PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2102.13123

DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning

Galaxy clusters identified from the Sunyaev Zel'dovich (SZ) effect are a key ingredient in multi-wavelength cluster-based cosmology. We present a comparison between two methods of cluster identification: the standard Matched Filter (MF) method in SZ cluster finding and a method using Convolutional Neural Networks (CNN). We further implement and show results for a `combined' identifier. We apply the methods to simulated millimeter maps for several observing frequencies for an SPT-3G-like survey. There are some key differences between the methods. The MF method requires image pre-processing to remove point sources and a model for the noise, while the CNN method requires very little pre-processing of images. Additionally, the CNN requires tuning of hyperparameters in the model and takes as input, cutout images of the sky. Specifically, we use the CNN to classify whether or not an 8 arcmin $\times$ 8 arcmin cutout of the sky contains a cluster. We compare differences in purity and completeness. The MF signal-to-noise ratio depends on both mass and redshift. Our CNN, trained for a given mass threshold, captures a different set of clusters than the MF, some of which have SNR below the MF detection threshold. However, the CNN tends to mis-classify cutouts whose clusters are located near the edge of the cutout, which can be mitigated with staggered cutouts. We leverage the complementarity of the two methods, combining the scores from each method for identification. The purity and completeness of the MF alone are both 0.61, assuming a standard detection threshold. The purity and completeness of the CNN alone are 0.59 and 0.61. The combined classification method yields 0.60 and 0.77, a significant increase for completeness with a modest decrease in purity. We advocate for combined methods that increase the confidence of many lower signal-to-noise clusters.

arXiv:2102.12903공식 코드 · Papers with Code

Self-Tuning for Data-Efficient Deep Learning

Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios. To mitigate the requirement for labeled data, semi-supervised learning (SSL) focuses on simultaneously exploring both labeled and unlabeled data, while transfer learning (TL) popularizes a favorable practice of fine-tuning a pre-trained model to the target data. A dilemma is thus encountered: Without a decent pre-trained model to provide an implicit regularization, SSL through self-training from scratch will be easily misled by inaccurate pseudo-labels, especially in large-sized label space; Without exploring the intrinsic structure of unlabeled data, TL through fine-tuning from limited labeled data is at risk of under-transfer caused by model shift. To escape from this dilemma, we present Self-Tuning to enable data-efficient deep learning by unifying the exploration of labeled and unlabeled data and the transfer of a pre-trained model, as well as a Pseudo Group Contrast (PGC) mechanism to mitigate the reliance on pseudo-labels and boost the tolerance to false labels. Self-Tuning outperforms its SSL and TL counterparts on five tasks by sharp margins, e.g. it doubles the accuracy of fine-tuning on Cars with 15% labels.

arXiv:2102.12898

ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning

Diffusion-weighted magnetic resonance imaging (DW-MRI) can be used to characterise the microstructure of the nervous tissue, e.g. to delineate brain white matter connections in a non-invasive manner via fibre tracking. Magnetic Resonance Imaging (MRI) in high spatial resolution would play an important role in visualising such fibre tracts in a superior manner. However, obtaining an image of such resolution comes at the expense of longer scan time. Longer scan time can be associated with the increase of motion artefacts, due to the patient's psychological and physical conditions. Single Image Super-Resolution (SISR), a technique aimed to obtain high-resolution (HR) details from one single low-resolution (LR) input image, achieved with Deep Learning, is the focus of this study. Compared to interpolation techniques or sparse-coding algorithms, deep learning extracts prior knowledge from big datasets and produces superior MRI images from the low-resolution counterparts. In this research, a deep learning based super-resolution technique is proposed and has been applied for DW-MRI. Images from the IXI dataset have been used as the ground-truth and were artificially downsampled to simulate the low-resolution images. The proposed method has shown statistically significant improvement over the baselines and achieved an SSIM of $0.913\pm0.045$.

