PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2301.01454

Accurate, Low-latency, Efficient SAR Automatic Target Recognition on FPGA

Synthetic aperture radar (SAR) automatic target recognition (ATR) is the key technique for remote-sensing image recognition. The state-of-the-art convolutional neural networks (CNNs) for SAR ATR suffer from \emph{high computation cost} and \emph{large memory footprint}, making them unsuitable to be deployed on resource-limited platforms, such as small/micro satellites. In this paper, we propose a comprehensive GNN-based model-architecture {co-design} on FPGA to address the above issues. \emph{Model design}: we design a novel graph neural network (GNN) for SAR ATR. The proposed GNN model incorporates GraphSAGE layer operators and attention mechanism, achieving comparable accuracy as the state-of-the-art work with near $1/100$ computation cost. Then, we propose a pruning approach including weight pruning and input pruning. While weight pruning through lasso regression reduces most parameters without accuracy drop, input pruning eliminates most input pixels with negligible accuracy drop. \emph{Architecture design}: to fully unleash the computation parallelism within the proposed model, we develop a novel unified hardware architecture that can execute various computation kernels (feature aggregation, feature transformation, graph pooling). The proposed hardware design adopts the Scatter-Gather paradigm to efficiently handle the irregular computation {patterns} of various computation kernels. We deploy the proposed design on an embedded FPGA (AMD Xilinx ZCU104) and evaluate the performance using MSTAR dataset. Compared with the state-of-the-art CNNs, the proposed GNN achieves comparable accuracy with $1/3258$ computation cost and $1/83$ model size. Compared with the state-of-the-art CPU/GPU, our FPGA accelerator achieves $14.8\times$/$2.5\times$ speedup (latency) and is $62\times$/$39\times$ more energy efficient.

arXiv:2212.14647공식 코드 · Papers with Code

RL and Fingerprinting to Select Moving Target Defense Mechanisms for Zero-day Attacks in IoT

Cybercriminals are moving towards zero-day attacks affecting resource-constrained devices such as single-board computers (SBC). Assuming that perfect security is unrealistic, Moving Target Defense (MTD) is a promising approach to mitigate attacks by dynamically altering target attack surfaces. Still, selecting suitable MTD techniques for zero-day attacks is an open challenge. Reinforcement Learning (RL) could be an effective approach to optimize the MTD selection through trial and error, but the literature fails when i) evaluating the performance of RL and MTD solutions in real-world scenarios, ii) studying whether behavioral fingerprinting is suitable for representing SBC's states, and iii) calculating the consumption of resources in SBC. To improve these limitations, the work at hand proposes an online RL-based framework to learn the correct MTD mechanisms mitigating heterogeneous zero-day attacks in SBC. The framework considers behavioral fingerprinting to represent SBCs' states and RL to learn MTD techniques that mitigate each malicious state. It has been deployed on a real IoT crowdsensing scenario with a Raspberry Pi acting as a spectrum sensor. More in detail, the Raspberry Pi has been infected with different samples of command and control malware, rootkits, and ransomware to later select between four existing MTD techniques. A set of experiments demonstrated the suitability of the framework to learn proper MTD techniques mitigating all attacks (except a harmfulness rootkit) while consuming <1 MB of storage and utilizing <55% CPU and <80% RAM.

arXiv:2212.12180공식 코드 · Papers with Code

Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices

Achieving resource efficiency while preserving end-user experience is non-trivial for cloud application operators. As cloud applications progressively adopt microservices, resource managers are faced with two distinct levels of system behavior: end-to-end application latency and per-service resource usage. Translating between the two levels, however, is challenging because user requests traverse heterogeneous services that collectively (but unevenly) contribute to the end-to-end latency. We present Autothrottle, a bi-level resource management framework for microservices with latency SLOs (service-level objectives). It architecturally decouples application SLO feedback from service resource control, and bridges them through the notion of performance targets. Specifically, an application-wide learning-based controller is employed to periodically set performance targets -- expressed as CPU throttle ratios -- for per-service heuristic controllers to attain. We evaluate Autothrottle on three microservice applications, with workload traces from production scenarios. Results show superior CPU savings, up to 26.21% over the best-performing baseline and up to 93.84% over all baselines.

