PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.04097

Deep Learning for Embodied Vision Navigation: A Survey

"Embodied visual navigation" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in autonomous driving, vacuum cleaner, and rescue robot. A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc. Building such an agent that observes, thinks, and acts is a key to real intelligence. The remarkable learning ability of deep learning methods empowered the agents to accomplish embodied visual navigation tasks. Despite this, embodied visual navigation is still in its infancy since a lot of advanced skills are required, including perceiving partially observed visual input, exploring unseen areas, memorizing and modeling seen scenarios, understanding cross-modal instructions, and adapting to a new environment, etc. Recently, embodied visual navigation has attracted rising attention of the community, and numerous works has been proposed to learn these skills. This paper attempts to establish an outline of the current works in the field of embodied visual navigation by providing a comprehensive literature survey. We summarize the benchmarks and metrics, review different methods, analysis the challenges, and highlight the state-of-the-art methods. Finally, we discuss unresolved challenges in the field of embodied visual navigation and give promising directions in pursuing future research.

arXiv:2108.04139

Segmentation-free Heart Pathology Detection Using Deep Learning

Cardiovascular (CV) diseases are the leading cause of death in the world, and auscultation is typically an essential part of a cardiovascular examination. The ability to diagnose a patient based on their heart sounds is a rather difficult skill to master. Thus, many approaches for automated heart auscultation have been explored. However, most of the previously proposed methods involve a segmentation step, the performance of which drops significantly for high pulse rates or noisy signals. In this work, we propose a novel segmentation-free heart sound classification method. Specifically, we apply discrete wavelet transform to denoise the signal, followed by feature extraction and feature reduction. Then, Support Vector Machines and Deep Neural Networks are utilised for classification. On the PASCAL heart sound dataset our approach showed superior performance compared to others, achieving 81% and 96% precision on normal and murmur classes, respectively. In addition, for the first time, the data were further explored under a user-independent setting, where the proposed method achieved 92% and 86% precision on normal and murmur, demonstrating the potential of enabling automatic murmur detection for practical use.

arXiv:2108.03888공식 코드 · Papers with Code

Efficient Hyperparameter Optimization for Differentially Private Deep Learning

Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used many times for hyperparameter search in DPSGD; e.g., via a grid search. Therefore, there is an essential need for algorithms that, within a given search space, can find near-optimal hyperparameters for the best achievable privacy-utility tradeoffs efficiently. We formulate this problem into a general optimization framework for establishing a desirable privacy-utility tradeoff, and systematically study three cost-effective algorithms for being used in the proposed framework: evolutionary, Bayesian, and reinforcement learning. Our experiments, for hyperparameter tuning in DPSGD conducted on MNIST and CIFAR-10 datasets, show that these three algorithms significantly outperform the widely used grid search baseline. As this paper offers a first-of-a-kind framework for hyperparameter tuning in DPSGD, we discuss existing challenges and open directions for future studies. As we believe our work has implications to be utilized in the pipeline of private deep learning, we open-source our code at https://github.com/AmanPriyanshu/DP-HyperparamTuning.

arXiv:2108.04169

Using Deep Learning for Visual Decoding and Reconstruction from Brain Activity: A Review

This literature review will discuss the use of deep learning methods for image reconstruction using fMRI data. More specifically, the quality of image reconstruction will be determined by the choice in decoding and reconstruction architectures. I will show that these structures can struggle with adaptability to various input stimuli due to complicated objects in images. Also, the significance of feature representation will be evaluated. This paper will conclude the use of deep learning within visual decoding and reconstruction is highly optimal when using variations of deep neural networks and will provide details of potential future work.