arXiv:2009.02868공식 코드 · Papers with Code

pdADMM: parallel deep learning Alternating Direction Method of Multipliers

Alternating Direction Method of Multipliers (ADMM) has recently been proposed as a potential alternative optimizer to the Stochastic Gradient Descent(SGD) for deep learning problems. This is because ADMM can solve gradient vanishing and poor conditioning problems. Moreover, it has shown good scalability in many large-scale deep learning applications. However, there still lacks a parallel ADMM computational framework for deep neural networks because of layer dependency among variables. In this paper, we propose a novel parallel deep learning ADMM framework (pdADMM) to achieve layer parallelism: parameters in each layer of neural networks can be updated independently in parallel. The convergence of the proposed pdADMM to a critical point is theoretically proven under mild conditions. The convergence rate of the pdADMM is proven to be o(1/k) where k is the number of iterations. Extensive experiments on six benchmark datasets demonstrated that our proposed pdADMM can lead to more than 10 times speedup for training large-scale deep neural networks, and outperformed most of the comparison methods.

arXiv:2102.11903

Neural ranking models for document retrieval

Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep learning models in information retrieval. These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features. A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking. In this paper, we compare the proposed models in the literature along different dimensions in order to understand the major contributions and limitations of each model. In our discussion of the literature, we analyze the promising neural components, and propose future research directions. We also show the analogy between document retrieval and other retrieval tasks where the items to be ranked are structured documents, answers, images and videos.

arXiv:2102.12147

A New Pairwise Deep Learning Feature For Environmental Microorganism Image Analysis

Environmental microorganism (EM) offers a high-efficient, harmless, and low-cost solution to environmental pollution. They are used in sanitation, monitoring, and decomposition of environmental pollutants. However, this depends on the proper identification of suitable microorganisms. In order to fasten, low the cost, increase consistency and accuracy of identification, we propose the novel pairwise deep learning features to analyze microorganisms. The pairwise deep learning features technique combines the capability of handcrafted and deep learning features. In this technique we, leverage the Shi and Tomasi interest points by extracting deep learning features from patches which are centered at interest points locations. Then, to increase the number of potential features that have intermediate spatial characteristics between nearby interest points, we use Delaunay triangulation theorem and straight-line geometric theorem to pair the nearby deep learning features. The potential of pairwise features is justified on the classification of EMs using SVMs, k-NN, and Random Forest classifier. The pairwise features obtain outstanding results of 99.17%, 91.34%, 91.32%, 91.48%, and 99.56%, which are the increase of about 5.95%, 62.40%, 62.37%, 61.84%, and 3.23% in accuracy, F1-score, recall, precision, and specificity respectively, compared to non-paired deep learning features.

arXiv:2102.11677공식 코드 · Papers with Code

Cell abundance aware deep learning for cell detection on highly imbalanced pathological data

Automated analysis of tissue sections allows a better understanding of disease biology and may reveal biomarkers that could guide prognosis or treatment selection. In digital pathology, less abundant cell types can be of biological significance, but their scarcity can result in biased and sub-optimal cell detection model. To minimize the effect of cell imbalance on cell detection, we proposed a deep learning pipeline that considers the abundance of cell types during model training. Cell weight images were generated, which assign larger weights to less abundant cells and used the weights to regularize Dice overlap loss function. The model was trained and evaluated on myeloma bone marrow trephine samples. Our model obtained a cell detection F1-score of 0.78, a 2% increase compared to baseline models, and it outperformed baseline models at detecting rare cell types. We found that scaling deep learning loss function by the abundance of cells improves cell detection performance. Our results demonstrate the importance of incorporating domain knowledge on deep learning methods for pathological data with class imbalance.

arXiv:2102.11651

A Novel Deep Learning Method for Textual Sentiment Analysis

Sentiment analysis is known as one of the most crucial tasks in the field of natural language processing and Convolutional Neural Network (CNN) is one of those prominent models that is commonly used for this aim. Although convolutional neural networks have obtained remarkable results in recent years, they are still confronted with some limitations. Firstly, they consider that all words in a sentence have equal contributions in the sentence meaning representation and are not able to extract informative words. Secondly, they require a large number of training data to obtain considerable results while they have many parameters that must be accurately adjusted. To this end, a convolutional neural network integrated with a hierarchical attention layer is proposed which is able to extract informative words and assign them higher weight. Moreover, the effect of transfer learning that transfers knowledge learned in the source domain to the target domain with the aim of improving the performance is also explored. Based on the empirical results, the proposed model not only has higher classification accuracy and can extract informative words but also applying incremental transfer learning can significantly enhance the classification performance.