arXiv:2212.11506

Accelerating Barnes-Hut t-SNE Algorithm by Efficient Parallelization on Multi-Core CPUs

t-SNE remains one of the most popular embedding techniques for visualizing high-dimensional data. Most standard packages of t-SNE, such as scikit-learn, use the Barnes-Hut t-SNE (BH t-SNE) algorithm for large datasets. However, existing CPU implementations of this algorithm are inefficient. In this work, we accelerate the BH t-SNE on CPUs via cache optimizations, SIMD, parallelizing sequential steps, and improving parallelization of multithreaded steps. Our implementation (Acc-t-SNE) is up to 261x and 4x faster than scikit-learn and the state-of-the-art BH t-SNE implementation from daal4py, respectively, on a 32-core Intel(R) Icelake cloud instance.

arXiv:2212.10319

Image quality prediction using synthetic and natural codebooks: comparative results

We investigate a model for image/video quality assessment based on building a set of codevectors representing in a sense some basic properties of images, similar to well-known CORNIA model. We analyze the codebook building method and propose some modifications for it. Also the algorithm is investigated from the point of inference time reduction. Both natural and synthetic images are used for building codebooks and some analysis of synthetic images used for codebooks is provided. It is demonstrated the results on quality assessment may be improves with the use if synthetic images for codebook construction. We also demonstrate regimes of the algorithm in which real time execution on CPU is possible for sufficiently high correlations with mean opinion score (MOS). Various pooling strategies are considered as well as the problem of metric sensitivity to bitrate.

arXiv:2212.09501

NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution

In recent years, image and video delivery systems have begun integrating deep learning super-resolution (SR) approaches, leveraging their unprecedented visual enhancement capabilities while reducing reliance on networking conditions. Nevertheless, deploying these solutions on mobile devices still remains an active challenge as SR models are excessively demanding with respect to workload and memory footprint. Despite recent progress on on-device SR frameworks, existing systems either penalize visual quality, lead to excessive energy consumption or make inefficient use of the available resources. This work presents NAWQ-SR, a novel framework for the efficient on-device execution of SR models. Through a novel hybrid-precision quantization technique and a runtime neural image codec, NAWQ-SR exploits the multi-precision capabilities of modern mobile NPUs in order to minimize latency, while meeting user-specified quality constraints. Moreover, NAWQ-SR selectively adapts the arithmetic precision at run time to equip the SR DNN's layers with wider representational power, improving visual quality beyond what was previously possible on NPUs. Altogether, NAWQ-SR achieves an average speedup of 7.9x, 3x and 1.91x over the state-of-the-art on-device SR systems that use heterogeneous processors (MobiSR), CPU (SplitSR) and NPU (XLSR), respectively. Furthermore, NAWQ-SR delivers an average of 3.2x speedup and 0.39 dB higher PSNR over status-quo INT8 NPU designs, but most importantly mitigates the negative effects of quantization on visual quality, setting a new state-of-the-art in the attainable quality of NPU-based SR.

arXiv:2212.08985

Efficient Image Captioning for Edge Devices

Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie in the heavyweight visual feature extractors (i.e., object detectors) and complicated cross-modal fusion networks. To this end, we propose LightCap, a lightweight image captioner for resource-limited devices. The core design is built on the recent CLIP model for efficient image captioning. To be specific, on the one hand, we leverage the CLIP model to extract the compact grid features without relying on the time-consuming object detectors. On the other hand, we transfer the image-text retrieval design of CLIP to image captioning scenarios by devising a novel visual concept extractor and a cross-modal modulator. We further optimize the cross-modal fusion model and parallel prediction heads via sequential and ensemble distillations. With the carefully designed architecture, our model merely contains 40M parameters, saving the model size by more than 75% and the FLOPs by more than 98% in comparison with the current state-of-the-art methods. In spite of the low capacity, our model still exhibits state-of-the-art performance on prevalent datasets, e.g., 136.6 CIDEr on COCO Karpathy test split. Testing on the smartphone with only a single CPU, the proposed LightCap exhibits a fast inference speed of 188ms per image, which is ready for practical applications.

arXiv:2212.08046

Silhouette: Toward Performance-Conscious and Transferable CPU Embeddings

Learned embeddings are widely used to obtain concise data representation and enable transfer learning between different data sets and tasks. In this paper, we present Silhouette, our approach that leverages publicly-available performance data sets to learn CPU embeddings. We show how these embeddings enable transfer learning between data sets of different types and sizes. Each of these scenarios leads to an improvement in accuracy for the target data set.

