PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2006.13046

Rotation Invariant Deep CBIR

Introduction of Convolutional Neural Networks has improved results on almost every image-based problem and Content-Based Image Retrieval is not an exception. But the CNN features, being rotation invariant, creates problems to build a rotation-invariant CBIR system. Though rotation-invariant features can be hand-engineered, the retrieval accuracy is very low because by hand engineering only low-level features can be created, unlike deep learning models that create high-level features along with low-level features. This paper shows a novel method to build a rotational invariant CBIR system by introducing a deep learning orientation angle detection model along with the CBIR feature extraction model. This paper also highlights that this rotation invariant deep CBIR can retrieve images from a large dataset in real-time.

arXiv:2006.12567공식 코드 · Papers with Code

A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence

Deep learning based localization and mapping has recently attracted significant attention. Instead of creating hand-designed algorithms through exploitation of physical models or geometric theories, deep learning based solutions provide an alternative to solve the problem in a data-driven way. Benefiting from ever-increasing volumes of data and computational power, these methods are fast evolving into a new area that offers accurate and robust systems to track motion and estimate scenes and their structure for real-world applications. In this work, we provide a comprehensive survey, and propose a new taxonomy for localization and mapping using deep learning. We also discuss the limitations of current models, and indicate possible future directions. A wide range of topics are covered, from learning odometry estimation, mapping, to global localization and simultaneous localization and mapping (SLAM). We revisit the problem of perceiving self-motion and scene understanding with on-board sensors, and show how to solve it by integrating these modules into a prospective spatial machine intelligence system (SMIS). It is our hope that this work can connect emerging works from robotics, computer vision and machine learning communities, and serve as a guide for future researchers to apply deep learning to tackle localization and mapping problems.

arXiv:2006.12878공식 코드 · Papers with Code

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.

arXiv:2006.12698

Security and Privacy Preserving Deep Learning

Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data collection required for deep learning presents obvious privacy issues. Users personal, highly sensitive data such as photos and voice recordings are kept indefinitely by the companies that collect it. Users can neither delete it nor restrict the purposes for which it is used. So, data privacy has been a very important concern for governments and companies these days. It gives rise to a very interesting challenge since on the one hand, we are pushing further and further for high-quality models and accessible data, but on the other hand, we need to keep data safe from both intentional and accidental leakage. The more personal the data is it is more restricted it means some of the most important social issues cannot be addressed using machine learning because researchers do not have access to proper training data. But by learning how to machine learning that protects privacy we can make a huge difference in solving many social issues like curing disease etc. Deep neural networks are susceptible to various inference attacks as they remember information about their training data. In this chapter, we introduce differential privacy, which ensures that different kinds of statistical analyses dont compromise privacy and federated learning, training a machine learning model on a data to which we do not have access to.

arXiv:2006.12621공식 코드 · Papers with Code

Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning

Deep neural networks (DNNs) are increasingly used in real-world applications (e.g. facial recognition). This has resulted in concerns about the fairness of decisions made by these models. Various notions and measures of fairness have been proposed to ensure that a decision-making system does not disproportionately harm (or benefit) particular subgroups of the population. In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks. We argue that in some cases, it may be easier for an attacker to target a particular subgroup, resulting in a form of \textit{robustness bias}. We show that measuring robustness bias is a challenging task for DNNs and propose two methods to measure this form of bias. We then conduct an empirical study on state-of-the-art neural networks on commonly used real-world datasets such as CIFAR-10, CIFAR-100, Adience, and UTKFace and show that in almost all cases there are subgroups (in some cases based on sensitive attributes like race, gender, etc) which are less robust and are thus at a disadvantage. We argue that this kind of bias arises due to both the data distribution and the highly complex nature of the learned decision boundary in the case of DNNs, thus making mitigation of such biases a non-trivial task. Our results show that robustness bias is an important criterion to consider while auditing real-world systems that rely on DNNs for decision making. Code to reproduce all our results can be found here: \url{https://github.com/nvedant07/Fairness-Through-Robustness}

arXiv:2006.12379

Deep Learning feature selection to unhide demographic recommender systems factors