arXiv:2108.03614

Monte Carlo DropBlock for Modelling Uncertainty in Object Detection

With the advancements made in deep learning, computer vision problems like object detection and segmentation have seen a great improvement in performance. However, in many real-world applications such as autonomous driving vehicles, the risk associated with incorrect predictions of objects is very high. Standard deep learning models for object detection such as YOLO models are often overconfident in their predictions and do not take into account the uncertainty in predictions on out-of-distribution data. In this work, we propose an efficient and effective approach to model uncertainty in object detection and segmentation tasks using Monte-Carlo DropBlock (MC-DropBlock) based inference. The proposed approach applies drop-block during training time and test time on the convolutional layer of the deep learning models such as YOLO. We show that this leads to a Bayesian convolutional neural network capable of capturing the epistemic uncertainty in the model. Additionally, we capture the aleatoric uncertainty using a Gaussian likelihood. We demonstrate the effectiveness of the proposed approach on modeling uncertainty in object detection and segmentation tasks using out-of-distribution experiments. Experimental results show that MC-DropBlock improves the generalization, calibration, and uncertainty modeling capabilities of YOLO models in object detection and segmentation.

arXiv:2108.03890

SPECT Angle Interpolation Based on Deep Learning Methodologies

A novel method for SPECT angle interpolation based on deep learning methodologies is presented. Projection data from software phantoms were used to train the proposed model. For evaluation of the efficacy of the method, phantoms based on Shepp Logan, with various noise levels added were used, and the resulting interpolated sinograms are reconstructed using Ordered Subset Expectation Maximization (OSEM) and compared to the reconstructions of the original sinograms. The proposed method can quadruple the projections, and denoise the original sinogram, in the same process. As the results show, the proposed model significantly improves the reconstruction accuracy. Finally, to demonstrate the efficacy and capability of the proposed method results from real-world DAT-SPECT sinograms are presented.

arXiv:2108.03645

Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters

Efficient GPU resource scheduling is essential to maximize resource utilization and save training costs for the increasing amount of deep learning workloads in shared GPU clusters. Existing GPU schedulers largely rely on static policies to leverage the performance characteristics of deep learning jobs. However, they can hardly reach optimal efficiency due to the lack of elasticity. To address the problem, we propose ONES, an ONline Evolutionary Scheduler for elastic batch size orchestration. ONES automatically manages the elasticity of each job based on the training batch size, so as to maximize GPU utilization and improve scheduling efficiency. It determines the batch size for each job through an online evolutionary search that can continuously optimize the scheduling decisions. We evaluate the effectiveness of ONES with 64 GPUs on TACC's Longhorn supercomputers. The results show that ONES can outperform the prior deep learning schedulers with a significantly shorter average job completion time.

arXiv:2108.03591

FederatedNILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring based on Federated Deep Learning

Non-intrusive load monitoring (NILM), which usually utilizes machine learning methods and is effective in disaggregating smart meter readings from the household-level into appliance-level consumptions, can help to analyze electricity consumption behaviours of users and enable practical smart energy and smart grid applications. However, smart meters are privately owned and distributed, which make real-world applications of NILM challenging. To this end, this paper develops a distributed and privacy-preserving federated deep learning framework for NILM (FederatedNILM), which combines federated learning with a state-of-the-art deep learning architecture to conduct NILM for the classification of typical states of household appliances. Through extensive comparative experiments, the effectiveness of the proposed FederatedNILM framework is demonstrated.

arXiv:2108.03585

Ensemble neuroevolution based approach for multivariate time series anomaly detection

Multivariate time series anomaly detection is a very common problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms which automates the process of detecting anomalies are crucial in modern failure-prevention systems. Therefore, many machine and deep learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. In this work, a framework is shown which incorporates neuroevolution methods to boost the anomaly-detection scores of new and already known models. The presented approach adapts evolution strategies for evolving ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimise architecture and hyperparameters like window size, the number of layers, layer depths, etc. The proposed framework shows that it is possible to boost most of the anomaly detection deep learning models in a reasonable time and a fully automated mode. The tests were run on SWAT and WADI datasets. To our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.

arXiv:2108.03579

Expressive Power and Loss Surfaces of Deep Learning Models

The goals of this paper are two-fold. The first goal is to serve as an expository tutorial on the working of deep learning models which emphasizes geometrical intuition about the reasons for success of deep learning. The second goal is to complement the current results on the expressive power of deep learning models and their loss surfaces with novel insights and results. In particular, we describe how deep neural networks carve out manifolds especially when the multiplication neurons are introduced. Multiplication is used in dot products and the attention mechanism and it is employed in capsule networks and self-attention based transformers. We also describe how random polynomial, random matrix, spin glass and computational complexity perspectives on the loss surfaces are interconnected.