arXiv:2212.06958

A Novel Active Solution for Two-Dimensional Face Presentation Attack Detection

Identity authentication is the process of verifying one's identity. There are several identity authentication methods, among which biometric authentication is of utmost importance. Facial recognition is a sort of biometric authentication with various applications, such as unlocking mobile phones and accessing bank accounts. However, presentation attacks pose the greatest threat to facial recognition. A presentation attack is an attempt to present a non-live face, such as a photo, video, mask, and makeup, to the camera. Presentation attack detection is a countermeasure that attempts to identify between a genuine user and a presentation attack. Several industries, such as financial services, healthcare, and education, use biometric authentication services on various devices. This illustrates the significance of presentation attack detection as the verification step. In this paper, we study state-of-the-art to cover the challenges and solutions related to presentation attack detection in a single place. We identify and classify different presentation attack types and identify the state-of-the-art methods that could be used to detect each of them. We compare the state-of-the-art literature regarding attack types, evaluation metrics, accuracy, and datasets and discuss research and industry challenges of presentation attack detection. Most presentation attack detection approaches rely on extensive data training and quality, making them difficult to implement. We introduce an efficient active presentation attack detection approach that overcomes weaknesses in the existing literature. The proposed approach does not require training data, is CPU-light, can process low-quality images, has been tested with users of various ages and is shown to be user-friendly and highly robust to 2-dimensional presentation attacks.

arXiv:2212.05271공식 코드 · Papers with Code

GPU-accelerated Guided Source Separation for Meeting Transcription

Guided source separation (GSS) is a type of target-speaker extraction method that relies on pre-computed speaker activities and blind source separation to perform front-end enhancement of overlapped speech signals. It was first proposed during the CHiME-5 challenge and provided significant improvements over the delay-and-sum beamforming baseline. Despite its strengths, however, the method has seen limited adoption for meeting transcription benchmarks primarily due to its high computation time. In this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-based pipelines, including batched processing of frequencies and segments, to provide 300x speed-up over CPU-based inference. The improved inference time allows us to perform detailed ablation studies over several parameters of the GSS algorithm -- such as context duration, number of channels, and noise class, to name a few. We provide end-to-end reproducible pipelines for speaker-attributed transcription of popular meeting benchmarks: LibriCSS, AMI, and AliMeeting. Our code and recipes are publicly available: https://github.com/desh2608/gss.

arXiv:2212.05339공식 코드 · Papers with Code

Elixir: Train a Large Language Model on a Small GPU Cluster

In recent years, large language models have achieved great success due to their unprecedented size. However, training these models poses a challenge for most researchers as it requires a substantial number of GPUs. To reduce GPU memory usage, memory partitioning, and memory offloading have been proposed. These approaches eliminate memory redundancies and offload memory usage to the CPU and NVMe memory, respectively, enabling training on small GPU clusters. However, directly deploying these solutions often leads to suboptimal efficiency. Only experienced experts can unleash the full potential of hardware by carefully tuning the distributed configuration. Thus, we present a novel solution, Elixir, which automates efficient large-model training based on pre-runtime model profiling. Elixir aims to identify the optimal combination of partitioning and offloading techniques to maximize training throughput. In our experiments, Elixir significantly outperforms the current state-of-the-art baseline. Our optimal configuration achieves up to a 3.4$\times$ speedup on GPT-2 models compared with SOTA solutions. We hope that our work will benefit individuals who lack computing resources and expertise, granting them access to large models. The beta version of Elixir is now available at https://github.com/hpcaitech/ColossalAI/tree/feature/elixir.

arXiv:2212.04180공식 코드 · Papers with Code

evosax: JAX-based Evolution Strategies

The deep learning revolution has greatly been accelerated by the 'hardware lottery': Recent advances in modern hardware accelerators and compilers paved the way for large-scale batch gradient optimization. Evolutionary optimization, on the other hand, has mainly relied on CPU-parallelism, e.g. using Dask scheduling and distributed multi-host infrastructure. Here we argue that also modern evolutionary computation can significantly benefit from the massive computational throughput provided by GPUs and TPUs. In order to better harness these resources and to enable the next generation of black-box optimization algorithms, we release evosax: A JAX-based library of evolution strategies which allows researchers to leverage powerful function transformations such as just-in-time compilation, automatic vectorization and hardware parallelization. evosax implements 30 evolutionary optimization algorithms including finite-difference-based, estimation-of-distribution evolution strategies and various genetic algorithms. Every single algorithm can directly be executed on hardware accelerators and automatically vectorized or parallelized across devices using a single line of code. It is designed in a modular fashion and allows for flexible usage via a simple ask-evaluate-tell API. We thereby hope to facilitate a new wave of scalable evolutionary optimization algorithms.

arXiv:2212.02197

Performance Quantification of a Nonlinear Model Predictive Controller by Parallel Monte Carlo Simulations of a Closed-loop System

