PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2006.09628

Visor: Privacy-Preserving Video Analytics as a Cloud Service

Video-analytics-as-a-service is becoming an important offering for cloud providers. A key concern in such services is privacy of the videos being analyzed. While trusted execution environments (TEEs) are promising options for preventing the direct leakage of private video content, they remain vulnerable to side-channel attacks. We present Visor, a system that provides confidentiality for the user's video stream as well as the ML models in the presence of a compromised cloud platform and untrusted co-tenants. Visor executes video pipelines in a hybrid TEE that spans both the CPU and GPU. It protects the pipeline against side-channel attacks induced by data-dependent access patterns of video modules, and also addresses leakage in the CPU-GPU communication channel. Visor is up to $1000\times$ faster than na\"ive oblivious solutions, and its overheads relative to a non-oblivious baseline are limited to $2\times$--$6\times$.

arXiv:2006.10011

Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances

Object detection algorithms for Lidar data have seen numerous publications in recent years, reporting good results on dataset benchmarks oriented towards automotive requirements. Nevertheless, many of these are not deployable to embedded vehicle systems, as they require immense computational power to be executed close to real time. In this work, we propose a way to facilitate real-time Lidar object classification on CPU. We show how our approach uses segmented object instances to extract important features, enabling a computationally efficient batch-wise classification. For this, we introduce a data representation which translates three-dimensional information into small image patches, using decomposed normal vector images. We couple this with dedicated object statistics to handle edge cases. We apply our method on the tasks of object detection and semantic segmentation, as well as the relatively new challenge of panoptic segmentation. Through evaluation, we show, that our algorithm is capable of producing good results on public data, while running in real time on CPU without using specific optimisation.

arXiv:2006.07637

SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose that it is possible to transfer the MelGAN's [3] robustness in learning speech features to speech enhancement and noise reduction domain without any model modification tasks. Our proposed method generalizes over multi-speaker speech dataset and is able to robustly handle unseen background noises during the inference. Also, we show that by increasing the batch size for this particular approach not only yields better speech results, but generalizes over multi-speaker dataset easily and leads to faster convergence. Additionally, it outperforms previous state of the art GAN approach for speech enhancement SEGAN [5] in two domains: 1. quality ; 2. speed. Proposed method runs at more than 100x faster than realtime on GPU and more than 2x faster than real time on CPU without any hardware optimization tasks, right at the speed of MelGAN [3].

arXiv:2006.06762

Ansor: Generating High-Performance Tensor Programs for Deep Learning

High-performance tensor programs are crucial to guarantee efficient execution of deep neural networks. However, obtaining performant tensor programs for different operators on various hardware platforms is notoriously challenging. Currently, deep learning systems rely on vendor-provided kernel libraries or various search strategies to get performant tensor programs. These approaches either require significant engineering effort to develop platform-specific optimization code or fall short of finding high-performance programs due to restricted search space and ineffective exploration strategy. We present Ansor, a tensor program generation framework for deep learning applications. Compared with existing search strategies, Ansor explores many more optimization combinations by sampling programs from a hierarchical representation of the search space. Ansor then fine-tunes the sampled programs with evolutionary search and a learned cost model to identify the best programs. Ansor can find high-performance programs that are outside the search space of existing state-of-the-art approaches. In addition, Ansor utilizes a task scheduler to simultaneously optimize multiple subgraphs in deep neural networks. We show that Ansor improves the execution performance of deep neural networks relative to the state-of-the-art on the Intel CPU, ARM CPU, and NVIDIA GPU by up to $3.8\times$, $2.6\times$, and $1.7\times$, respectively.

arXiv:2006.06443

Convolutional neural networks compression with low rank and sparse tensor decompositions

Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some real-world applications, it is crucial to develop models, which can be fast and light enough to run on edge systems and mobile devices. However, many modern architectures that demonstrate good performance don't satisfy inference time and storage limitation requirements. Thus, arises a problem of neural network compression to obtain a smaller and faster model, which is on par with the initial one. In this work, we consider a neural network compression method based on tensor decompositions. Namely, we propose to approximate the convolutional layer weight with a tensor, which can be represented as a sum of low-rank and sparse components. The motivation for such approximation is based on the assumption that low-rank and sparse terms allow eliminating two different types of redundancy and thus yield a better compression rate. An efficient CPU implementation for the proposed method has been developed. Our algorithm has demonstrated up to 3.5x CPU layer speedup and 11x layer size reduction when compressing Resnet50 architecture for the image classification task.

