PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2009.04323

VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents numerous challenges: It should improve the performance when the input signal consists of overlapped speech, and must not hurt the speech recognition performance under all other acoustic conditions. Besides, this model must be tiny, fast, and perform inference in a streaming fashion, in order to have minimal impact on CPU, memory, battery and latency. We propose novel techniques to meet these multi-faceted requirements, including using a new asymmetric loss, and adopting adaptive runtime suppression strength. We also show that such a model can be quantized as a 8-bit integer model and run in realtime.

arXiv:2009.02353

Running Neural Networks on the NIC

In this paper we show that the data plane of commodity programmable (Network Interface Cards) NICs can run neural network inference tasks required by packet monitoring applications, with low overhead. This is particularly important as the data transfer costs to the host system and dedicated machine learning accelerators, e.g., GPUs, can be more expensive than the processing task itself. We design and implement our system -- N3IC -- on two different NICs and we show that it can greatly benefit three different network monitoring use cases that require machine learning inference as first-class-primitive. N3IC can perform inference for millions of network flows per second, while forwarding traffic at 40Gb/s. Compared to an equivalent solution implemented on a general purpose CPU, N3IC can provide 100x lower processing latency, with 1.5x increase in throughput.

arXiv:2009.02784

An FPGA Accelerated Method for Training Feed-forward Neural Networks Using Alternating Direction Method of Multipliers and LSMR

In this project, we have successfully designed, implemented, deployed and tested a novel FPGA accelerated algorithm for neural network training. The algorithm itself was developed in an independent study option. This training method is based on Alternating Direction Method of Multipliers algorithm, which has strong parallel characteristics and avoids procedures such as matrix inversion that are problematic in hardware designs by employing LSMR. As an intermediate stage, we fully implemented the ADMM-LSMR method in C language for feed-forward neural networks with a flexible number of layers and hidden size. We demonstrated that the method can operate with fixed-point arithmetic without compromising the accuracy. Next, we devised an FPGA accelerated version of the algorithm using Intel FPGA SDK for OpenCL and performed extensive optimisation stages followed by successful deployment of the program on an Intel Arria 10 GX FPGA. The FPGA accelerated program showed up to 6 times speed up comparing to equivalent CPU implementation while achieving promising accuracy.

arXiv:2009.01845공식 코드 · Papers with Code

Qibo: a framework for quantum simulation with hardware acceleration

We present Qibo, a new open-source software for fast evaluation of quantum circuits and adiabatic evolution which takes full advantage of hardware accelerators. The growing interest in quantum computing and the recent developments of quantum hardware devices motivates the development of new advanced computational tools focused on performance and usage simplicity. In this work we introduce a new quantum simulation framework that enables developers to delegate all complicated aspects of hardware or platform implementation to the library so they can focus on the problem and quantum algorithms at hand. This software is designed from scratch with simulation performance, code simplicity and user friendly interface as target goals. It takes advantage of hardware acceleration such as multi-threading CPU, single GPU and multi-GPU devices.

arXiv:2009.00100공식 코드 · Papers with Code

Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets.

arXiv:2008.13571

Machine learning thermal circuit network model for thermal design optimization of electronic circuit board layout with transient heating chips

This paper describes a method combining Bayesian optimization (BO) and a lamped-capacitance thermal circuit network model that is effective for speeding up the thermal design optimization of an electronic circuit board layout with transient heating chips. As electronic devices have become smaller and more complex, the importance of thermal design optimization to ensure heat dissipation performance has increased. However, such thermal design optimization is difficult because it is necessary to consider various trade-offs associated with packaging and transient temperature changes of heat-generating components. This study aims to improve the performance of thermal design optimization by artificial intelligence. BO using a Gaussian process was combined with the lamped-capacitance thermal circuit network model, and its performance was verified by case studies. As a result, BO successfully found the ideal circuit board layout as well as particle swarm optimization (PSO) and genetic algorithm (GA) could. The CPU time for BO was 1/5 and 1/4 of that for PSO and GA, respectively. In addition, BO found a non-intuitive optimal solution in approximately 7 minutes from 10 million layout patterns. It was estimated that this was 1/1000 of the CPU time required for analyzing all layout patterns.

arXiv:2008.12085

DMD: A Large-Scale Multi-Modal Driver Monitoring Dataset for Attention and Alertness Analysis