Extracting demographic features from hidden factors is an innovative concept that provides multiple and relevant applications. The matrix factorization model generates factors which do not incorporate semantic knowledge. This paper provides a deep learning-based method: DeepUnHide, able to extract demographic information from the users and items factors in collaborative filtering recommender systems. The core of the proposed method is the gradient-based localization used in the image processing literature to highlight the representative areas of each classification class. Validation experiments make use of two public datasets and current baselines. Results show the superiority of DeepUnHide to make feature selection and demographic classification, compared to the state of art of feature selection methods. Relevant and direct applications include recommendations explanation, fairness in collaborative filtering and recommendation to groups of users.

arXiv:2006.11287공식 코드 · Papers with Code

Discovering Symbolic Models from Deep Learning with Inductive Biases

We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations. We find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.

arXiv:2006.11586공식 코드 · Papers with Code

AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss

Classical and some deep learning techniques for Arabic text classification often depend on complex morphological analysis, word segmentation, and hand-crafted feature engineering. These could be eliminated by using character-level features. We propose a novel end-to-end Arabic document classification framework, Arabic document image-based classifier (AraDIC), inspired by the work on image-based character embeddings. AraDIC consists of an image-based character encoder and a classifier. They are trained in an end-to-end fashion using the class balanced loss to deal with the long-tailed data distribution problem. To evaluate the effectiveness of AraDIC, we created and published two datasets, the Arabic Wikipedia title (AWT) dataset and the Arabic poetry (AraP) dataset. To the best of our knowledge, this is the first image-based character embedding framework addressing the problem of Arabic text classification. We also present the first deep learning-based text classifier widely evaluated on modern standard Arabic, colloquial Arabic and classical Arabic. AraDIC shows performance improvement over classical and deep learning baselines by 12.29% and 23.05% for the micro and macro F-score, respectively.

arXiv:2006.11569

Weakly-correlated synapses promote dimension reduction in deep neural networks

By controlling synaptic and neural correlations, deep learning has achieved empirical successes in improving classification performances. How synaptic correlations affect neural correlations to produce disentangled hidden representations remains elusive. Here we propose a simplified model of dimension reduction, taking into account pairwise correlations among synapses, to reveal the mechanism underlying how the synaptic correlations affect dimension reduction. Our theory determines the synaptic-correlation scaling form requiring only mathematical self-consistency, for both binary and continuous synapses. The theory also predicts that weakly-correlated synapses encourage dimension reduction compared to their orthogonal counterparts. In addition, these synapses slow down the decorrelation process along the network depth. These two computational roles are explained by the proposed mean-field equation. The theoretical predictions are in excellent agreement with numerical simulations, and the key features are also captured by a deep learning with Hebbian rules.

arXiv:2006.12004공식 코드 · Papers with Code

MaskIt: Masking for efficient utilization of incomplete public datasets for training deep learning models

A major challenge in training deep learning models is the lack of high quality and complete datasets. In the paper, we present a masking approach for training deep learning models from a publicly available but incomplete dataset. For example, city of Hamburg, Germany maintains a list of trees along the roads, but this dataset does not contain any information about trees in private homes and parks. To train a deep learning model on such a dataset, we mask the street trees and aerial images with the road network. Road network used for creating the mask is downloaded from OpenStreetMap, and it marks the area where the training data is available. The mask is passed to the model as one of the inputs and it also coats the output. Our model learns to successfully predict trees only in the masked region with 78.4% accuracy.

arXiv:2006.11767

Patch Based Classification of Remote Sensing Data: A Comparison of 2D-CNN, SVM and NN Classifiers

Pixel based algorithms including back propagation neural networks (NN) and support vector machines (SVM) have been widely used for remotely sensed image classifications. Within last few years, deep learning based image classifier like convolution neural networks (2D-CNN) are becoming popular alternatives to these classifiers. In this paper, we compare performance of patch based SVM and NN with that of a deep learning algorithms comprising of 2D-CNN and fully connected layers. Similar to CNN which utilise image patches to derive features for further classification, we propose to use patches as an input in place of individual pixel with both SVM and NN classifiers. Two datasets, one multispectral and other hyperspectral data was used to compare the performance of different classifiers. Results with both datasets suggest the effectiveness of patch based SVM and NN classifiers in comparison to state of art 2D-CNN classifier.