arXiv:2006.05181

Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs

The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). Works have mainly focused on: i) efficient DNN architectures, ii) network optimisation techniques such as pruning and quantisation, iii) optimised algorithms to speed up the execution of the most computational intensive layers and, iv) dedicated hardware to accelerate the data flow and computation. However, there is a lack of research on cross-level optimisation as the space of approaches becomes too large to test and obtain a globally optimised solution. Thus, leading to suboptimal deployment in terms of latency, accuracy, and memory. In this work, we first detail and analyse the methods to improve the deployment of DNNs across the different levels of software optimisation. Building on this knowledge, we present an automated exploration framework to ease the deployment of DNNs. The framework relies on a Reinforcement Learning search that, combined with a deep learning inference framework, automatically explores the design space and learns an optimised solution that speeds up the performance and reduces the memory on embedded CPU platforms. Thus, we present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4x improvement in performance and over 2x reduction in memory with negligible loss in accuracy with respect to the BLAS floating-point implementation.

arXiv:2006.03790공식 코드 · Papers with Code

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

Telehealth and remote health monitoring have become increasingly important during the SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on healthcare practices. These tools can help reduce the risk of exposing patients and medical staff to infection, make healthcare services more accessible, and allow providers to see more patients. However, objective measurement of vital signs is challenging without direct contact with a patient. We present a video-based and on-device optical cardiopulmonary vital sign measurement approach. It leverages a novel multi-task temporal shift convolutional attention network (MTTS-CAN) and enables real-time cardiovascular and respiratory measurements on mobile platforms. We evaluate our system on an Advanced RISC Machine (ARM) CPU and achieve state-of-the-art accuracy while running at over 150 frames per second which enables real-time applications. Systematic experimentation on large benchmark datasets reveals that our approach leads to substantial (20%-50%) reductions in error and generalizes well across datasets.

arXiv:2006.03970공식 코드 · Papers with Code

An Efficient Semi-smooth Newton Augmented Lagrangian Method for Elastic Net

Feature selection is an important and active research area in statistics and machine learning. The Elastic Net is often used to perform selection when the features present non-negligible collinearity or practitioners wish to incorporate additional known structure. In this article, we propose a new Semi-smooth Newton Augmented Lagrangian Method to efficiently solve the Elastic Net in ultra-high dimensional settings. Our new algorithm exploits both the sparsity induced by the Elastic Net penalty and the sparsity due to the second order information of the augmented Lagrangian. This greatly reduces the computational cost of the problem. Using simulations on both synthetic and real datasets, we demonstrate that our approach outperforms its best competitors by at least an order of magnitude in terms of CPU time. We also apply our approach to a Genome Wide Association Study on childhood obesity.

arXiv:2006.04593공식 코드 · Papers with Code

ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a recent lightweight cryptographic protocol that allows us to achieve an efficient online phase. We design optimized primitives for the building blocks of neural networks such as ReLU, MaxPool and BatchNorm. For instance, we perform private comparison for ReLU operations with a single message of the size of the input during the online phase, and with preprocessing keys close to 4X smaller than previous work. Last, we propose an extension to support n-party private federated learning. We implement our framework as an extensible system on top of PyTorch that leverages CPU and GPU hardware acceleration for cryptographic and machine learning operations. We evaluate our end-to-end system for private inference between distant servers on standard neural networks such as AlexNet, VGG16 or ResNet18, and for private training on smaller networks like LeNet. We show that computation rather than communication is the main bottleneck and that using GPUs together with reduced key size is a promising solution to overcome this barrier.

arXiv:2006.02049

FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining

Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a training recipe), overlooking superior architecture-recipe combinations. To address this, we present Neural Architecture-Recipe Search (NARS) to search both (a) architectures and (b) their corresponding training recipes, simultaneously. NARS utilizes an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. Furthermore, to compensate for the enlarged search space, we leverage "free" architecture statistics (e.g., FLOP count) to pretrain the predictor, significantly improving its sample efficiency and prediction reliability. After training the predictor via constrained iterative optimization, we run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints, called FBNetV3. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors. For example, FBNetV3 matches both EfficientNet and ResNeSt accuracy on ImageNet with up to 2.0x and 7.1x fewer FLOPs, respectively. Furthermore, FBNetV3 yields significant performance gains for downstream object detection tasks, improving mAP despite 18% fewer FLOPs and 34% fewer parameters than EfficientNet-based equivalents.