Vision is the richest and most cost-effective technology for Driver Monitoring Systems (DMS), especially after the recent success of Deep Learning (DL) methods. The lack of sufficiently large and comprehensive datasets is currently a bottleneck for the progress of DMS development, crucial for the transition of automated driving from SAE Level-2 to SAE Level-3. In this paper, we introduce the Driver Monitoring Dataset (DMD), an extensive dataset which includes real and simulated driving scenarios: distraction, gaze allocation, drowsiness, hands-wheel interaction and context data, in 41 hours of RGB, depth and IR videos from 3 cameras capturing face, body and hands of 37 drivers. A comparison with existing similar datasets is included, which shows the DMD is more extensive, diverse, and multi-purpose. The usage of the DMD is illustrated by extracting a subset of it, the dBehaviourMD dataset, containing 13 distraction activities, prepared to be used in DL training processes. Furthermore, we propose a robust and real-time driver behaviour recognition system targeting a real-world application that can run on cost-efficient CPU-only platforms, based on the dBehaviourMD. Its performance is evaluated with different types of fusion strategies, which all reach enhanced accuracy still providing real-time response.

arXiv:2008.11359

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems

Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is associated with a scalar, GNNs attach a feature tensor to each vertex/edge. This additional feature dimension, along with consequently more complex vertex- and edge-wise computations, has enormous implications on locality and parallelism, which existing graph processing systems fail to exploit. This paper proposes FeatGraph to accelerate GNN workloads by co-optimizing graph traversal and feature dimension computation. FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge. FeatGraph incorporates optimizations for graph traversal into the sparse templates and allows users to specify optimizations for UDFs with a feature dimension schedule (FDS). FeatGraph speeds up end-to-end GNN training and inference by up to 32x on CPU and 7x on GPU.

arXiv:2008.08178

Discovering Multi-Hardware Mobile Models via Architecture Search

Hardware-aware neural architecture designs have been predominantly focusing on optimizing model performance on single hardware and model development complexity, where another important factor, model deployment complexity, has been largely ignored. In this paper, we argue that, for applications that may be deployed on multiple hardware, having different single-hardware models across the deployed hardware makes it hard to guarantee consistent outputs across hardware and duplicates engineering work for debugging and fixing. To minimize such deployment cost, we propose an alternative solution, multi-hardware models, where a single architecture is developed for multiple hardware. With thoughtful search space design and incorporating the proposed multi-hardware metrics in neural architecture search, we discover multi-hardware models that give state-of-the-art (SoTA) performance across multiple hardware in both average and worse case scenarios. For performance on individual hardware, the single multi-hardware model yields similar or better results than SoTA performance on accelerators like GPU, DSP and EdgeTPU which was achieved by different models, while having similar performance with MobilenetV3 Large Minimalistic model on mobile CPU.

arXiv:2008.06142공식 코드 · Papers with Code

Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network

Purpose: To develop a convolutional neural network (CNN) solution for robust landmark detection in cardiac MR images. Methods: This retrospective study included cine, LGE and T1 mapping scans from two hospitals. The training set included 2,329 patients and 34,019 images. A hold-out test set included 531 patients and 7,723 images. CNN models were developed to detect two mitral valve plane and apical points on long-axis (LAX) images. On short-axis (SAX) images, anterior and posterior RV insertion points and LV center were detected. Model outputs were compared to manual labels by two operators for accuracy with a t-test for statistical significance. The trained model was deployed to MR scanners. Results: For the LAX images, success detection was 99.8% for cine, 99.4% for LGE. For the SAX, success rate was 96.6%, 97.6% and 98.9% for cine, LGE and T1-mapping. The L2 distances between model and manual labels were 2 to 3.5 mm, indicating close agreement between model landmarks to manual labels. No significant differences were found for the anterior RV insertion angle and LV length by the models and operators for all views and imaging sequences. Model inference on MR scanner took 610ms/5.6s on GPU/CPU, respectively, for a typical cardiac cine series. Conclusions: This study developed, validated and deployed a CNN solution for robust landmark detection in both long and short-axis CMR images for cine, LGE and T1 mapping sequences, with the accuracy comparable to the inter-operator variation.

arXiv:2008.07119

Generative Design by Reinforcement Learning: Enhancing the Diversity of Topology Optimization Designs

