PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.01779공식 코드 · Papers with Code

Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection

RGB-D salient object detection (SOD) recently has attracted increasing research interest by benefiting conventional RGB SOD with extra depth information. However, existing RGB-D SOD models often fail to perform well in terms of both efficiency and accuracy, which hinders their potential applications on mobile devices and real-world problems. An underlying challenge is that the model accuracy usually degrades when the model is simplified to have few parameters. To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy. DQFM resorts to the alignment of low-level RGB and depth features, as well as holistic attention of the depth stream to explicitly control and enhance cross-modal fusion. We embed DQFM to obtain an efficient light-weight model called DFM-Net, where we also design a tailored depth backbone and a two-stage decoder for further efficiency consideration. Extensive experimental results demonstrate that our DFM-Net achieves state-of-the-art accuracy when comparing to existing non-efficient models, and meanwhile runs at 140ms on CPU (2.2$\times$ faster than the prior fastest efficient model) with only $\sim$8.5Mb model size (14.9% of the prior lightest). Our code will be available at https://github.com/zwbx/DFM-Net.

arXiv:2107.01056

Structural biology in the clouds: The WeNMR-EOSC Ecosystem

Structural biology aims at characterizing the structural and dynamic properties of biological macromolecules at atomic details. Gaining insight into three dimensional structures of biomolecules and their interactions is critical for understanding the vast majority of cellular processes, with direct applications in health and food sciences. Since 2010, the WeNMR project (www.wenmr.eu) has implemented numerous web-based services to facilitate the use of advanced computational tools by researchers in the field, using the high throughput computing infrastructure provided by EGI. These services have been further developed in subsequent initiatives under H2020 projects and are now operating as Thematic Services in the European Open Science Cloud (EOSC) portal (www.eosc-portal.eu), sending >12 millions of jobs and using around 4000 CPU-years per year. Here we review 10 years of successful e-infrastructure solutions serving a large worldwide community of over 23,000 users to date, providing them with user-friendly, web-based solutions that run complex workflows in structural biology. The current set of active WeNMR portals are described, together with the complex backend machinery that allows distributed computing resources to be harvested efficiently.

arXiv:2106.15335공식 코드 · Papers with Code

Privacy Budget Scheduling

Machine learning (ML) models trained on personal data have been shown to leak information about users. Differential privacy (DP) enables model training with a guaranteed bound on this leakage. Each new model trained with DP increases the bound on data leakage and can be seen as consuming part of a global privacy budget that should not be exceeded. This budget is a scarce resource that must be carefully managed to maximize the number of successfully trained models. We describe PrivateKube, an extension to the popular Kubernetes datacenter orchestrator that adds privacy as a new type of resource to be managed alongside other traditional compute resources, such as CPU, GPU, and memory. The abstractions we design for the privacy resource mirror those defined by Kubernetes for traditional resources, but there are also major differences. For example, traditional compute resources are replenishable while privacy is not: a CPU can be regained after a model finishes execution while privacy budget cannot. This distinction forces a re-design of the scheduler. We present DPF (Dominant Private Block Fairness) -- a variant of the popular Dominant Resource Fairness (DRF) algorithm -- that is geared toward the non-replenishable privacy resource but enjoys similar theoretical properties as DRF. We evaluate PrivateKube and DPF on microbenchmarks and an ML workload on Amazon Reviews data. Compared to existing baselines, DPF allows training more models under the same global privacy guarantee. This is especially true for DPF over R\'enyi DP, a highly composable form of DP.

arXiv:2106.15214

Joint Majorization-Minimization for Nonnegative Matrix Factorization with the $β$-divergence

This article proposes new multiplicative updates for nonnegative matrix factorization (NMF) with the $\beta$-divergence objective function. Our new updates are derived from a joint majorization-minimization (MM) scheme, in which an auxiliary function (a tight upper bound of the objective function) is built for the two factors jointly and minimized at each iteration. This is in contrast with the classic approach in which a majorizer is derived for each factor separately. Like that classic approach, our joint MM algorithm also results in multiplicative updates that are simple to implement. They however yield a significant drop of computation time (for equally good solutions), in particular for some $\beta$-divergences of important applicative interest, such as the squared Euclidean distance and the Kullback-Leibler or Itakura-Saito divergences. We report experimental results using diverse datasets: face images, an audio spectrogram, hyperspectral data and song play counts. Depending on the value of $\beta$ and on the dataset, our joint MM approach can yield CPU time reductions from about $13\%$ to $78\%$ in comparison to the classic alternating scheme.