arXiv:2102.11502

Oriole: Thwarting Privacy against Trustworthy Deep Learning Models

Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy. Recently, a well-known system named Fawkes (published in USENIX Security 2020) claimed this privacy threat can be neutralized by uploading cloaked user images instead of their original images. In this paper, we present Oriole, a system that combines the advantages of data poisoning attacks and evasion attacks, to thwart the protection offered by Fawkes, by training the attacker face recognition model with multi-cloaked images generated by Oriole. Consequently, the face recognition accuracy of the attack model is maintained and the weaknesses of Fawkes are revealed. Experimental results show that our proposed Oriole system is able to effectively interfere with the performance of the Fawkes system to achieve promising attacking results. Our ablation study highlights multiple principal factors that affect the performance of the Oriole system, including the DSSIM perturbation budget, the ratio of leaked clean user images, and the numbers of multi-cloaks for each uncloaked image. We also identify and discuss at length the vulnerabilities of Fawkes. We hope that the new methodology presented in this paper will inform the security community of a need to design more robust privacy-preserving deep learning models.

arXiv:2102.10140

BPLight-CNN: A Photonics-based Backpropagation Accelerator for Deep Learning

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation algorithm (BP). This results in expensive computation overheads during training. Consequently, most deep learning accelerators today employ pre-trained weights and focus only on improving the design of the inference phase. The recent trend is to build a complete deep learning accelerator by incorporating the training module. Such efforts require an ultra-fast chip architecture for executing the BP algorithm. In this article, we propose a novel photonics-based backpropagation accelerator for high performance deep learning training. We present the design for a convolutional neural network, BPLight-CNN, which incorporates the silicon photonics-based backpropagation accelerator. BPLight-CNN is a first-of-its-kind photonic and memristor-based CNN architecture for end-to-end training and prediction. We evaluate BPLight-CNN using a photonic CAD framework (IPKISS) on deep learning benchmark models including LeNet and VGG-Net. The proposed design achieves (i) at least 34x speedup, 34x improvement in computational efficiency, and 38.5x energy savings, during training; and (ii) 29x speedup, 31x improvement in computational efficiency, and 38.7x improvement in energy savings, during inference compared to the state-of-the-art designs. All these comparisons are done at a 16-bit resolution; and BPLight-CNN achieves these improvements at a cost of approximately 6% lower accuracy compared to the state-of-the-art.

arXiv:2102.10640

Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution

The recent outbreak of COVID-19 has motivated researchers to contribute in the area of medical imaging using artificial intelligence and deep learning. Super-resolution (SR), in the past few years, has produced remarkable results using deep learning methods. The ability of deep learning methods to learn the non-linear mapping from low-resolution (LR) images to their corresponding high-resolution (HR) images leads to compelling results for SR in diverse areas of research. In this paper, we propose a deep learning based image super-resolution architecture in Tchebichef transform domain. This is achieved by integrating a transform layer into the proposed architecture through a customized Tchebichef convolutional layer ($TCL$). The role of TCL is to convert the LR image from the spatial domain to the orthogonal transform domain using Tchebichef basis functions. The inversion of the aforementioned transformation is achieved using another layer known as the Inverse Tchebichef convolutional Layer (ITCL), which converts back the LR images from the transform domain to the spatial domain. It has been observed that using the Tchebichef transform domain for the task of SR takes the advantage of high and low-frequency representation of images that makes the task of super-resolution simplified. We, further, introduce transfer learning approach to enhance the quality of Covid based medical images. It is shown that our architecture enhances the quality of X-ray and CT images of COVID-19, providing a better image quality that helps in clinical diagnosis. Experimental results obtained using the proposed Tchebichef transform domain super-resolution (TTDSR) architecture provides competitive results when compared with most of the deep learning methods employed using a fewer number of trainable parameters.