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse topology designs, which cannot be represented by conventional parametric design approaches. Recently, data-driven topology optimization research has started to exploit artificial intelligence, such as deep learning or machine learning, to improve the capability of design exploration. This study proposes a reinforcement learning (RL) based generative design process, with reward functions maximizing the diversity of topology designs. We formulate generative design as a sequential problem of finding optimal design parameter combinations in accordance with a given reference design. Proximal Policy Optimization is used as the learning framework, which is demonstrated in the case study of an automotive wheel design problem. To reduce the heavy computational burden of the wheel topology optimization process required by our RL formulation, we approximate the optimization process with neural networks. With efficient data preprocessing/augmentation and neural architecture, the neural networks achieve a generalized performance and symmetricity-reserving characteristics. We show that RL-based generative design produces a large number of diverse designs within a short inference time by exploiting GPU in a fully automated manner. It is different from the previous approach using CPU which takes much more processing time and involving human intervention.

arXiv:2008.05000

Degree-Quant: Quantization-Aware Training for Graph Neural Networks

Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there exists little research exploring methods to make them more efficient at inference time. In this work, we explore the viability of training quantized GNNs, enabling the usage of low precision integer arithmetic during inference. We identify the sources of error that uniquely arise when attempting to quantize GNNs, and propose an architecturally-agnostic method, Degree-Quant, to improve performance over existing quantization-aware training baselines commonly used on other architectures, such as CNNs. We validate our method on six datasets and show, unlike previous attempts, that models generalize to unseen graphs. Models trained with Degree-Quant for INT8 quantization perform as well as FP32 models in most cases; for INT4 models, we obtain up to 26% gains over the baselines. Our work enables up to 4.7x speedups on CPU when using INT8 arithmetic.

arXiv:2008.04885공식 코드 · Papers with Code

The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020

We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, distributed mixed precision training, and efficient CPU decoding with 8-bit quantization. These improvements result in faster training and inference, higher automatic metric scores, and a shorter path from research to production.

arXiv:2008.03802공식 코드 · Papers with Code

SpeedySpeech: Efficient Neural Speech Synthesis

While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. We propose a student-teacher network capable of high-quality faster-than-real-time spectrogram synthesis, with low requirements on computational resources and fast training time. We show that self-attention layers are not necessary for generation of high quality audio. We utilize simple convolutional blocks with residual connections in both student and teacher networks and use only a single attention layer in the teacher model. Coupled with a MelGAN vocoder, our model's voice quality was rated significantly higher than Tacotron 2. Our model can be efficiently trained on a single GPU and can run in real time even on a CPU. We provide both our source code and audio samples in our GitHub repository.

arXiv:2008.03704

Learning Consistency Pursued Correlation Filters for Real-Time UAV Tracking

Correlation filter (CF)-based methods have demonstrated exceptional performance in visual object tracking for unmanned aerial vehicle (UAV) applications, but suffer from the undesirable boundary effect. To solve this issue, spatially regularized correlation filters (SRDCF) proposes the spatial regularization to penalize filter coefficients, thereby significantly improving the tracking performance. However, the temporal information hidden in the response maps is not considered in SRDCF, which limits the discriminative power and the robustness for accurate tracking. This work proposes a novel approach with dynamic consistency pursued correlation filters, i.e., the CPCF tracker. Specifically, through a correlation operation between adjacent response maps, a practical consistency map is generated to represent the consistency level across frames. By minimizing the difference between the practical and the scheduled ideal consistency map, the consistency level is constrained to maintain temporal smoothness, and rich temporal information contained in response maps is introduced. Besides, a dynamic constraint strategy is proposed to further improve the adaptability of the proposed tracker in complex situations. Comprehensive experiments are conducted on three challenging UAV benchmarks, i.e., UAV123@10FPS, UAVDT, and DTB70. Based on the experimental results, the proposed tracker favorably surpasses the other 25 state-of-the-art trackers with real-time running speed ($\sim$43FPS) on a single CPU.

arXiv:2008.03915공식 코드 · Papers with Code

Automatic Failure Recovery and Re-Initialization for Online UAV Tracking with Joint Scale and Aspect Ratio Optimization

Current unmanned aerial vehicle (UAV) visual tracking algorithms are primarily limited with respect to: (i) the kind of size variation they can deal with, (ii) the implementation speed which hardly meets the real-time requirement. In this work, a real-time UAV tracking algorithm with powerful size estimation ability is proposed. Specifically, the overall tracking task is allocated to two 2D filters: (i) translation filter for location prediction in the space domain, (ii) size filter for scale and aspect ratio optimization in the size domain. Besides, an efficient two-stage re-detection strategy is introduced for long-term UAV tracking tasks. Large-scale experiments on four UAV benchmarks demonstrate the superiority of the presented method which has computation feasibility on a low-cost CPU.

