PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.11696

A Real Use Case of Semi-Supervised Learning for Mammogram Classification in a Local Clinic of Costa Rica

The implementation of deep learning based computer aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model requires a considerable amount of labeled images, which can be expensive to obtain as time and effort from clinical practitioners is required. A number of publicly available datasets have been built with data from different hospitals and clinics. However, using models trained on these datasets for later work on images sampled from a different hospital or clinic might result in lower performance. This is due to the distribution mismatch of the datasets, which include different patient populations and image acquisition protocols. The scarcity of labeled data can also bring a challenge towards the application of transfer learning with models trained using these source datasets. In this work, a real world scenario is evaluated where a novel target dataset sampled from a private Costa Rican clinic is used, with few labels and heavily imbalanced data. The use of two popular and publicly available datasets (INbreast and CBIS-DDSM) as source data, to train and test the models on the novel target dataset, is evaluated. The use of the semi-supervised deep learning approach known as MixMatch, to leverage the usage of unlabeled data from the target dataset, is proposed and evaluated. In the tests, the performance of models is extensively measured, using different metrics to assess the performance of a classifier under heavy data imbalance conditions. It is shown that the use of semi-supervised deep learning combined with fine-tuning can provide a meaningful advantage when using scarce labeled observations. We make available the novel dataset for the benefit of the community.

arXiv:2107.11678

Deep-learning-driven Reliable Single-pixel Imaging with Uncertainty Approximation

Single-pixel imaging (SPI) has the advantages of high-speed acquisition over a broad wavelength range and system compactness, which are difficult to achieve by conventional imaging sensors. However, a common challenge is low image quality arising from undersampling. Deep learning (DL) is an emerging and powerful tool in computational imaging for many applications and researchers have applied DL in SPI to achieve higher image quality than conventional reconstruction approaches. One outstanding challenge, however, is that the accuracy of DL predictions in SPI cannot be assessed in practical applications where the ground truths are unknown. Here, we propose the use of the Bayesian convolutional neural network (BCNN) to approximate the uncertainty (coming from finite training data and network model) of the DL predictions in SPI. Each pixel in the predicted result from BCNN represents the parameter of a probability distribution rather than the image intensity value. Then, the uncertainty can be approximated with BCNN by minimizing a negative log-likelihood loss function in the training stage and Monte Carlo dropout in the prediction stage. The results show that the BCNN can reliably approximate the uncertainty of the DL predictions in SPI with varying compression ratios and noise levels. The predicted uncertainty from BCNN in SPI reveals that most of the reconstruction errors in deep-learning-based SPI come from the edges of the image features. The results show that the proposed BCNN can provide a reliable tool to approximate the uncertainty of DL predictions in SPI and can be widely used in many applications of SPI.

arXiv:2107.11640

Deep Machine Learning Based Egyptian Vehicle License Plate Recognition Systems

Automated Vehicle License Plate (VLP) detection and recognition have ended up being a significant research issue as of late. VLP localization and recognition are some of the most essential techniques for managing traffic using digital techniques. In this paper, four smart systems are developed to recognize Egyptian vehicles license plates. Two systems are based on character recognition, which are (System1, Characters Recognition with Classical Machine Learning) and (System2, Characters Recognition with Deep Machine Learning). The other two systems are based on the whole plate recognition which are (System3, Whole License Plate Recognition with Classical Machine Learning) and (System4, Whole License Plate Recognition with Deep Machine Learning). We use object detection algorithms, and machine learning based object recognition algorithms. The performance of the developed systems has been tested on real images, and the experimental results demonstrate that the best detection accuracy rate for VLP is provided by using the deep learning method. Where the VLP detection accuracy rate is better than the classical system by 32%. However, the best detection accuracy rate for Vehicle License Plate Arabic Character (VLPAC) is provided by using the classical method. Where VLPAC detection accuracy rate is better than the deep learning-based system by 6%. Also, the results show that deep learning is better than the classical technique used in VLP recognition processes. Where the recognition accuracy rate is better than the classical system by 8%. Finally, the paper output recommends a robust VLP recognition system based on both statistical and deep machine learning.

arXiv:2107.11447

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

Deep learning methods are the de-facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application which, like many others, requires a large number of annotated data so a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated datasets that machine learning can successfully train on. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with different loss functions on expert and non-expert groundtruth for cardiac cine-MRI segmentation. Evaluation was done with classic segmentation metrics (Dice index and Hausdorff distance) as well as clinical measurements, such as the ventricular ejection fractions and the myocardial mass. Results reveal that generalization performances of a segmentation neural network trained on non-expert groundtruth data is, to all practical purposes, as good as on expert groundtruth data, in particular when the non-expert gets a decent level of training, highlighting an opportunity for the efficient and cheap creation of annotations for cardiac datasets.