arXiv:2108.02948

Deep Learning-based Biological Anatomical Landmark Detection in Colonoscopy Videos

Colonoscopy is a standard imaging tool for visualizing the entire gastrointestinal (GI) tract of patients to capture lesion areas. However, it takes the clinicians excessive time to review a large number of images extracted from colonoscopy videos. Thus, automatic detection of biological anatomical landmarks within the colon is highly demanded, which can help reduce the burden of clinicians by providing guidance information for the locations of lesion areas. In this article, we propose a novel deep learning-based approach to detect biological anatomical landmarks in colonoscopy videos. First, raw colonoscopy video sequences are pre-processed to reject interference frames. Second, a ResNet-101 based network is used to detect three biological anatomical landmarks separately to obtain the intermediate detection results. Third, to achieve more reliable localization of the landmark periods within the whole video period, we propose to post-process the intermediate detection results by identifying the incorrectly predicted frames based on their temporal distribution and reassigning them back to the correct class. Finally, the average detection accuracy reaches 99.75\%. Meanwhile, the average IoU of 0.91 shows a high degree of similarity between our predicted landmark periods and ground truth. The experimental results demonstrate that our proposed model is capable of accurately detecting and localizing biological anatomical landmarks from colonoscopy videos.

arXiv:2108.02940공식 코드 · Papers with Code

Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles

In recent years, many deep learning models have been adopted in autonomous driving. At the same time, these models introduce new vulnerabilities that may compromise the safety of autonomous vehicles. Specifically, recent studies have demonstrated that adversarial attacks can cause a significant decline in detection precision of deep learning-based 3D object detection models. Although driving safety is the ultimate concern for autonomous driving, there is no comprehensive study on the linkage between the performance of deep learning models and the driving safety of autonomous vehicles under adversarial attacks. In this paper, we investigate the impact of two primary types of adversarial attacks, perturbation attacks and patch attacks, on the driving safety of vision-based autonomous vehicles rather than the detection precision of deep learning models. In particular, we consider two state-of-the-art models in vision-based 3D object detection, Stereo R-CNN and DSGN. To evaluate driving safety, we propose an end-to-end evaluation framework with a set of driving safety performance metrics. By analyzing the results of our extensive evaluation experiments, we find that (1) the attack's impact on the driving safety of autonomous vehicles and the attack's impact on the precision of 3D object detectors are decoupled, and (2) the DSGN model demonstrates stronger robustness to adversarial attacks than the Stereo R-CNN model. In addition, we further investigate the causes behind the two findings with an ablation study. The findings of this paper provide a new perspective to evaluate adversarial attacks and guide the selection of deep learning models in autonomous driving.

arXiv:2108.02870

A Data Augmented Approach to Transfer Learning for Covid-19 Detection

Covid-19 detection at an early stage can aid in an effective treatment and isolation plan to prevent its spread. Recently, transfer learning has been used for Covid-19 detection using X-ray, ultrasound, and CT scans. One of the major limitations inherent to these proposed methods is limited labeled dataset size that affects the reliability of Covid-19 diagnosis and disease progression. In this work, we demonstrate that how we can augment limited X-ray images data by using Contrast limited adaptive histogram equalization (CLAHE) to train the last layer of the pre-trained deep learning models to mitigate the bias of transfer learning for Covid-19 detection. We transfer learned various pre-trained deep learning models including AlexNet, ZFNet, VGG-16, ResNet-18, and GoogLeNet, and fine-tune the last layer by using CLAHE-augmented dataset. The experiment results reveal that the CLAHE-based augmentation to various pre-trained deep learning models significantly improves the model efficiency. The pre-trained VCG-16 model with CLAHEbased augmented images achieves a sensitivity of 95% using 15 epochs. AlexNet works show good sensitivity when trained on non-augmented data. Other models demonstrate a value of less than 60% when trained on non-augmented data. Our results reveal that the sample bias can negatively impact the performance of transfer learning which is significantly improved by using CLAHE-based augmentation.