arXiv:2102.10545

Bayesian Deep Learning for Segmentation for Autonomous Safe Planetary Landing

Hazard detection is critical for enabling autonomous landing on planetary surfaces. Current state-of-the-art methods leverage traditional computer vision approaches to automate the identification of safe terrain from input digital elevation models (DEMs). However, performance for these methods can degrade for input DEMs with increased sensor noise. In the last decade, deep learning techniques have been developed for various applications. Nevertheless, their applicability to safety-critical space missions has often been limited due to concerns regarding their outputs' reliability. In response to these limitations, this paper proposes an application of the Bayesian deep-learning segmentation method for hazard detection. The developed approach enables reliable, safe landing site detection by: (i) generating simultaneously a safety prediction map and its uncertainty map via Bayesian deep learning and semantic segmentation; and (ii) using the uncertainty map to filter out the uncertain pixels in the prediction map so that the safe site identification is performed only based on the certain pixels (i.e., pixels for which the model is certain about its safety prediction). Experiments are presented with simulated data based on a Mars HiRISE digital terrain model by varying uncertainty threshold and noise levels to demonstrate the performance of the proposed approach.

arXiv:2102.10929

Deep Learning for Robust Motion Segmentation with Non-Static Cameras

This work proposes a new end-to-end DCNN based approach for motion segmentation, especially for video sequences captured with such non-static cameras, called MOSNET. While other approaches focus on spatial or temporal context only, the proposed approach uses 3D convolutions as a key technology to factor in, spatio-temporal features in cohesive video frames. This is done by capturing temporal information in features with a low and also with a high level of abstraction. The lean network architecture with about 21k trainable parameters is mainly based on a pre-trained VGG-16 network. The MOSNET uses a new feature map fusion technique, which enables the network to focus on the appropriate level of abstraction, resolution, and the appropriate size of the receptive field regarding the input. Furthermore, the end-to-end deep learning based approach can be extended by feature based image alignment as a pre-processing step, which brings a gain in performance for some scenes. Evaluating the end-to-end deep learning based MOSNET network in a scene independent manner leads to an overall F-measure of 0.803 on the CDNet2014 dataset. A small temporal window of five input frames, without the need of any initialization is used to obtain this result. Therefore the network is able to perform well on scenes captured with non-static cameras where the image content changes significantly during the scene. In order to get robust results in scenes captured with a moving camera, feature based image alignment can implemented as pre-processing step. The MOSNET combined with pre-processing leads to an F-measure of 0.685 when cross-evaluating with a relabeled LASIESTA dataset, which underpins the capability generalise of the MOSNET.

arXiv:2102.10788

Attention Models for Point Clouds in Deep Learning: A Survey

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks. However, creating feature representation of robust, discriminative from unordered and irregular point clouds is challenging. In this paper, our ultimate goal is to provide a comprehensive overview of the point clouds feature representation which uses attention models. More than 75+ key contributions in the recent three years are summarized in this survey, including the 3D objective detection, 3D semantic segmentation, 3D pose estimation, point clouds completion etc. We provide a detailed characterization (1) the role of attention mechanisms, (2) the usability of attention models into different tasks, (3) the development trend of key technology.

arXiv:2102.09759

Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey

Detecting, predicting, and alleviating traffic congestion are targeted at improving the level of service of the transportation network. With increasing access to larger datasets of higher resolution, the relevance of deep learning for such tasks is increasing. Several comprehensive survey papers in recent years have summarised the deep learning applications in the transportation domain. However, the system dynamics of the transportation network vary greatly between the non-congested state and the congested state -- thereby necessitating the need for a clear understanding of the challenges specific to congestion prediction. In this survey, we present the current state of deep learning applications in the tasks related to detection, prediction, and alleviation of congestion. Recurring and non-recurring congestion are discussed separately. Our survey leads us to uncover inherent challenges and gaps in the current state of research. Finally, we present some suggestions for future research directions as answers to the identified challenges.

arXiv:2102.09972공식 코드 · Papers with Code

Implicit Regularization in Tensor Factorization

Recent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization -- matrix completion via linear neural network. As a step further towards practical deep learning, we provide the first theoretical analysis of implicit regularization in tensor factorization -- tensor completion via certain type of non-linear neural network. We circumvent the notorious difficulty of tensor problems by adopting a dynamical systems perspective, and characterizing the evolution induced by gradient descent. The characterization suggests a form of greedy low tensor rank search, which we rigorously prove under certain conditions, and empirically demonstrate under others. Motivated by tensor rank capturing the implicit regularization of a non-linear neural network, we empirically explore it as a measure of complexity, and find that it captures the essence of datasets on which neural networks generalize. This leads us to believe that tensor rank may pave way to explaining both implicit regularization in deep learning, and the properties of real-world data translating this implicit regularization to generalization.