arXiv:2107.10912

Explainable artificial intelligence (XAI) in deep learning-based medical image analysis

With an increase in deep learning-based methods, the call for explainability of such methods grows, especially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduced to classify deep learning-based medical image analysis methods. Papers on XAI techniques in medical image analysis are then surveyed and categorized according to the framework and according to anatomical location. The paper concludes with an outlook of future opportunities for XAI in medical image analysis.

arXiv:2107.10894

Power Plant Classification from Remote Imaging with Deep Learning

Satellite remote imaging enables the detailed study of land use patterns on a global scale. We investigate the possibility to improve the information content of traditional land use classification by identifying the nature of industrial sites from medium-resolution remote sensing images. In this work, we focus on classifying different types of power plants from Sentinel-2 imaging data. Using a ResNet-50 deep learning model, we are able to achieve a mean accuracy of 90.0% in distinguishing 10 different power plant types and a background class. Furthermore, we are able to identify the cooling mechanisms utilized in thermal power plants with a mean accuracy of 87.5%. Our results enable us to qualitatively investigate the energy mix from Sentinel-2 imaging data, and prove the feasibility to classify industrial sites on a global scale from freely available satellite imagery.

arXiv:2107.11238

Exploring Deep Registration Latent Spaces

Explainability of deep neural networks is one of the most challenging and interesting problems in the field. In this study, we investigate the topic focusing on the interpretability of deep learning-based registration methods. In particular, with the appropriate model architecture and using a simple linear projection, we decompose the encoding space, generating a new basis, and we empirically show that this basis captures various decomposed anatomically aware geometrical transformations. We perform experiments using two different datasets focusing on lungs and hippocampus MRI. We show that such an approach can decompose the highly convoluted latent spaces of registration pipelines in an orthogonal space with several interesting properties. We hope that this work could shed some light on a better understanding of deep learning-based registration methods.

arXiv:2107.11042

Deep Learning Based Reconstruction of Total Solar Irradiance

The Earth's primary source of energy is the radiant energy generated by the Sun, which is referred to as solar irradiance, or total solar irradiance (TSI) when all of the radiation is measured. A minor change in the solar irradiance can have a significant impact on the Earth's climate and atmosphere. As a result, studying and measuring solar irradiance is crucial in understanding climate changes and solar variability. Several methods have been developed to reconstruct total solar irradiance for long and short periods of time; however, they are physics-based and rely on the availability of data, which does not go beyond 9,000 years. In this paper we propose a new method, called TSInet, to reconstruct total solar irradiance by deep learning for short and long periods of time that span beyond the physical models' data availability. On the data that are available, our method agrees well with the state-of-the-art physics-based reconstruction models. To our knowledge, this is the first time that deep learning has been used to reconstruct total solar irradiance for more than 9,000 years.

arXiv:2107.11350공식 코드 · Papers with Code

Heteroscedastic Temporal Variational Autoencoder For Irregular Time Series

Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models. In this paper, we propose a new deep learning framework for probabilistic interpolation of irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE). HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output interpolations. Our results show that the proposed architecture is better able to reflect variable uncertainty through time due to sparse and irregular sampling than a range of baseline and traditional models, as well as recently proposed deep latent variable models that use homoscedastic output layers.

arXiv:2107.11059

LocalGLMnet: interpretable deep learning for tabular data

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep learning models is that their solutions are difficult to interpret and explain, and variable selection is not easily possible because deep learning models solve feature engineering and variable selection internally in a nontransparent way. Inspired by the appealing structure of generalized linear models, we propose a new network architecture that shares similar features as generalized linear models, but provides superior predictive power benefiting from the art of representation learning. This new architecture allows for variable selection of tabular data and for interpretation of the calibrated deep learning model, in fact, our approach provides an additive decomposition in the spirit of Shapley values and integrated gradients.

arXiv:2107.10662

A Multimodal Deep Learning Model for Cardiac Resynchronisation Therapy Response Prediction

We present a novel multimodal deep learning framework for cardiac resynchronisation therapy (CRT) response prediction from 2D echocardiography and cardiac magnetic resonance (CMR) data. The proposed method first uses the `nnU-Net' segmentation model to extract segmentations of the heart over the full cardiac cycle from the two modalities. Next, a multimodal deep learning classifier is used for CRT response prediction, which combines the latent spaces of the segmentation models of the two modalities. At inference time, this framework can be used with 2D echocardiography data only, whilst taking advantage of the implicit relationship between CMR and echocardiography features learnt from the model. We evaluate our pipeline on a cohort of 50 CRT patients for whom paired echocardiography/CMR data were available, and results show that the proposed multimodal classifier results in a statistically significant improvement in accuracy compared to the baseline approach that uses only 2D echocardiography data. The combination of multimodal data enables CRT response to be predicted with 77.38% accuracy (83.33% sensitivity and 71.43% specificity), which is comparable with the current state-of-the-art in machine learning-based CRT response prediction. Our work represents the first multimodal deep learning approach for CRT response prediction.