arXiv:2106.12942

High Performance Hyperspectral Image Classification using Graphics Processing Units

Real-time remote sensing applications like search and rescue missions, military target detection, environmental monitoring, hazard prevention and other time-critical applications require onboard real time processing capabilities or autonomous decision making. Some unmanned remote systems like satellites are physically remote from their operators, and all control of the spacecraft and data returned by the spacecraft must be transmitted over a wireless radio link. This link may not be available for extended periods when the satellite is out of line of sight of its ground station. Therefore, lightweight, small size and low power consumption hardware is essential for onboard real time processing systems. With increasing dimensionality, size and resolution of recent hyperspectral imaging sensors, additional challenges are posed upon remote sensing processing systems and more capable computing architectures are needed. Graphical Processing Units (GPUs) emerged as promising architecture for light weight high performance computing that can address these computational requirements for onboard systems. The goal of this study is to build high performance methods for onboard hyperspectral analysis. We propose accelerated methods for the well-known recursive hierarchical segmentation (RHSEG) clustering method, using GPUs, hybrid multicore CPU with a GPU and hybrid multi-core CPU/GPU clusters. RHSEG is a method developed by the National Aeronautics and Space Administration (NASA), which is designed to provide rich classification information with several output levels. The achieved speedups by parallel solutions compared to CPU sequential implementations are 21x for parallel single GPU and 240x for hybrid multi-node computer clusters with 16 computing nodes. The energy consumption is reduced to 74% using a single GPU compared to the equivalent parallel CPU cluster.

arXiv:2106.11075

EML Online Speech Activity Detection for the Fearless Steps Challenge Phase-III

Speech Activity Detection (SAD), locating speech segments within an audio recording, is a main part of most speech technology applications. Robust SAD is usually more difficult in noisy conditions with varying signal-to-noise ratios (SNR). The Fearless Steps challenge has recently provided such data from the NASA Apollo-11 mission for different speech processing tasks including SAD. Most audio recordings are degraded by different kinds and levels of noise varying within and between channels. This paper describes the EML online algorithm for the most recent phase of this challenge. The proposed algorithm can be trained both in a supervised and unsupervised manner and assigns speech and non-speech labels at runtime approximately every 0.1 sec. The experimental results show a competitive accuracy on both development and evaluation datasets with a real-time factor of about 0.002 using a single CPU machine.

arXiv:2106.10240

VSAC: Efficient and Accurate Estimator for H and F

We present VSAC, a RANSAC-type robust estimator with a number of novelties. It benefits from the introduction of the concept of independent inliers that improves significantly the efficacy of the dominant plane handling and, also, allows near error-free rejection of incorrect models, without false positives. The local optimization process and its application is improved so that it is run on average only once. Further technical improvements include adaptive sequential hypothesis verification and efficient model estimation via Gaussian elimination. Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU. It is two orders of magnitude faster and yet as precise as MAGSAC++, the currently most accurate estimator of two-view geometry. In the repeated runs on EVD, HPatches, PhotoTourism, and Kusvod2 datasets, it never failed.

arXiv:2106.08921

A Spiking Neural Network for Image Segmentation

We seek to investigate the scalability of neuromorphic computing for computer vision, with the objective of replicating non-neuromorphic performance on computer vision tasks while reducing power consumption. We convert the deep Artificial Neural Network (ANN) architecture U-Net to a Spiking Neural Network (SNN) architecture using the Nengo framework. Both rate-based and spike-based models are trained and optimized for benchmarking performance and power, using a modified version of the ISBI 2D EM Segmentation dataset consisting of microscope images of cells. We propose a partitioning method to optimize inter-chip communication to improve speed and energy efficiency when deploying multi-chip networks on the Loihi neuromorphic chip. We explore the advantages of regularizing firing rates of Loihi neurons for converting ANN to SNN with minimum accuracy loss and optimized energy consumption. We propose a percentile based regularization loss function to limit the spiking rate of the neuron between a desired range. The SNN is converted directly from the corresponding ANN, and demonstrates similar semantic segmentation as the ANN using the same number of neurons and weights. However, the neuromorphic implementation on the Intel Loihi neuromorphic chip is over 2x more energy-efficient than conventional hardware (CPU, GPU) when running online (one image at a time). These power improvements are achieved without sacrificing the task performance accuracy of the network, and when all weights (Loihi, CPU, and GPU networks) are quantized to 8 bits.

