PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1904.09737

Facial Expression Recognition Research Based on Deep Learning

With the development of deep learning, the structure of convolution neural network is becoming more and more complex and the performance of object recognition is getting better. However, the classification mechanism of convolution neural networks is still an unsolved core problem. The main problem is that convolution neural networks have too many parameters, which makes it difficult to analyze them. In this paper, we design and train a convolution neural network based on the expression recognition, and explore the classification mechanism of the network. By using the Deconvolution visualization method, the extremum point of the convolution neural network is projected back to the pixel space of the original image, and we qualitatively verify that the trained expression recognition convolution neural network forms a detector for the specific facial action unit. At the same time, we design the distance function to measure the distance between the presence of facial feature unit and the maximal value of the response on the feature map of convolution neural network. The greater the distance, the more sensitive the feature map is to the facial feature unit. By comparing the maximum distance of all facial feature elements in the feature graph, the mapping relationship between facial feature element and convolution neural network feature map is determined. Therefore, we have verified that the convolution neural network has formed a detector for the facial Action unit in the training process to realize the expression recognition.

arXiv:1904.09722

FishNet: A Camera Localizer using Deep Recurrent Networks

This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation. Inspired by the fact that global scene structure can be revealed by wide field-of-view, we leverage the large overlap of a fisheye camera between adjacent frames, and the powerful high-level feature representations of deep learning. Our main contribution is the novel network architecture that extracts both temporal and spatial information using a Recurrent Neural Network. Specifically, we propose a novel pose regularization term combined with LSTM. This leads to smoother pose estimation, especially for large outdoor scenery. Promising experimental results on three benchmark datasets manifest the effectiveness of the proposed approach.

arXiv:1904.09708

Compositional generalization in a deep seq2seq model by separating syntax and semantics

Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily generalize in this way, e.g. by applying known grammatical rules to novel words. Inspired by work in neuroscience suggesting separate brain systems for syntactic and semantic processing, we implement a modification to standard approaches in neural machine translation, imposing an analogous separation. The novel model, which we call Syntactic Attention, substantially outperforms standard methods in deep learning on the SCAN dataset, a compositional generalization task, without any hand-engineered features or additional supervision. Our work suggests that separating syntactic from semantic learning may be a useful heuristic for capturing compositional structure.

arXiv:1904.09673

Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions

The new demands for high-reliability and ultra-high capacity wireless communication have led to extensive research into 5G communications. However, the current communication systems, which were designed on the basis of conventional communication theories, signficantly restrict further performance improvements and lead to severe limitations. Recently, the emerging deep learning techniques have been recognized as a promising tool for handling the complicated communication systems, and their potential for optimizing wireless communications has been demonstrated. In this article, we first review the development of deep learning solutions for 5G communication, and then propose efficient schemes for deep learning-based 5G scenarios. Specifically, the key ideas for several important deep learningbased communication methods are presented along with the research opportunities and challenges. In particular, novel communication frameworks of non-orthogonal multiple access (NOMA), massive multiple-input multiple-output (MIMO), and millimeter wave (mmWave) are investigated, and their superior performances are demonstrated. We vision that the appealing deep learning-based wireless physical layer frameworks will bring a new direction in communication theories and that this work will move us forward along this road.

arXiv:1904.09274

Deep Learning on Mobile Devices - A Review

Recent breakthroughs in deep learning and artificial intelligence technologies have enabled numerous mobile applications. While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning implemented on mobile devices provides several advantages. These advantages include low communication bandwidth, small cloud computing resource cost, quick response time, and improved data privacy. Research and development of deep learning on mobile and embedded devices has recently attracted much attention. This paper provides a timely review of this fast-paced field to give the researcher, engineer, practitioner, and graduate student a quick grasp on the recent advancements of deep learning on mobile devices. In this paper, we discuss hardware architectures for mobile deep learning, including Field Programmable Gate Arrays, Application Specific Integrated Circuit, and recent mobile Graphic Processing Units. We present Size, Weight, Area and Power considerations and their relation to algorithm optimizations, such as quantization, pruning, compression, and approximations that simplify computation while retaining performance accuracy. We cover existing systems and give a state-of-the-industry review of TensorFlow, MXNet, Mobile AI Compute Engine, and Paddle-mobile deep learning platform. We discuss resources for mobile deep learning practitioners, including tools, libraries, models, and performance benchmarks. We present applications of various mobile sensing modalities to industries, ranging from robotics, healthcare and multi-media, biometrics to autonomous drive and defense. We address the key deep learning challenges to overcome, including low quality data, and small training/adaptation data sets. In addition, the review provides numerous citations and links to existing code bases implementing various technologies.