논문 ID: document/9208871

Perceptual Modelling of Unconstrained Road Traffic Scenarios with Deep Learning

In recent times, advanced driver assistance system (ADAS) and autonomous driving have received significant interest in the automotive community. In this regard, lane assistance system and vehicle detection are considered as core modules of ADAS. However, the drawback is that the conventional image processing and vision-based techniques are quite slow and computationally expensive. The proposed work circumvents this limitation with the practical use of deep learning (CNN) based detection architecture. This paper proposes the use of CNN inspired detection methods such as Faster RCNN and YOLO for visual perception of road traffic. Notably, they were applied for effective vehicle detection in non-disciplined, heterogeneous Indian road traffic. This involved collecting own dataset for Indian urban heterogeneous traffic in both day and night time. An application of YOLO with VGG network resulted in a mAP score of 78.57%. On the other hand, Faster RCNN with Inception v2 and ResNet networks resulted in mAP score of 88% and 89.44%, on Indian road traffic datasets. This is a significant result; that shows the use of Deep Learning techniques for an efficient visual modelling of unconstrained road traffic scenarios.

arXiv:2107.09951

Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies

Objective: Temporal electronic health records (EHRs) can be a wealth of information for secondary uses, such as clinical events prediction or chronic disease management. However, challenges exist for temporal data representation. We therefore sought to identify these challenges and evaluate novel methodologies for addressing them through a systematic examination of deep learning solutions. Methods: We searched five databases (PubMed, EMBASE, the Institute of Electrical and Electronics Engineers [IEEE] Xplore Digital Library, the Association for Computing Machinery [ACM] digital library, and Web of Science) complemented with hand-searching in several prestigious computer science conference proceedings. We sought articles that reported deep learning methodologies on temporal data representation in structured EHR data from January 1, 2010, to August 30, 2020. We summarized and analyzed the selected articles from three perspectives: nature of time series, methodology, and model implementation. Results: We included 98 articles related to temporal data representation using deep learning. Four major challenges were identified, including data irregularity, data heterogeneity, data sparsity, and model opacity. We then studied how deep learning techniques were applied to address these challenges. Finally, we discuss some open challenges arising from deep learning. Conclusion: Temporal EHR data present several major challenges for clinical prediction modeling and data utilization. To some extent, current deep learning solutions can address these challenges. Future studies can consider designing comprehensive and integrated solutions. Moreover, researchers should incorporate additional clinical domain knowledge into study designs and enhance the interpretability of the model to facilitate its implementation in clinical practice.

arXiv:2107.10161공식 코드 · Papers with Code

Evidential Deep Learning for Open Set Action Recognition

In a real-world scenario, human actions are typically out of the distribution from training data, which requires a model to both recognize the known actions and reject the unknown. Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions. In this paper, we propose a Deep Evidential Action Recognition (DEAR) method to recognize actions in an open testing set. Specifically, we formulate the action recognition problem from the evidential deep learning (EDL) perspective and propose a novel model calibration method to regularize the EDL training. Besides, to mitigate the static bias of video representation, we propose a plug-and-play module to debias the learned representation through contrastive learning. Experimental results show that our DEAR method achieves consistent performance gain on multiple mainstream action recognition models and benchmarks. Code and pre-trained models are available at {\small{\url{https://www.rit.edu/actionlab/dear}}}.

arXiv:2107.10004

Deep Iterative 2D/3D Registration

Deep Learning-based 2D/3D registration methods are highly robust but often lack the necessary registration accuracy for clinical application. A refinement step using the classical optimization-based 2D/3D registration method applied in combination with Deep Learning-based techniques can provide the required accuracy. However, it also increases the runtime. In this work, we propose a novel Deep Learning driven 2D/3D registration framework that can be used end-to-end for iterative registration tasks without relying on any further refinement step. We accomplish this by learning the update step of the 2D/3D registration framework using Point-to-Plane Correspondences. The update step is learned using iterative residual refinement-based optical flow estimation, in combination with the Point-to-Plane correspondence solver embedded as a known operator. Our proposed method achieves an average runtime of around 8s, a mean re-projection distance error of 0.60 $\pm$ 0.40 mm with a success ratio of 97 percent and a capture range of 60 mm. The combination of high registration accuracy, high robustness, and fast runtime makes our solution ideal for clinical applications.