arXiv:2106.08846

Algorithm to Compilation Co-design: An Integrated View of Neural Network Sparsity

Reducing computation cost, inference latency, and memory footprint of neural networks are frequently cited as research motivations for pruning and sparsity. However, operationalizing those benefits and understanding the end-to-end effect of algorithm design and regularization on the runtime execution is not often examined in depth. Here we apply structured and unstructured pruning to attention weights of transformer blocks of the BERT language model, while also expanding block sparse representation (BSR) operations in the TVM compiler. Integration of BSR operations enables the TVM runtime execution to leverage structured pattern sparsity induced by model regularization. This integrated view of pruning algorithms enables us to study relationships between modeling decisions and their direct impact on sparsity-enhanced execution. Our main findings are: 1) we validate that performance benefits of structured sparsity block regularization must be enabled by the BSR augmentations to TVM, with 4x speedup relative to vanilla PyTorch and 2.2x speedup relative to standard TVM compilation (without expanded BSR support). 2) for BERT attention weights, the end-to-end optimal block sparsity shape in this CPU inference context is not a square block (as in \cite{gray2017gpu}) but rather a linear 32x1 block 3) the relationship between performance and block size / shape is is suggestive of how model regularization parameters interact with task scheduler optimizations resulting in the observed end-to-end performance.

arXiv:2106.08150공식 코드 · Papers with Code

MetaCache-GPU: Ultra-Fast Metagenomic Classification

The cost of DNA sequencing has dropped exponentially over the past decade, making genomic data accessible to a growing number of scientists. In bioinformatics, localization of short DNA sequences (reads) within large genomic sequences is commonly facilitated by constructing index data structures which allow for efficient querying of substrings. Recent metagenomic classification pipelines annotate reads with taxonomic labels by analyzing their $k$-mer histograms with respect to a reference genome database. CPU-based index construction is often performed in a preprocessing phase due to the relatively high cost of building irregular data structures such as hash maps. However, the rapidly growing amount of available reference genomes establishes the need for index construction and querying at interactive speeds. In this paper, we introduce MetaCache-GPU -- an ultra-fast metagenomic short read classifier specifically tailored to fit the characteristics of CUDA-enabled accelerators. Our approach employs a novel hash table variant featuring efficient minhash fingerprinting of reads for locality-sensitive hashing and their rapid insertion using warp-aggregated operations. Our performance evaluation shows that MetaCache-GPU is able to build large reference databases in a matter of seconds, enabling instantaneous operability, while popular CPU-based tools such as Kraken2 require over an hour for index construction on the same data. In the context of an ever-growing number of reference genomes, MetaCache-GPU is the first metagenomic classifier that makes analysis pipelines with on-demand composition of large-scale reference genome sets practical. The source code is publicly available at https://github.com/muellan/metacache .

arXiv:2106.07927

ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices

With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the importance of embedded high-performance image processing has increased. For a long time, FPGAs were the only processing hardware that were capable of high-performance computing, while at the same time preserving a low power consumption, essential for embedded systems. However, the recently increasing availability of embedded GPU-based systems, such as the NVIDIA Jetson series, comprised of an ARM CPU and a NVIDIA Tegra GPU, allows for massively parallel embedded computing on graphics hardware. With this in mind, we propose an approach for real-time embedded stereo processing on ARM and CUDA-enabled devices, which is based on the popular and widely used Semi-Global Matching algorithm. In this, we propose an optimization of the algorithm for embedded CUDA GPUs, by using massively parallel computing, as well as using the NEON intrinsics to optimize the algorithm for vectorized SIMD processing on embedded ARM CPUs. We have evaluated our approach with different configurations on two public stereo benchmark datasets to demonstrate that they can reach an error rate as low as 3.3%. Furthermore, our experiments show that the fastest configuration of our approach reaches up to 46 FPS on VGA image resolution. Finally, in a use-case specific qualitative evaluation, we have evaluated the power consumption of our approach and deployed it on the DJI Manifold 2-G attached to a DJI Matrix 210v2 RTK unmanned aerial vehicle (UAV), demonstrating its suitability for real-time stereo processing onboard a UAV.