arXiv:2108.02867

Enterprise Analytics using Graph Database and Graph-based Deep Learning

In a business-to-business (B2B) customer relationship management (CRM) use case, each client is a potential business organization/company with a solid business strategy and focused and rational decisions. This paper introduces a graph-based analytics approach to improve CRM within a B2B environment. In our approach, in the first instance, we have designed a graph database using the Neo4j platform. Secondly, the graph database has been investigated by using data mining and exploratory analysis coupled with cypher graph query language. Specifically, we have applied the graph convolution network (GCN) to enable CRM analytics to forecast sales. This is the first step towards a GCN-based binary classification based on graph databases in the domain of B2B CRM. We evaluate the performance of the proposed GCN model on graph databases and compare it with Random Forest (RF), Convolutional Neural Network (CNN), and Artificial Neural Network (ANN). The proposed GCN approach is further augmented with the shortest path and eigenvector centrality attribute to significantly improve the accuracy of sales prediction. Experimental results reveal that the proposed graph-based deep learning approach outperforms the Random Forests (RsF) and two deep learning models, i.e., CNN and ANN under different combinations of graph features.

arXiv:2108.02744

Deep learning for inverse problems with unknown operator

We consider ill-posed inverse problems where the forward operator $T$ is unknown, and instead we have access to training data consisting of functions $f_i$ and their noisy images $Tf_i$. This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the training set. Here we propose a new method that requires minimal assumptions on the data, and prove reconstruction rates that depend on the number of training points and the noise level. We show that, in the regime of "many" training data, the method is minimax optimal. The proposed method employs a type of convolutional neural networks (U-nets) and empirical risk minimization in order to "fit" the unknown operator. In a nutshell, our approach is based on two ideas: the first is to relate U-nets to multiscale decompositions such as wavelets, thereby linking them to the existing theory, and the second is to use the hierarchical structure of U-nets and the low number of parameters of convolutional neural nets to prove entropy bounds that are practically useful. A significant difference with the existing works on neural networks in nonparametric statistics is that we use them to approximate operators and not functions, which we argue is mathematically more natural and technically more convenient.

arXiv:2108.02656

A Computer-Aided Diagnosis System for Breast Pathology: A Deep Learning Approach with Model Interpretability from Pathological Perspective

Objective: We develop a computer-aided diagnosis (CAD) system using deep learning approaches for lesion detection and classification on whole-slide images (WSIs) with breast cancer. The deep features being distinguishing in classification from the convolutional neural networks (CNN) are demonstrated in this study to provide comprehensive interpretability for the proposed CAD system using pathological knowledge. Methods: In the experiment, a total of 186 slides of WSIs were collected and classified into three categories: Non-Carcinoma, Ductal Carcinoma in Situ (DCIS), and Invasive Ductal Carcinoma (IDC). Instead of conducting pixel-wise classification into three classes directly, we designed a hierarchical framework with the multi-view scheme that performs lesion detection for region proposal at higher magnification first and then conducts lesion classification at lower magnification for each detected lesion. Results: The slide-level accuracy rate for three-category classification reaches 90.8% (99/109) through 5-fold cross-validation and achieves 94.8% (73/77) on the testing set. The experimental results show that the morphological characteristics and co-occurrence properties learned by the deep learning models for lesion classification are accordant with the clinical rules in diagnosis. Conclusion: The pathological interpretability of the deep features not only enhances the reliability of the proposed CAD system to gain acceptance from medical specialists, but also facilitates the development of deep learning frameworks for various tasks in pathology. Significance: This paper presents a CAD system for pathological image analysis, which fills the clinical requirements and can be accepted by medical specialists with providing its interpretability from the pathological perspective.

arXiv:2108.02563

GuavaNet: A deep neural network architecture for automatic sensory evaluation to predict degree of acceptability for Guava by a consumer