arXiv:2006.12138공식 코드 · Papers with Code

Graph Neural Networks in TensorFlow and Keras with Spektral

In this paper we present Spektral, an open-source Python library for building graph neural networks with TensorFlow and the Keras application programming interface. Spektral implements a large set of methods for deep learning on graphs, including message-passing and pooling operators, as well as utilities for processing graphs and loading popular benchmark datasets. The purpose of this library is to provide the essential building blocks for creating graph neural networks, focusing on the guiding principles of user-friendliness and quick prototyping on which Keras is based. Spektral is, therefore, suitable for absolute beginners and expert deep learning practitioners alike. In this work, we present an overview of Spektral's features and report the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression.

arXiv:2006.10971

A Deep Learning Framework for Hybrid Beamforming Without Instantaneous CSI Feedback

Hybrid beamformer design plays very crucial role in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output) systems. Previous works assume the perfect channel state information (CSI) which results heavy feedback overhead. To lower complexity, channel statistics can be utilized such that only infrequent update of the channel information is needed. To reduce the complexity and provide robustness, in this work, we propose a deep learning (DL) framework to deal with both hybrid beamforming and channel estimation. For this purpose, we introduce three deep convolutional neural network (CNN) architectures. We assume that the base station (BS) has the channel statistics only and feeds the channel covariance matrix into a CNN to obtain the hybrid precoders. At the receiver, two CNNs are employed. The first one is used for channel estimation purposes and the another is employed to design the hybrid combiners. The proposed DL framework does not require the instantaneous feedback of the CSI at the BS. We have shown that the proposed approach has higher spectral efficiency with comparison to the conventional techniques. The trained CNN structures do not need to be re-trained due to the changes in the propagation environment such as the deviations in the number of received paths and the fluctuations in the received path angles up to 4 degrees. Also, the proposed DL framework exhibits at least 10 times lower computational complexity as compared to the conventional optimization-based approaches.

arXiv:2006.10901공식 코드 · Papers with Code

Sparse GPU Kernels for Deep Learning

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because these applications have relatively moderate levels of sparsity that are not sufficient for existing sparse kernels to outperform their dense counterparts. In this work, we study sparse matrices from deep learning applications and identify favorable properties that can be exploited to accelerate computation. Based on these insights, we develop high-performance GPU kernels for two sparse matrix operations widely applicable in neural networks: sparse matrix-dense matrix multiplication and sampled dense-dense matrix multiplication. Our kernels reach 27% of single-precision peak on Nvidia V100 GPUs. Using our kernels, we demonstrate sparse Transformer and MobileNet models that achieve 1.2-2.1x speedups and up to 12.8x memory savings without sacrificing accuracy.

arXiv:2006.10869

Model-Aware Regularization For Learning Approaches To Inverse Problems

There are various inverse problems -- including reconstruction problems arising in medical imaging -- where one is often aware of the forward operator that maps variables of interest to the observations. It is therefore natural to ask whether such knowledge of the forward operator can be exploited in deep learning approaches increasingly used to solve inverse problems. In this paper, we provide one such way via an analysis of the generalisation error of deep learning methods applicable to inverse problems. In particular, by building on the algorithmic robustness framework, we offer a generalisation error bound that encapsulates key ingredients associated with the learning problem such as the complexity of the data space, the size of the training set, the Jacobian of the deep neural network and the Jacobian of the composition of the forward operator with the neural network. We then propose a 'plug-and-play' regulariser that leverages the knowledge of the forward map to improve the generalization of the network. We likewise also propose a new method allowing us to tightly upper bound the Lipschitz constants of the relevant functions that is much more computational efficient than existing ones. We demonstrate the efficacy of our model-aware regularised deep learning algorithms against other state-of-the-art approaches on inverse problems involving various sub-sampling operators such as those used in classical compressed sensing setup and accelerated Magnetic Resonance Imaging (MRI).

arXiv:2006.11091

Deep Learning-based Single Image Face Depth Data Enhancement

Face recognition can benefit from the utilization of depth data captured using low-cost cameras, in particular for presentation attack detection purposes. Depth video output from these capture devices can however contain defects such as holes or general depth inaccuracies. This work proposes a deep learning face depth enhancement method in this context of facial biometrics, which adds a security aspect to the topic. U-Net-like architectures are utilized, and the networks are compared against hand-crafted enhancer types, as well as a similar depth enhancer network from related work trained for an adjacent application scenario. All tested enhancer types exclusively use depth data as input, which differs from methods that enhance depth based on additional input data such as visible light color images. Synthetic face depth ground truth images and degraded forms thereof are created with help of PRNet, to train multiple deep learning enhancer models with different network sizes and training configurations. Evaluations are carried out on the synthetic data, on Kinect v1 images from the KinectFaceDB, and on in-house RealSense D435 images. These evaluations include an assessment of the falsification for occluded face depth input, which is relevant to biometric security. The proposed deep learning enhancers yield noticeably better results than the tested preexisting enhancers, without overly falsifying depth data when non-face input is provided, and are shown to reduce the error of a simple landmark-based PAD method.