arXiv:2106.07551공식 코드 · Papers with Code

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated sequence of tasks arising from the coupled population dynamics. By leveraging auto-curricula to induce a population of distinct emergent strategies, PB-MARL has achieved impressive success in tackling multi-agent tasks. Despite remarkable prior arts of distributed RL frameworks, PB-MARL poses new challenges for parallelizing the training frameworks due to the additional complexity of multiple nested workloads between sampling, training and evaluation involved with heterogeneous policy interactions. To solve these problems, we present MALib, a scalable and efficient computing framework for PB-MARL. Our framework is comprised of three key components: (1) a centralized task dispatching model, which supports the self-generated tasks and scalable training with heterogeneous policy combinations; (2) a programming architecture named Actor-Evaluator-Learner, which achieves high parallelism for both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible deployments on different distributed computing paradigms. Experiments on a series of complex tasks such as multi-agent Atari Games show that MALib achieves throughput higher than 40K FPS on a single machine with $32$ CPU cores; 5x speedup than RLlib and at least 3x speedup than OpenSpiel in multi-agent training tasks. MALib is publicly available at https://github.com/sjtu-marl/malib.

arXiv:2106.06882공식 코드 · Papers with Code

Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2X or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance.

arXiv:2106.07136공식 코드 · Papers with Code

Bayesian dense inverse searching algorithm for real-time stereo matching in minimally invasive surgery

This paper reports a CPU-level real-time stereo matching method for surgical images (10 Hz on 640 * 480 image with a single core of i5-9400). The proposed method is built on the fast ''dense inverse searching'' algorithm, which estimates the disparity of the stereo images. The overlapping image patches (arbitrary squared image segment) from the images at different scales are aligned based on the photometric consistency presumption. We propose a Bayesian framework to evaluate the probability of the optimized patch disparity at different scales. Moreover, we introduce a spatial Gaussian mixed probability distribution to address the pixel-wise probability within the patch. In-vivo and synthetic experiments show that our method can handle ambiguities resulted from the textureless surfaces and the photometric inconsistency caused by the Lambertian reflectance. Our Bayesian method correctly balances the probability of the patch for stereo images at different scales. Experiments indicate that the estimated depth has higher accuracy and fewer outliers than the baseline methods in the surgical scenario.

arXiv:2106.06150

Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs

Graph neural networks (GNNs) are powerful tools for learning from graph data and are widely used in various applications such as social network recommendation, fraud detection, and graph search. The graphs in these applications are typically large, usually containing hundreds of millions of nodes. Training GNN models on such large graphs efficiently remains a big challenge. Despite a number of sampling-based methods have been proposed to enable mini-batch training on large graphs, these methods have not been proved to work on truly industry-scale graphs, which require GPUs or mixed-CPU-GPU training. The state-of-the-art sampling-based methods are usually not optimized for these real-world hardware setups, in which data movement between CPUs and GPUs is a bottleneck. To address this issue, we propose Global Neighborhood Sampling that aims at training GNNs on giant graphs specifically for mixed-CPU-GPU training. The algorithm samples a global cache of nodes periodically for all mini-batches and stores them in GPUs. This global cache allows in-GPU importance sampling of mini-batches, which drastically reduces the number of nodes in a mini-batch, especially in the input layer, to reduce data copy between CPU and GPU and mini-batch computation without compromising the training convergence rate or model accuracy. We provide a highly efficient implementation of this method and show that our implementation outperforms an efficient node-wise neighbor sampling baseline by a factor of 2X-4X on giant graphs. It outperforms an efficient implementation of LADIES with small layers by a factor of 2X-14X while achieving much higher accuracy than LADIES.We also theoretically analyze the proposed algorithm and show that with cached node data of a proper size, it enjoys a comparable convergence rate as the underlying node-wise sampling method.

arXiv:2106.03167

Mathematical Vocoder Algorithm : Modified Spectral Inversion for Efficient Neural Speech Synthesis

In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the training stage of the neural vocoder from the end-to-end speech synthesis model. Our implementation can synthesize high fidelity speech at approximately 20 Mhz on CPU and 59.6MHz on GPU. This is 909 and 2,702 times faster compared to real-time. Since the proposed methodology is not a data-driven method, it is applicable to unseen voices and multiple languages without any additional work. The proposed method is expected to adapt for researching on neural network models capable of synthesizing speech at the studio recording level.

arXiv:2106.02463

A Robust and Accurate Deep Learning based Pattern Recognition Framework for Upper Limb Prosthesis using sEMG