arXiv:1904.09233

Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry

Deep learning has achieved spectacular performance in image and speech recognition and synthesis. It outperforms other machine learning algorithms in problems where large amounts of data are available. In the area of measurement technology, instruments based on the photonic time stretch have established record real-time measurement throughput in spectroscopy, optical coherence tomography, and imaging flow cytometry. These extreme-throughput instruments generate approximately 1 Tbit/s of continuous measurement data and have led to the discovery of rare phenomena in nonlinear and complex systems as well as new types of biomedical instruments. Owing to the abundance of data they generate, time-stretch instruments are a natural fit to deep learning classification. Previously we had shown that high-throughput label-free cell classification with high accuracy can be achieved through a combination of time-stretch microscopy, image processing and feature extraction, followed by deep learning for finding cancer cells in the blood. Such a technology holds promise for early detection of primary cancer or metastasis. Here we describe a new deep learning pipeline, which entirely avoids the slow and computationally costly signal processing and feature extraction steps by a convolutional neural network that directly operates on the measured signals. The improvement in computational efficiency enables low-latency inference and makes this pipeline suitable for cell sorting via deep learning. Our neural network takes less than a few milliseconds to classify the cells, fast enough to provide a decision to a cell sorter for real-time separation of individual target cells. We demonstrate the applicability of our new method in the classification of OT-II white blood cells and SW-480 epithelial cancer cells with more than 95% accuracy in a label-free fashion.

arXiv:1904.09029

Deep Learning for Power System Security Assessment

Security assessment is among the most fundamental functions of power system operator. The sheer complexity of power systems exceeding a few buses, however, makes it an extremely computationally demanding task. The emergence of deep learning methods that are able to handle immense amounts of data, and infer valuable information appears as a promising alternative. This paper has two main contributions. First, inspired by the remarkable performance of convolutional neural networks for image processing, we represent for the first time power system snapshots as 2-dimensional images, thus taking advantage of the wide range of deep learning methods available for image processing. Second, we train deep neural networks on a large database for the NESTA 162-bus system to assess both N-1 security and small-signal stability. We find that our approach is over 255 times faster than a standard small-signal stability assessment, and it can correctly determine unsafe points with over 99% accuracy.

arXiv:1809.09968공식 코드 · Papers with Code

Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving

Privacy recently emerges as a severe concern in deep learning, that is, sensitive data must be prohibited from being shared with the third party during deep neural network development. In this paper, we propose Morphed Learning (MoLe), an efficient and secure scheme to deliver deep learning data. MoLe has two main components: data morphing and Augmented Convolutional (Aug-Conv) layer. Data morphing allows data providers to send morphed data without privacy information, while Aug-Conv layer helps deep learning developers to apply their networks on the morphed data without performance penalty. MoLe provides stronger security while introducing lower overhead compared to GAZELLE (USENIX Security 2018), which is another method with no performance penalty on the neural network. When using MoLe for VGG-16 network on CIFAR dataset, the computational overhead is only 9% and the data transmission overhead is 5.12%. As a comparison, GAZELLE has computational overhead of 10,000 times and data transmission overhead of 421,000 times. In this setting, the attack success rate of adversary is 7.9 x 10^{-90} for MoLe and 2.9 x 10^{-30} for GAZELLE, respectively.

arXiv:1904.09211

Analyzing the benefits of communication channels between deep learning models

As artificial intelligence systems spread to more diverse and larger tasks in many domains, the machine learning algorithms, and in particular the deep learning models and the databases required to train them are getting bigger themselves. Some algorithms do allow for some scaling of large computations by leveraging data parallelism. However, they often require a large amount of data to be exchanged in order to ensure the shared knowledge throughout the compute nodes is accurate. In this work, the effect of different levels of communications between deep learning models is studied, in particular how it affects performance. The first approach studied looks at decentralizing the numerous computations that are done in parallel in training procedures such as synchronous and asynchronous stochastic gradient descent. In this setting, a simplified communication that consists of exchanging low bandwidth outputs between compute nodes can be beneficial. In the following chapter, the communication protocol is slightly modified to further include training instructions. Indeed, this is studied in a simplified setup where a pre-trained model, analogous to a teacher, can customize a randomly initialized model's training procedure to accelerate learning. Finally, a communication channel where two deep learning models can exchange a purposefully crafted language is explored while allowing for different ways of optimizing that language.