arXiv:2006.01786

Hyperparameter Selection for Subsampling Bootstraps

Massive data analysis becomes increasingly prevalent, subsampling methods like BLB (Bag of Little Bootstraps) serves as powerful tools for assessing the quality of estimators for massive data. However, the performance of the subsampling methods are highly influenced by the selection of tuning parameters ( e.g., the subset size, number of resamples per subset ). In this article we develop a hyperparameter selection methodology, which can be used to select tuning parameters for subsampling methods. Specifically, by a careful theoretical analysis, we find an analytically simple and elegant relationship between the asymptotic efficiency of various subsampling estimators and their hyperparameters. This leads to an optimal choice of the hyperparameters. More specifically, for an arbitrarily specified hyperparameter set, we can improve it to be a new set of hyperparameters with no extra CPU time cost, but the resulting estimator's statistical efficiency can be much improved. Both simulation studies and real data analysis demonstrate the superior advantage of our method.

arXiv:2006.00844

Distilling Neural Networks for Greener and Faster Dependency Parsing

The carbon footprint of natural language processing research has been increasing in recent years due to its reliance on large and inefficient neural network implementations. Distillation is a network compression technique which attempts to impart knowledge from a large model to a smaller one. We use teacher-student distillation to improve the efficiency of the Biaffine dependency parser which obtains state-of-the-art performance with respect to accuracy and parsing speed (Dozat and Manning, 2017). When distilling to 20\% of the original model's trainable parameters, we only observe an average decrease of $\sim$1 point for both UAS and LAS across a number of diverse Universal Dependency treebanks while being 2.30x (1.19x) faster than the baseline model on CPU (GPU) at inference time. We also observe a small increase in performance when compressing to 80\% for some treebanks. Finally, through distillation we attain a parser which is not only faster but also more accurate than the fastest modern parser on the Penn Treebank.

arXiv:2006.00816

Real-Time Face and Landmark Localization for Eyeblink Detection

Pavlovian eyeblink conditioning is a powerful experiment used in the field of neuroscience to measure multiple aspects of how we learn in our daily life. To track the movement of the eyelid during an experiment, researchers have traditionally made use of potentiometers or electromyography. More recently, the use of computer vision and image processing alleviated the need for these techniques but currently employed methods require human intervention and are not fast enough to enable real-time processing. In this work, a face- and landmark-detection algorithm have been carefully combined in order to provide fully automated eyelid tracking, and have further been accelerated to make the first crucial step towards online, closed-loop experiments. Such experiments have not been achieved so far and are expected to offer significant insights in the workings of neurological and psychiatric disorders. Based on an extensive literature search, various different algorithms for face detection and landmark detection have been analyzed and evaluated. Two algorithms were identified as most suitable for eyelid detection: the Histogram-of-Oriented-Gradients (HOG) algorithm for face detection and the Ensemble-of-Regression-Trees (ERT) algorithm for landmark detection. These two algorithms have been accelerated on GPU and CPU, achieving speedups of 1,753$\times$ and 11$\times$, respectively. To demonstrate the usefulness of our eyelid-detection algorithm, a research hypothesis was formed and a well-established neuroscientific experiment was employed: eyeblink detection. Our experimental evaluation reveals an overall application runtime of 0.533 ms per frame, which is 1,101$\times$ faster than the sequential implementation and well within the real-time requirements of eyeblink conditioning in humans, i.e. faster than 500 frames per second.

arXiv:2006.00568

A General-Purpose Dehazing Algorithm based on Local Contrast Enhancement Approaches

Dehazing is in the image processing and computer vision communities, the task of enhancing the image taken in foggy conditions. To better understand this type of algorithm, we present in this document a dehazing method which is suitable for several local contrast adjustment algorithms. We base it on two filters. The first filter is built with a step of normalization with some other statistical tricks while the last represents the local contrast improvement algorithm. Thus, it can work on both CPU and GPU for real-time applications. We hope that our approach will open the door to new ideas in the community. Other advantages of our method are first that it does not need to be trained, then it does not need additional optimization processing. Furthermore, it can be used as a pre-treatment or post-processing step in many vision tasks. In addition, it does not need to convert the problem into a physical interpretation, and finally that it is very fast. This family of defogging algorithms is fairly simple, but it shows promising results compared to state-of-the-art algorithms based not only on a visual assessment but also on objective criteria.