arXiv:2107.09519

Canonical Polyadic Decomposition and Deep Learning for Machine Fault Detection

Acoustic monitoring for machine fault detection is a recent and expanding research path that has already provided promising results for industries. However, it is impossible to collect enough data to learn all types of faults from a machine. Thus, new algorithms, trained using data from healthy conditions only, were developed to perform unsupervised anomaly detection. A key issue in the development of these algorithms is the noise in the signals, as it impacts the anomaly detection performance. In this work, we propose a powerful data-driven and quasi non-parametric denoising strategy for spectral data based on a tensor decomposition: the Non-negative Canonical Polyadic (CP) decomposition. This method is particularly adapted for machine emitting stationary sound. We demonstrate in a case study, the Malfunctioning Industrial Machine Investigation and Inspection (MIMII) baseline, how the use of our denoising strategy leads to a sensible improvement of the unsupervised anomaly detection. Such approaches are capable to make sound-based monitoring of industrial processes more reliable.

arXiv:2107.09483

Significant Wave Height Prediction based on Wavelet Graph Neural Network

Computational intelligence-based ocean characteristics forecasting applications, such as Significant Wave Height (SWH) prediction, are crucial for avoiding social and economic loss in coastal cities. Compared to the traditional empirical-based or numerical-based forecasting models, "soft computing" approaches, including machine learning and deep learning models, have shown numerous success in recent years. In this paper, we focus on enabling the deep learning model to learn both short-term and long-term spatial-temporal dependencies for SWH prediction. A Wavelet Graph Neural Network (WGNN) approach is proposed to integrate the advantages of wavelet transform and graph neural network. Several parallel graph neural networks are separately trained on wavelet decomposed data, and the reconstruction of each model's prediction forms the final SWH prediction. Experimental results show that the proposed WGNN approach outperforms other models, including the numerical models, the machine learning models, and several deep learning models.

arXiv:2107.09384

An induction proof of the backpropagation algorithm in matrix notation

Backpropagation (BP) is a core component of the contemporary deep learning incarnation of neural networks. Briefly, BP is an algorithm that exploits the computational architecture of neural networks to efficiently evaluate the gradient of a cost function during neural network parameter optimization. The validity of BP rests on the application of a multivariate chain rule to the computational architecture of neural networks and their associated objective functions. Introductions to deep learning theory commonly present the computational architecture of neural networks in matrix form, but eschew a parallel formulation and justification of BP in the framework of matrix differential calculus. This entails several drawbacks for the theory and didactics of deep learning. In this work, we overcome these limitations by providing a full induction proof of the BP algorithm in matrix notation. Specifically, we situate the BP algorithm in the framework of matrix differential calculus, encompass affine-linear potential functions, prove the validity of the BP algorithm in inductive form, and exemplify the implementation of the matrix form BP algorithm in computer code.

arXiv:2107.09652

Towards Privacy-preserving Explanations in Medical Image Analysis

The use of Deep Learning in the medical field is hindered by the lack of interpretability. Case-based interpretability strategies can provide intuitive explanations for deep learning models' decisions, thus, enhancing trust. However, the resulting explanations threaten patient privacy, motivating the development of privacy-preserving methods compatible with the specifics of medical data. In this work, we analyze existing privacy-preserving methods and their respective capacity to anonymize medical data while preserving disease-related semantic features. We find that the PPRL-VGAN deep learning method was the best at preserving the disease-related semantic features while guaranteeing a high level of privacy among the compared state-of-the-art methods. Nevertheless, we emphasize the need to improve privacy-preserving methods for medical imaging, as we identified relevant drawbacks in all existing privacy-preserving approaches.

arXiv:2107.09507공식 코드 · Papers with Code

EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Network

In the context of electroencephalogram (EEG)-based driver drowsiness recognition, it is still challenging to design a calibration-free system, since EEG signals vary significantly among different subjects and recording sessions. Many efforts have been made to use deep learning methods for mental state recognition from EEG signals. However, existing work mostly treats deep learning models as black-box classifiers, while what have been learned by the models and to which extent they are affected by the noise in EEG data are still underexplored. In this paper, we develop a novel convolutional neural network combined with an interpretation technique that allows sample-wise analysis of important features for classification. The network has a compact structure and takes advantage of separable convolutions to process the EEG signals in a spatial-temporal sequence. Results show that the model achieves an average accuracy of 78.35% on 11 subjects for leave-one-out cross-subject drowsiness recognition, which is higher than the conventional baseline methods of 53.40%-72.68% and state-of-the-art deep learning methods of 71.75%-75.19%. Interpretation results indicate the model has learned to recognize biologically meaningful features from EEG signals, e.g., Alpha spindles, as strong indicators of drowsiness across different subjects. In addition, we also explore reasons behind some wrongly classified samples with the interpretation technique and discuss potential ways to improve the recognition accuracy. Our work illustrates a promising direction on using interpretable deep learning models to discover meaningful patterns related to different mental states from complex EEG signals.