In EMG based pattern recognition (EMG-PR), deep learning-based techniques have become more prominent for their self-regulating capability to extract discriminant features from large data-sets. Moreover, the performance of traditional machine learning-based methods show limitation to categorize over a certain number of classes and degrades over a period of time. In this paper, an accurate, robust, and fast convolutional neural network-based framework for EMG pattern identification is presented. To assess the performance of the proposed system, five publicly available and benchmark data-sets of upper limb activities were used. This data-set contains 49 to 52 upper limb motions (NinaPro DB1, NinaPro DB2, and NinaPro DB3), Data with force variation, and data with arm position variation for intact and amputated subjects. The classification accuracies of 91.11% (53 classes), 89.45% (49 classes), 81.67% (49 classes of amputees), 95.67% (6 classes with force variation), and 99.11% (8 classes with arm position variation) have been observed during the testing and validation. The performance of the proposed system is compared with the state of art techniques in the literature. The findings demonstrate that classification accuracy and time complexity have improved significantly. Keras, TensorFlow's high-level API for constructing deep learning models, was used for signal pre-processing and deep-learning-based algorithms. The suggested method was run on an Intel 3.5GHz Core i7, 7th Gen CPU with 8GB DDR4 RAM.

arXiv:2106.02412

Resource Allocation in Disaggregated Data Centre Systems with Reinforcement Learning

Resource-disaggregated data centres (RDDC) propose a resource-centric, and high-utilisation architecture for data centres (DC), avoiding resource fragmentation and enabling arbitrarily sized resource pools to be allocated to tasks, rather than server-sized ones. RDDCs typically impose greater demand on the network, requiring more infrastructure and increasing cost and power, so new resource allocation algorithms that co-manage both server and networks resources are essential to ensure that allocation is not bottlenecked by the network, and that requests can be served successfully with minimal networking resources. We apply reinforcement learning (RL) to this problem for the first time and show that an RL policy based on graph neural networks can learn resource allocation policies end-to-end that outperform previous hand-engineered heuristics by up to 22.0\%, 42.6\% and 22.6\% for acceptance ratio, CPU and memory utilisation respectively, maintain performance when scaled up to RDDC topologies with $10^2\times$ more nodes than those seen during training and can achieve comparable performance to the best baselines while using $5.3\times$ less network resources.

arXiv:2106.02495공식 코드 · Papers with Code

ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking

Prior correlation filter (CF)-based tracking methods for unmanned aerial vehicles (UAVs) have virtually focused on tracking in the daytime. However, when the night falls, the trackers will encounter more harsh scenes, which can easily lead to tracking failure. In this regard, this work proposes a novel tracker with anti-dark function (ADTrack). The proposed method integrates an efficient and effective low-light image enhancer into a CF-based tracker. Besides, a target-aware mask is simultaneously generated by virtue of image illumination variation. The target-aware mask can be applied to jointly train a target-focused filter that assists the context filter for robust tracking. Specifically, ADTrack adopts dual regression, where the context filter and the target-focused filter restrict each other for dual filter learning. Exhaustive experiments are conducted on typical dark sceneries benchmark, consisting of 37 typical night sequences from authoritative benchmarks, i.e., UAVDark, and our newly constructed benchmark UAVDark70. The results have shown that ADTrack favorably outperforms other state-of-the-art trackers and achieves a real-time speed of 34 frames/s on a single CPU, greatly extending robust UAV tracking to night scenes.

arXiv:2106.01097

T-BERT -- Model for Sentiment Analysis of Micro-blogs Integrating Topic Model and BERT

Sentiment analysis (SA) has become an extensive research area in recent years impacting diverse fields including ecommerce, consumer business, and politics, driven by increasing adoption and usage of social media platforms. It is challenging to extract topics and sentiments from unsupervised short texts emerging in such contexts, as they may contain figurative words, strident data, and co-existence of many possible meanings for a single word or phrase, all contributing to obtaining incorrect topics. Most prior research is based on a specific theme/rhetoric/focused-content on a clean dataset. In the work reported here, the effectiveness of BERT(Bidirectional Encoder Representations from Transformers) in sentiment classification tasks from a raw live dataset taken from a popular microblogging platform is demonstrated. A novel T-BERT framework is proposed to show the enhanced performance obtainable by combining latent topics with contextual BERT embeddings. Numerical experiments were conducted on an ensemble with about 42000 datasets using NimbleBox.ai platform with a hardware configuration consisting of Nvidia Tesla K80(CUDA), 4 core CPU, 15GB RAM running on an isolated Google Cloud Platform instance. The empirical results show that the model improves in performance while adding topics to BERT and an accuracy rate of 90.81% on sentiment classification using BERT with the proposed approach.