arXiv:2005.14187공식 코드 · Papers with Code

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search. We first construct a large design space with $\textit{arbitrary encoder-decoder attention}$ and $\textit{heterogeneous layers}$. Then we train a $\textit{SuperTransformer}$ that covers all candidates in the design space, and efficiently produces many $\textit{SubTransformers}$ with weight sharing. Finally, we perform an evolutionary search with a hardware latency constraint to find a specialized $\textit{SubTransformer}$ dedicated to run fast on the target hardware. Extensive experiments on four machine translation tasks demonstrate that HAT can discover efficient models for different hardware (CPU, GPU, IoT device). When running WMT'14 translation task on Raspberry Pi-4, HAT can achieve $\textbf{3}\times$ speedup, $\textbf{3.7}\times$ smaller size over baseline Transformer; $\textbf{2.7}\times$ speedup, $\textbf{3.6}\times$ smaller size over Evolved Transformer with $\textbf{12,041}\times$ less search cost and no performance loss. HAT code is https://github.com/mit-han-lab/hardware-aware-transformers.git

arXiv:2005.12073공식 코드 · Papers with Code

Visual Attention: Deep Rare Features

Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning (DNNs) drastically improved the algorithms efficiency on the main benchmark datasets. However, DNN-based models are counter-intuitive: surprising or unusual data is by definition difficult to learn because of its low occurrence probability. In reality, DNNs models mainly learn top-down features such as faces, text, people, or animals which usually attract human attention, but they have low efficiency in extracting surprising or unusual data in the images. In this paper, we propose a model called DeepRare2019 (DR) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms. DR 1) does not need any training, 2) it takes less than a second per image on CPU only and 3) our tests on three very different eye-tracking datasets show that DR is generic and is always in the top-3 models on all datasets and metrics while no other model exhibits such a regularity and genericity. DeepRare2019 code can be found at https://github.com/numediart/VisualAttention-RareFamily

arXiv:2005.10635공식 코드 · Papers with Code

SymJAX: symbolic CPU/GPU/TPU programming

SymJAX is a symbolic programming version of JAX simplifying graph input/output/updates and providing additional functionalities for general machine learning and deep learning applications. From an user perspective SymJAX provides a la Theano experience with fast graph optimization/compilation and broad hardware support, along with Lasagne-like deep learning functionalities.

arXiv:2005.10098

Classification of Industrial Control Systems screenshots using Transfer Learning

Industrial Control Systems depend heavily on security and monitoring protocols. Several tools are available for this purpose, which scout vulnerabilities and take screenshots from various control panels for later analysis. However, they do not adequately classify images into specific control groups, which can difficult operations performed by manual operators. In order to solve this problem, we use transfer learning with five CNN architectures, pre-trained on Imagenet, to determine which one best classifies screenshots obtained from Industrial Controls Systems. Using 337 manually labeled images, we train these architectures and study their performance both in accuracy and CPU and GPU time. We find out that MobilenetV1 is the best architecture based on its 97,95% of F1-Score, and its speed on CPU with 0.47 seconds per image. In systems where time is critical and GPU is available, VGG16 is preferable because it takes 0.04 seconds to process images, but dropping performance to 87,67%.

arXiv:2005.08497

Attention-based Transducer for Online Speech Recognition

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal Classification (CTC), RNN-T has some clear advantages given that it supports streaming recognition and does not have frame-independency assumption. Although significant progresses have been made for RNN-T research, it is still facing performance challenges in terms of training speed and accuracy. We propose attention-based transducer with modification over RNN-T in two aspects. First, we introduce chunk-wise attention in the joint network. Second, self-attention is introduced in the encoder. Our proposed model outperforms RNN-T for both training speed and accuracy. For training, we achieves over 1.7x speedup. With 500 hours LAIX non-native English training data, attention-based transducer yields ~10.6% WER reduction over baseline RNN-T. Trained with full set of over 10K hours data, our final system achieves ~5.5% WER reduction over that trained with the best Kaldi TDNN-f recipe. After 8-bit weight quantization without WER degradation, RTF and latency drop to 0.34~0.36 and 268~409 milliseconds respectively on a single CPU core of a production server.

arXiv:2005.08766

Evaluating Performance of an Adult Pornography Classifier for Child Sexual Abuse Detection

The information technology revolution has facilitated reaching pornographic material for everyone, including minors who are the most vulnerable in case they were abused. Accuracy and time performance are features desired by forensic tools oriented to child sexual abuse detection, whose main components may rely on image or video classifiers. In this paper, we identify which are the hardware and software requirements that may affect the performance of a forensic tool. We evaluated the adult porn classifier proposed by Yahoo, based on Deep Learning, into two different OS and four Hardware configurations, with two and four different CPU and GPU, respectively. The classification speed on Ubuntu Operating System is $~5$ and $~2$ times faster than on Windows 10, when a CPU and GPU are used, respectively. We demonstrate the superiority of a GPU-based machine rather than a CPU-based one, being $7$ to $8$ times faster. Finally, we prove that the upward and downward interpolation process conducted while resizing the input images do not influence the performance of the selected prediction model.