arXiv:2006.11236

Using Deep Learning to Predict Beam-Tunable Pareto Optimal Dose Distribution for Intensity Modulated Radiation Therapy

We propose to develop deep learning models that can predict Pareto optimal dose distributions by using any given set of beam angles, along with patient anatomy, as input to train the deep neural networks. We implement and compare two deep learning networks that predict with two different beam configuration modalities. We generated Pareto optimal plans for 70 patients with prostate cancer. We used fluence map optimization to generate 500 IMRT plans that sampled the Pareto surface for each patient, for a total of 35,000 plans. We studied and compared two different models, Model I and Model II. Model I directly uses beam angles as a second input to the network as a binary vector. Model II converts the beam angles into beam doses that are conformal to the PTV. Our deep learning models predicted voxel-level dose distributions that precisely matched the ground truth dose distributions. Quantitatively, Model I prediction error of 0.043 (confirmation), 0.043 (homogeneity), 0.327 (R50), 2.80% (D95), 3.90% (D98), 0.6% (D50), 1.10% (D2) was lower than that of Model II, which obtained 0.076 (confirmation), 0.058 (homogeneity), 0.626 (R50), 7.10% (D95), 6.50% (D98), 8.40% (D50), 6.30% (D2). Treatment planners who use our models will be able to use deep learning to control the tradeoffs between the PTV and OAR weights, as well as the beam number and configurations in real time. Our dose prediction methods provide a stepping stone to building automatic IMRT treatment planning.

arXiv:2006.10560

Gradient Amplification: An efficient way to train deep neural networks

Improving performance of deep learning models and reducing their training times are ongoing challenges in deep neural networks. There are several approaches proposed to address these challenges one of which is to increase the depth of the neural networks. Such deeper networks not only increase training times, but also suffer from vanishing gradients problem while training. In this work, we propose gradient amplification approach for training deep learning models to prevent vanishing gradients and also develop a training strategy to enable or disable gradient amplification method across several epochs with different learning rates. We perform experiments on VGG-19 and resnet (Resnet-18 and Resnet-34) models, and study the impact of amplification parameters on these models in detail. Our proposed approach improves performance of these deep learning models even at higher learning rates, thereby allowing these models to achieve higher performance with reduced training time.

arXiv:2006.10521공식 코드 · Papers with Code

LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection

The prevalence of location-based services contributes to the explosive growth of individual-level trajectory data and raises public concerns about privacy issues. In this research, we propose a novel LSTM-TrajGAN approach, which is an end-to-end deep learning model to generate privacy-preserving synthetic trajectory data for data sharing and publication. We design a loss metric function TrajLoss to measure the trajectory similarity losses for model training and optimization. The model is evaluated on the trajectory-user-linking task on a real-world semantic trajectory dataset. Compared with other common geomasking methods, our model can better prevent users from being re-identified, and it also preserves essential spatial, temporal, and thematic characteristics of the real trajectory data. The model better balances the effectiveness of trajectory privacy protection and the utility for spatial and temporal analyses, which offers new insights into the GeoAI-powered privacy protection.

arXiv:2006.10330

A Shooting Formulation of Deep Learning

Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE). Although important steps have been taken to realize the advantages of such continuous formulations, most current techniques are not truly continuous-depth as they assume \textit{identical} layers. Indeed, existing works throw into relief the myriad difficulties presented by an infinite-dimensional parameter space in learning a continuous-depth neural ODE. To this end, we introduce a shooting formulation which shifts the perspective from parameterizing a network layer-by-layer to parameterizing over optimal networks described only by a set of initial conditions. For scalability, we propose a novel particle-ensemble parametrization which fully specifies the optimal weight trajectory of the continuous-depth neural network. Our experiments show that our particle-ensemble shooting formulation can achieve competitive performance, especially on long-range forecasting tasks. Finally, though the current work is inspired by continuous-depth neural networks, the particle-ensemble shooting formulation also applies to discrete-time networks and may lead to a new fertile area of research in deep learning parametrization.