arXiv:2102.09188

Edge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization

EEG source localization is an important technical issue in EEG analysis. Despite many numerical methods existed for EEG source localization, they all rely on strong priors and the deep sources are intractable. Here we propose a deep learning framework using spatial basis function decomposition for EEG source localization. This framework combines the edge sparsity prior and Gaussian source basis, called Edge Sparse Basis Network (ESBN). The performance of ESBN is validated by both synthetic data and real EEG data during motor tasks. The results suggest that the supervised ESBN outperforms the traditional numerical methods in synthetic data and the unsupervised fine-tuning provides more focal and accurate localizations in real data. Our proposed deep learning framework can be extended to account for other source priors, and the real-time property of ESBN can facilitate the applications of EEG in brain-computer interfaces and clinics.

arXiv:2102.09069

SRDTI: Deep learning-based super-resolution for diffusion tensor MRI

High-resolution diffusion tensor imaging (DTI) is beneficial for probing tissue microstructure in fine neuroanatomical structures, but long scan times and limited signal-to-noise ratio pose significant barriers to acquiring DTI at sub-millimeter resolution. To address this challenge, we propose a deep learning-based super-resolution method entitled "SRDTI" to synthesize high-resolution diffusion-weighted images (DWIs) from low-resolution DWIs. SRDTI employs a deep convolutional neural network (CNN), residual learning and multi-contrast imaging, and generates high-quality results with rich textural details and microstructural information, which are more similar to high-resolution ground truth than those from trilinear and cubic spline interpolation.

arXiv:2102.09024

Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters

Computational tools for forecasting yields and prices for fresh produce have been based on traditional machine learning approaches or time series modelling. We propose here an alternate approach based on deep learning algorithms for forecasting strawberry yields and prices in Santa Barbara county, California. Building the proposed forecasting model comprises three stages: first, the station-based ensemble model (ATT-CNN-LSTM-SeriesNet_Ens) with its compound deep learning components, SeriesNet with Gated Recurrent Unit (GRU) and Convolutional Neural Network LSTM with Attention layer (Att-CNN-LSTM), are trained and tested using the station-based soil temperature and moisture data of SantaBarbara as input and the corresponding strawberry yields or prices as output. Secondly, the remote sensing ensemble model (SIM_CNN-LSTM_Ens), which is an ensemble model of Convolutional NeuralNetwork LSTM (CNN-LSTM) models, is trained and tested using satellite images of the same county as input mapped to the same yields and prices as output. These two ensembles forecast strawberry yields and prices with minimal forecasting errors and highest model correlation for five weeks ahead forecasts.Finally, the forecasts of these two models are ensembled to have a final forecasted value for yields and prices by introducing a voting ensemble. Based on an aggregated performance measure (AGM), it is found that this voting ensemble not only enhances the forecasting performance by 5% compared to its best performing component model but also outperforms the Deep Learning (DL) ensemble model found in literature by 33% for forecasting yields and 21% for forecasting prices

arXiv:2102.08990공식 코드 · Papers with Code

BEDS: Bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation

Reducing outcome variance is an essential task in deep learning based medical image analysis. Bootstrap aggregating, also known as bagging, is a canonical ensemble algorithm for aggregating weak learners to become a strong learner. Random forest is one of the most powerful machine learning algorithms before deep learning era, whose superior performance is driven by fitting bagged decision trees (weak learners). Inspired by the random forest technique, we propose a simple bagging ensemble deep segmentation (BEDs) method to train multiple U-Nets with partial training data to segment dense nuclei on pathological images. The contributions of this study are three-fold: (1) developing a self-ensemble learning framework for nucleus segmentation; (2) aggregating testing stage augmentation with self-ensemble learning; and (3) elucidating the idea that self-ensemble and testing stage stain augmentation are complementary strategies for a superior segmentation performance. Implementation Detail: https://github.com/xingli1102/BEDs.