regression problem using two separate Bayesian neural networks. We use a multi-task temporal-convolutional neural network to learn epicentral distance and P travel time from 1-minute seismograms. The network estimates epicentral distance and P travel time with absolute mean errors of 0.23 km and 0.03 s respectively, along with their epistemic and aleatory uncertainties. We design a separate multi-input network using standard convolutional layers to estimate the back-azimuth angle, and its epistemic uncertainty. This network estimates the direction from which seismic waves arrive to the station with a mean error of 1 degree. Using this information, we estimate the epicenter, origin time, and depth along with their confidence intervals. We use a global dataset of earthquake signals recorded within 1 degree (~112 km) from the event to build the model and to demonstrate its performance. Our model can predict epicenter, origin time, and depth with mean errors of 7.3 km, 0.4 second, and 6.7 km respectively, at different locations around the world. Our approach can be used for fast earthquake source characterization with a limited number of observations, and also for estimating location of earthquakes that are sparsely recorded -- either because they are small or because stations are widely separated.

arXiv:1912.01277

Make Thunderbolts Less Frightening -- Predicting Extreme Weather Using Deep Learning

Forecasting severe weather conditions is still a very challenging and computationally expensive task due to the enormous amount of data and the complexity of the underlying physics. Machine learning approaches and especially deep learning have however shown huge improvements in many research areas dealing with large datasets in recent years. In this work, we tackle one specific sub-problem of weather forecasting, namely the prediction of thunderstorms and lightning. We propose the use of a convolutional neural network architecture inspired by UNet++ and ResNet to predict thunderstorms as a binary classification problem based on satellite images and lightnings recorded in the past. We achieve a probability of detection of more than 94% for lightnings within the next 15 minutes while at the same time minimizing the false alarm ratio compared to previous approaches.

arXiv:1912.01198

Towards Understanding the Spectral Bias of Deep Learning

An intriguing phenomenon observed during training neural networks is the spectral bias, which states that neural networks are biased towards learning less complex functions. The priority of learning functions with low complexity might be at the core of explaining generalization ability of neural network, and certain efforts have been made to provide theoretical explanation for spectral bias. However, there is still no satisfying theoretical result justifying the underlying mechanism of spectral bias. In this paper, we give a comprehensive and rigorous explanation for spectral bias and relate it with the neural tangent kernel function proposed in recent work. We prove that the training process of neural networks can be decomposed along different directions defined by the eigenfunctions of the neural tangent kernel, where each direction has its own convergence rate and the rate is determined by the corresponding eigenvalue. We then provide a case study when the input data is uniformly distributed over the unit sphere, and show that lower degree spherical harmonics are easier to be learned by over-parameterized neural networks. Finally, we provide numerical experiments to demonstrate the correctness of our theory. Our experimental results also show that our theory can tolerate certain model misspecification in terms of the input data distribution.