arXiv:1904.09078

EmbraceNet: A robust deep learning architecture for multimodal classification

Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper, we propose a novel deep learning-based multimodal fusion architecture for classification tasks, which guarantees compatibility with any kind of learning models, deals with cross-modal information carefully, and prevents performance degradation due to partial absence of data. We employ two datasets for multimodal classification tasks, build models based on our architecture and other state-of-the-art models, and analyze their performance on various situations. The results show that our architecture outperforms the other multimodal fusion architectures when some parts of data are not available.

arXiv:1904.08764

Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading

Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images (<1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including results for accurately classifying images according to clinical five-grade diabetic retinopathy and four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.

arXiv:1904.08483

Deep learning for image segmentation: veritable or overhyped?

Deep learning has achieved great success as a powerful classification tool and also made great progress in sematic segmentation. As a result, many researchers also believe that deep learning is the most powerful tool for pixel level image segmentation. Could deep learning achieve the same pixel level accuracy as traditional image segmentation techniques by mapping the features of the object into a non-linear function? This paper gives a short survey of the accuracies achieved by deep learning so far in image classification and image segmentation. Compared to the high accuracies achieved by deep learning in classifying limited categories in international vision challenges, the image segmentation accuracies achieved by deep learning in the same challenges are only about eighty percent. On the contrary, the image segmentation accuracies achieved in international biomedical challenges are close to ninty five percent. Why the difference is so big? Since the accuracies of the competitors methods are only evaluated based on their submitted results instead of reproducing the results by submitting the source codes or the software, are the achieved accuracies verifiable or overhyped? We are going to find it out by analyzing the working principle of deep learning. Finally, we compared the accuracies of state of the art deep learning methods with a threshold selection method quantitatively. Experimental results showed that the threshold selection method could achieve significantly higher accuracy than deep learning methods in image segmentation.

arXiv:1904.08514공식 코드 · Papers with Code

DeepNovoV2: Better de novo peptide sequencing with deep learning

Personalized cancer vaccines are envisioned as the next generation rational cancer immunotherapy. The key step in developing personalized therapeutic cancer vaccines is to identify tumor-specific neoantigens that are on the surface of tumor cells. A promising method for this is through de novo peptide sequencing from mass spectrometry data. In this paper we introduce DeepNovoV2, the state-of-the-art model for peptide sequencing. In DeepNovoV2, a spectrum is directly represented as a set of (m/z, intensity) pairs, therefore it does not suffer from the accuracy-speed/memory trade-off problem. The model combines an order invariant network structure (T-Net) and recurrent neural networks and provides a complete end-to-end training and prediction framework to sequence patterns of peptides. Our experiments on a wide variety of data from different species show that DeepNovoV2 outperforms previous state-of-the-art methods, achieving 13.01-23.95\% higher accuracy at the peptide level.

arXiv:1904.08921공식 코드 · Papers with Code

Deep Parametric Shape Predictions using Distance Fields

Many tasks in graphics and vision demand machinery for converting shapes into consistent representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage. When the source data is noisy or ambiguous, however, artists and engineers often manually construct such representations, a tedious and potentially time-consuming process. While advances in deep learning have been successfully applied to noisy geometric data, the task of generating parametric shapes has so far been difficult for these methods. Hence, we propose a new framework for predicting parametric shape primitives using deep learning. We use distance fields to transition between shape parameters like control points and input data on a pixel grid. We demonstrate efficacy on 2D and 3D tasks, including font vectorization and surface abstraction.

arXiv:1904.08910공식 코드 · Papers with Code

Combating the Elsagate phenomenon: Deep learning architectures for disturbing cartoons

Watching cartoons can be useful for children's intellectual, social and emotional development. However, the most popular video sharing platform today provides many videos with Elsagate content. Elsagate is a phenomenon that depicts childhood characters in disturbing circumstances (e.g., gore, toilet humor, drinking urine, stealing). Even with this threat easily available for children, there is no work in the literature addressing the problem. As the first to explore disturbing content in cartoons, we proceed from the most recent pornography detection literature applying deep convolutional neural networks combined with static and motion information of the video. Our solution is compatible with mobile platforms and achieved 92.6% of accuracy. Our goal is not only to introduce the first solution but also to bring up the discussion around Elsagate.