This paper presents a parallel Monte Carlo simulation based performance quantification method for nonlinear model predictive control (NMPC) in closed-loop. The method provides distributions for the controller performance in stochastic systems enabling performance quantification. We perform high-performance Monte Carlo simulations in C enabled by a new thread-safe NMPC implementation in combination with an existing high-performance Monte Carlo simulation toolbox in C. We express the NMPC regulator as an optimal control problem (OCP), which we solve with the new thread-safe sequential quadratic programming software NLPSQP. Our results show almost linear scale-up for the NMPC closed-loop on a 32 core CPU. In particular, we get approximately 27 times speed-up on 32 cores. We demonstrate the performance quantification method on a simple continuous stirred tank reactor (CSTR), where we perform 30,000 closed-loop simulations with both an NMPC and a reference proportional-integral (PI) controller. Performance quantification of the stochastic closed-loop system shows that the NMPC outperforms the PI controller in both mean and variance.

arXiv:2212.01698

Precise Energy Consumption Measurements of Heterogeneous Artificial Intelligence Workloads

With the rise of AI in recent years and the increase in complexity of the models, the growing demand in computational resources is starting to pose a significant challenge. The need for higher compute power is being met with increasingly more potent accelerators and the use of large compute clusters. However, the gain in prediction accuracy from large models trained on distributed and accelerated systems comes at the price of a substantial increase in energy demand, and researchers have started questioning the environmental friendliness of such AI methods at scale. Consequently, energy efficiency plays an important role for AI model developers and infrastructure operators alike. The energy consumption of AI workloads depends on the model implementation and the utilized hardware. Therefore, accurate measurements of the power draw of AI workflows on different types of compute nodes is key to algorithmic improvements and the design of future compute clusters and hardware. To this end, we present measurements of the energy consumption of two typical applications of deep learning models on different types of compute nodes. Our results indicate that 1. deriving energy consumption directly from runtime is not accurate, but the consumption of the compute node needs to be considered regarding its composition; 2. neglecting accelerator hardware on mixed nodes results in overproportional inefficiency regarding energy consumption; 3. energy consumption of model training and inference should be considered separately - while training on GPUs outperforms all other node types regarding both runtime and energy consumption, inference on CPU nodes can be comparably efficient. One advantage of our approach is that the information on energy consumption is available to all users of the supercomputer, enabling an easy transfer to other workloads alongside a raise in user-awareness of energy consumption.

arXiv:2212.00827

Architectural Implications of Embedding Dimension during GCN on CPU and GPU

Graph Neural Networks (GNNs) are a class of neural networks designed to extract information from the graphical structure of data. Graph Convolutional Networks (GCNs) are a widely used type of GNN for transductive graph learning problems which apply convolution to learn information from graphs. GCN is a challenging algorithm from an architecture perspective due to inherent sparsity, low data reuse, and massive memory capacity requirements. Traditional neural algorithms exploit the high compute capacity of GPUs to achieve high performance for both inference and training. The architectural decision to use a GPU for GCN inference is a question explored in this work. GCN on both CPU and GPU was characterized in order to better understand the implications of graph size, embedding dimension, and sampling on performance.

arXiv:2212.00608

Exploiting Kernel Compression on BNNs

Binary Neural Networks (BNNs) are showing tremendous success on realistic image classification tasks. Notably, their accuracy is similar to the state-of-the-art accuracy obtained by full-precision models tailored to edge devices. In this regard, BNNs are very amenable to edge devices since they employ 1-bit to store the inputs and weights, and thus, their storage requirements are low. Also, BNNs computations are mainly done using xnor and pop-counts operations which are implemented very efficiently using simple hardware structures. Nonetheless, supporting BNNs efficiently on mobile CPUs is far from trivial since their benefits are hindered by frequent memory accesses to load weights and inputs. In BNNs, a weight or an input is stored using one bit, and aiming to increase storage and computation efficiency, several of them are packed together as a sequence of bits. In this work, we observe that the number of unique sequences representing a set of weights is typically low. Also, we have seen that during the evaluation of a BNN layer, a small group of unique sequences is employed more frequently than others. Accordingly, we propose exploiting this observation by using Huffman Encoding to encode the bit sequences and then using an indirection table to decode them during the BNN evaluation. Also, we propose a clustering scheme to identify the most common sequences of bits and replace the less common ones with some similar common sequences. Hence, we decrease the storage requirements and memory accesses since common sequences are encoded with fewer bits. We extend a mobile CPU by adding a small hardware structure that can efficiently cache and decode the compressed sequence of bits. We evaluate our scheme using the ReAacNet model with the Imagenet dataset. Our experimental results show that our technique can reduce memory requirement by 1.32x and improve performance by 1.35x.