This thesis is divided into two parts:Part I: Analysis of Fruits, Vegetables, Cheese and Fish based on Image Processing using Computer Vision and Deep Learning: A Review. It consists of a comprehensive review of image processing, computer vision and deep learning techniques applied to carry out analysis of fruits, vegetables, cheese and fish.This part also serves as a literature review for Part II.Part II: GuavaNet: A deep neural network architecture for automatic sensory evaluation to predict degree of acceptability for Guava by a consumer. This part introduces to an end-to-end deep neural network architecture that can predict the degree of acceptability by the consumer for a guava based on sensory evaluation.

arXiv:2108.02278공식 코드 · Papers with Code

Pan-Cancer Integrative Histology-Genomic Analysis via Interpretable Multimodal Deep Learning

The rapidly emerging field of deep learning-based computational pathology has demonstrated promise in developing objective prognostic models from histology whole slide images. However, most prognostic models are either based on histology or genomics alone and do not address how histology and genomics can be integrated to develop joint image-omic prognostic models. Additionally identifying explainable morphological and molecular descriptors from these models that govern such prognosis is of interest. We used multimodal deep learning to integrate gigapixel whole slide pathology images, RNA-seq abundance, copy number variation, and mutation data from 5,720 patients across 14 major cancer types. Our interpretable, weakly-supervised, multimodal deep learning algorithm is able to fuse these heterogeneous modalities for predicting outcomes and discover prognostic features from these modalities that corroborate with poor and favorable outcomes via multimodal interpretability. We compared our model with unimodal deep learning models trained on histology slides and molecular profiles alone, and demonstrate performance increase in risk stratification on 9 out of 14 cancers. In addition, we analyze morphologic and molecular markers responsible for prognostic predictions across all cancer types. All analyzed data, including morphological and molecular correlates of patient prognosis across the 14 cancer types at a disease and patient level are presented in an interactive open-access database (http://pancancer.mahmoodlab.org) to allow for further exploration and prognostic biomarker discovery. To validate that these model explanations are prognostic, we further analyzed high attention morphological regions in WSIs, which indicates that tumor-infiltrating lymphocyte presence corroborates with favorable cancer prognosis on 9 out of 14 cancer types studied.

arXiv:2108.02572

SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis

Deep learning has achieved great success in a wide spectrum of multimedia applications such as image classification, natural language processing and multimodal data analysis. Recent years have seen the development of many deep learning frameworks that provide a high-level programming interface for users to design models, conduct training and deploy inference. However, it remains challenging to build an efficient end-to-end multimedia application with most existing frameworks. Specifically, in terms of usability, it is demanding for non-experts to implement deep learning models, obtain the right settings for the entire machine learning pipeline, manage models and datasets, and exploit external data sources all together. Further, in terms of adaptability, elastic computation solutions are much needed as the actual serving workload fluctuates constantly, and scaling the hardware resources to handle the fluctuating workload is typically infeasible. To address these challenges, we introduce SINGA-Easy, a new deep learning framework that provides distributed hyper-parameter tuning at the training stage, dynamic computational cost control at the inference stage, and intuitive user interactions with multimedia contents facilitated by model explanation. Our experiments on the training and deployment of multi-modality data analysis applications show that the framework is both usable and adaptable to dynamic inference loads. We implement SINGA-Easy on top of Apache SINGA and demonstrate our system with the entire machine learning life cycle.

arXiv:2108.01810공식 코드 · Papers with Code

Deep Learning Chromatic and Clique Numbers of Graphs

Deep neural networks have been applied to a wide range of problems across different application domains with great success. Recently, research into combinatorial optimization problems in particular has generated much interest in the machine learning community. In this work, we develop deep learning models to predict the chromatic number and maximum clique size of graphs, both of which represent classical NP-complete combinatorial optimization problems encountered in graph theory. The neural networks are trained using the most basic representation of the graph, the adjacency matrix, as opposed to undergoing complex domain-specific feature engineering. The experimental results show that deep neural networks, and in particular convolutional neural networks, obtain strong performance on this problem.