arXiv:1904.08128공식 코드 · Papers with Code

Automated Design of Deep Learning Methods for Biomedical Image Segmentation

Biomedical imaging is a driver of scientific discovery and core component of medical care, currently stimulated by the field of deep learning. While semantic segmentation algorithms enable 3D image analysis and quantification in many applications, the design of respective specialised solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We propose nnU-Net, a deep learning framework that condenses the current domain knowledge and autonomously takes the key decisions required to transfer a basic architecture to different datasets and segmentation tasks. Without manual tuning, nnU-Net surpasses most specialised deep learning pipelines in 19 public international competitions and sets a new state of the art in the majority of the 49 tasks. The results demonstrate a vast hidden potential in the systematic adaptation of deep learning methods to different datasets. We make nnU-Net publicly available as an open-source tool that can effectively be used out-of-the-box, rendering state of the art segmentation accessible to non-experts and catalyzing scientific progress as a framework for automated method design.

arXiv:1904.08066

Collaboration Analysis Using Deep Learning

The analysis of the collaborative learning process is one of the growing fields of education research, which has many different analytic solutions. In this paper, we provided a new solution to improve automated collaborative learning analyses using deep neural networks. Instead of using self-reported questionnaires, which are subject to bias and noise, we automatically extract group-working information by object recognition results using Mask R-CNN method. This process is based on detecting the people and other objects from pictures and video clips of the collaborative learning process, then evaluate the mobile learning performance using the collaborative indicators. We tested our approach to automatically evaluate the group-work collaboration in a controlled study of thirty-three dyads while performing an anatomy body painting intervention. The results indicate that our approach recognizes the differences of collaborations among teams of treatment and control groups in the case study. This work introduces new methods for automated quality prediction of collaborations among human-human interactions using computer vision techniques.

arXiv:1904.08368

Relay: A High-Level Compiler for Deep Learning

Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently enabled progress in areas like computer vision and natural language processing. Extending these frameworks to accommodate the rapidly diversifying landscape of DL models and hardware platforms presents challenging tradeoffs between expressivity, composability, and portability. We present Relay, a new compiler framework for DL. Relay's functional, statically typed intermediate representation (IR) unifies and generalizes existing DL IRs to express state-of-the-art models. The introduction of Relay's expressive IR requires careful design of domain-specific optimizations, addressed via Relay's extension mechanisms. Using these extension mechanisms, Relay supports a unified compiler that can target a variety of hardware platforms. Our evaluation demonstrates Relay's competitive performance for a broad class of models and devices (CPUs, GPUs, and emerging accelerators). Relay's design demonstrates how a unified IR can provide expressivity, composability, and portability without compromising performance.

arXiv:1904.08352공식 코드 · Papers with Code

MOSNet: Deep Learning based Objective Assessment for Voice Conversion

Existing objective evaluation metrics for voice conversion (VC) are not always correlated with human perception. Therefore, training VC models with such criteria may not effectively improve naturalness and similarity of converted speech. In this paper, we propose deep learning-based assessment models to predict human ratings of converted speech. We adopt the convolutional and recurrent neural network models to build a mean opinion score (MOS) predictor, termed as MOSNet. The proposed models are tested on large-scale listening test results of the Voice Conversion Challenge (VCC) 2018. Experimental results show that the predicted scores of the proposed MOSNet are highly correlated with human MOS ratings at the system level while being fairly correlated with human MOS ratings at the utterance level. Meanwhile, we have modified MOSNet to predict the similarity scores, and the preliminary results show that the predicted scores are also fairly correlated with human ratings. These results confirm that the proposed models could be used as a computational evaluator to measure the MOS of VC systems to reduce the need for expensive human rating.

arXiv:1904.07404

swTVM: Towards Optimized Tensor Code Generation for Deep Learning on Sunway Many-Core Processor

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application portability. Among the existing deep learning compilers, TVM is well known for its efficiency in code generation and optimization across diverse hardware devices. In the meanwhile, the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning workloads. This paper combines the trends in these two directions. Specifically, we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as Sunway. In addition, we leverage the architecture features during the compilation such as core group for massive parallelism, DMA for high bandwidth memory transfer and local device memory for data locality, in order to generate efficient codes for deep learning workloads on Sunway. The experiment results show that the codes generated by swTVM achieves 1.79x on average compared to the state-of-the-art deep learning framework on Sunway, across six representative benchmarks. This work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in mind. We believe this work will encourage more people to embrace the power of deep learning and Sunway many-core processor.