arXiv:2008.03912

DR^2Track: Towards Real-Time Visual Tracking for UAV via Distractor Repressed Dynamic Regression

Visual tracking has yielded promising applications with unmanned aerial vehicle (UAV). In literature, the advanced discriminative correlation filter (DCF) type trackers generally distinguish the foreground from the background with a learned regressor which regresses the implicit circulated samples into a fixed target label. However, the predefined and unchanged regression target results in low robustness and adaptivity to uncertain aerial tracking scenarios. In this work, we exploit the local maximum points of the response map generated in the detection phase to automatically locate current distractors. By repressing the response of distractors in the regressor learning, we can dynamically and adaptively alter our regression target to leverage the tracking robustness as well as adaptivity. Substantial experiments conducted on three challenging UAV benchmarks demonstrate both excellent performance and extraordinary speed (~50fps on a cheap CPU) of our tracker.

arXiv:2008.02891

Mesh sampling and weighting for the hyperreduction of nonlinear Petrov-Galerkin reduced-order models with local reduced-order bases

The energy-conserving sampling and weighting (ECSW) method is a hyperreduction method originally developed for accelerating the performance of Galerkin projection-based reduced-order models (PROMs) associated with large-scale finite element models, when the underlying projected operators need to be frequently recomputed as in parametric and/or nonlinear problems. In this paper, this hyperreduction method is extended to Petrov-Galerkin PROMs where the underlying high-dimensional models can be associated with arbitrary finite element, finite volume, and finite difference semi-discretization methods. Its scope is also extended to cover local PROMs based on piecewise-affine approximation subspaces, such as those designed for mitigating the Kolmogorov $n$-width barrier issue associated with convection-dominated flow problems. The resulting ECSW method is shown in this paper to be robust and accurate. In particular, its offline phase is shown to be fast and parallelizable, and the potential of its online phase for large-scale applications of industrial relevance is demonstrated for turbulent flow problems with $O(10^7)$ and $O(10^8)$ degrees of freedom. For such problems, the online part of the ECSW method proposed in this paper for Petrov-Galerkin PROMs is shown to enable wall-clock time and CPU time speedup factors of several orders of magnitude while delivering exceptional accuracy.

arXiv:2008.01896

A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint

Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning. Nevertheless, the efficiency and performance of the existing registration algorithms can still be improved. In this paper, we propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registrations. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed to improve the robustness and achieve end-to-end registration. Furthermore, a dual consistency constraint and a new prior knowledge-based loss function are developed to enhance the registration performances. The proposed method has been evaluated on a clinical dataset containing 555 cases, and encouraging performances have been achieved. Compared to the commonly utilized registration methods, including VoxelMorph, SyN, and LT-Net, the proposed method achieves better registration performance with a Dice score of 0.8397 in identifying stroke lesions. With regards to the registration speed, our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU. Moreover, we prove that our method can still perform well on more challenging tasks with lacking scanning information data, showing high robustness for the clinical application.

arXiv:2008.01814공식 코드 · Papers with Code

A Case For Adaptive Deep Neural Networks in Edge Computing

Edge computing offers an additional layer of compute infrastructure closer to the data source before raw data from privacy-sensitive and performance-critical applications is transferred to a cloud data center. Deep Neural Networks (DNNs) are one class of applications that are reported to benefit from collaboratively computing between the edge and the cloud. A DNN is partitioned such that specific layers of the DNN are deployed onto the edge and the cloud to meet performance and privacy objectives. However, there is limited understanding of: (a) whether and how evolving operational conditions (increased CPU and memory utilization at the edge or reduced data transfer rates between the edge and the cloud) affect the performance of already deployed DNNs, and (b) whether a new partition configuration is required to maximize performance. A DNN that adapts to changing operational conditions is referred to as an 'adaptive DNN'. This paper investigates whether there is a case for adaptive DNNs in edge computing by considering three questions: (i) Are DNNs sensitive to operational conditions? (ii) How sensitive are DNNs to operational conditions? (iii) Do individual or a combination of operational conditions equally affect DNNs? (iv) Is DNN partitioning sensitive to hardware architectures on the cloud/edge? The exploration is carried out in the context of 8 pre-trained DNN models and the results presented are from analyzing nearly 8 million data points. The results highlight that network conditions affects DNN performance more than CPU or memory related operational conditions. Repartitioning is noted to provide a performance gain in a number of cases, but a specific trend was not noted in relation to its correlation to the underlying hardware architecture. Nonetheless, the need for adaptive DNNs is confirmed.