arXiv:2211.17170공식 코드 · Papers with Code

How to Train an Accurate and Efficient Object Detection Model on Any Dataset

The rapidly evolving industry demands high accuracy of the models without the need for time-consuming and computationally expensive experiments required for fine-tuning. Moreover, a model and training pipeline, which was once carefully optimized for a specific dataset, rarely generalizes well to training on a different dataset. This makes it unrealistic to have carefully fine-tuned models for each use case. To solve this, we propose an alternative approach that also forms a backbone of Intel Geti platform: a dataset-agnostic template for object detection trainings, consisting of carefully chosen and pre-trained models together with a robust training pipeline for further training. Our solution works out-of-the-box and provides a strong baseline on a wide range of datasets. It can be used on its own or as a starting point for further fine-tuning for specific use cases when needed. We obtained dataset-agnostic templates by performing parallel training on a corpus of datasets and optimizing the choice of architectures and training tricks with respect to the average results on the whole corpora. We examined a number of architectures, taking into account the performance-accuracy trade-off. Consequently, we propose 3 finalists, VFNet, ATSS, and SSD, that can be deployed on CPU using the OpenVINO toolkit. The source code is available as a part of the OpenVINO Training Extensions (https://github.com/openvinotoolkit/training_extensions}

arXiv:2211.15739

CWD: A Machine Learning based Approach to Detect Unknown Cloud Workloads

Workloads in modern cloud data centers are becoming increasingly complex. The number of workloads running in cloud data centers has been growing exponentially for the last few years, and cloud service providers (CSP) have been supporting on-demand services in real-time. Realizing the growing complexity of cloud environment and cloud workloads, hardware vendors such as Intel and AMD are increasingly introducing cloud-specific workload acceleration features in their CPU platforms. These features are typically targeted towards popular and commonly-used cloud workloads. Nonetheless, uncommon, customer-specific workloads (unknown workloads), if their characteristics are different from common workloads (known workloads), may not realize the potential of the underlying platform. To address this problem of realizing the full potential of the underlying platform, we develop a machine learning based technique to characterize, profile and predict workloads running in the cloud environment. Experimental evaluation of our technique demonstrates good prediction performance. We also develop techniques to analyze the performance of the model in a standalone manner.

arXiv:2211.15444공식 코드 · Papers with Code

DAMO-YOLO : A Report on Real-Time Object Detection Design

In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series. DAMO-YOLO is extended from YOLO with some new technologies, including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement. In particular, we use MAE-NAS, a method guided by the principle of maximum entropy, to search our detection backbone under the constraints of low latency and high performance, producing ResNet/CSP-like structures with spatial pyramid pooling and focus modules. In the design of necks and heads, we follow the rule of ``large neck, small head''.We import Generalized-FPN with accelerated queen-fusion to build the detector neck and upgrade its CSPNet with efficient layer aggregation networks (ELAN) and reparameterization. Then we investigate how detector head size affects detection performance and find that a heavy neck with only one task projection layer would yield better results.In addition, AlignedOTA is proposed to solve the misalignment problem in label assignment. And a distillation schema is introduced to improve performance to a higher level. Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios. For general industry requirements, we propose DAMO-YOLO-T/S/M/L. They can achieve 43.6/47.7/50.2/51.9 mAPs on COCO with the latency of 2.78/3.83/5.62/7.95 ms on T4 GPUs respectively. Additionally, for edge devices with limited computing power, we have also proposed DAMO-YOLO-Ns/Nm/Nl lightweight models. They can achieve 32.3/38.2/40.5 mAPs on COCO with the latency of 4.08/5.05/6.69 ms on X86-CPU. Our proposed general and lightweight models have outperformed other YOLO series models in their respective application scenarios.

arXiv:2211.15082

DGI: Easy and Efficient Inference for GNNs

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to 94% of the time in the end-to-end training process due to neighbor explosion, which means that a node accesses its multi-hop neighbors. On the other hand, layer-wise inference avoids the neighbor explosion problem by conducting inference layer by layer such that the nodes only need their one-hop neighbors in each layer. However, implementing layer-wise inference requires substantial engineering efforts because users need to manually decompose a GNN model into layers for computation and split workload into batches to fit into device memory. In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution. DGI is general for various GNN models and different kinds of inference requests, and supports out-of-core execution on large graphs that cannot fit in CPU memory. Experimental results show that DGI consistently outperforms layer-wise inference across different datasets and hardware settings, and the speedup can be over 1,000x.